diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 194 | ||||
| -rw-r--r-- | mm/Makefile | 14 | ||||
| -rw-r--r-- | mm/backing-dev.c | 304 | ||||
| -rw-r--r-- | mm/balloon_compaction.c | 4 | ||||
| -rw-r--r-- | mm/bootmem.c | 55 | ||||
| -rw-r--r-- | mm/bounce.c | 301 | ||||
| -rw-r--r-- | mm/cleancache.c | 273 | ||||
| -rw-r--r-- | mm/compaction.c | 439 | ||||
| -rw-r--r-- | mm/dmapool.c | 31 | ||||
| -rw-r--r-- | mm/early_ioremap.c | 245 | ||||
| -rw-r--r-- | mm/fadvise.c | 38 | ||||
| -rw-r--r-- | mm/filemap.c | 1354 | ||||
| -rw-r--r-- | mm/filemap_xip.c | 5 | ||||
| -rw-r--r-- | mm/fremap.c | 86 | ||||
| -rw-r--r-- | mm/frontswap.c | 169 | ||||
| -rw-r--r-- | mm/gup.c | 662 | ||||
| -rw-r--r-- | mm/huge_memory.c | 1008 | ||||
| -rw-r--r-- | mm/hugetlb.c | 1652 | ||||
| -rw-r--r-- | mm/hugetlb_cgroup.c | 115 | ||||
| -rw-r--r-- | mm/hwpoison-inject.c | 11 | ||||
| -rw-r--r-- | mm/internal.h | 85 | ||||
| -rw-r--r-- | mm/iov_iter.c | 743 | ||||
| -rw-r--r-- | mm/kmemleak-test.c | 36 | ||||
| -rw-r--r-- | mm/kmemleak.c | 200 | ||||
| -rw-r--r-- | mm/ksm.c | 810 | ||||
| -rw-r--r-- | mm/list_lru.c | 152 | ||||
| -rw-r--r-- | mm/madvise.c | 154 | ||||
| -rw-r--r-- | mm/memblock.c | 784 | ||||
| -rw-r--r-- | mm/memcontrol.c | 3311 | ||||
| -rw-r--r-- | mm/memory-failure.c | 538 | ||||
| -rw-r--r-- | mm/memory.c | 1652 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 906 | ||||
| -rw-r--r-- | mm/mempolicy.c | 475 | ||||
| -rw-r--r-- | mm/mempool.c | 14 | ||||
| -rw-r--r-- | mm/migrate.c | 619 | ||||
| -rw-r--r-- | mm/mincore.c | 30 | ||||
| -rw-r--r-- | mm/mlock.c | 461 | ||||
| -rw-r--r-- | mm/mm_init.c | 81 | ||||
| -rw-r--r-- | mm/mmap.c | 688 | ||||
| -rw-r--r-- | mm/mmu_context.c | 6 | ||||
| -rw-r--r-- | mm/mmu_notifier.c | 72 | ||||
| -rw-r--r-- | mm/mmzone.c | 20 | ||||
| -rw-r--r-- | mm/mprotect.c | 161 | ||||
| -rw-r--r-- | mm/mremap.c | 70 | ||||
| -rw-r--r-- | mm/msync.c | 9 | ||||
| -rw-r--r-- | mm/nobootmem.c | 116 | ||||
| -rw-r--r-- | mm/nommu.c | 192 | ||||
| -rw-r--r-- | mm/oom_kill.c | 90 | ||||
| -rw-r--r-- | mm/page-writeback.c | 421 | ||||
| -rw-r--r-- | mm/page_alloc.c | 1561 | ||||
| -rw-r--r-- | mm/page_cgroup.c | 19 | ||||
| -rw-r--r-- | mm/page_io.c | 143 | ||||
| -rw-r--r-- | mm/page_isolation.c | 22 | ||||
| -rw-r--r-- | mm/pagewalk.c | 72 | ||||
| -rw-r--r-- | mm/percpu.c | 257 | ||||
| -rw-r--r-- | mm/pgtable-generic.c | 53 | ||||
| -rw-r--r-- | mm/process_vm_access.c | 280 | ||||
| -rw-r--r-- | mm/readahead.c | 73 | ||||
| -rw-r--r-- | mm/rmap.c | 775 | ||||
| -rw-r--r-- | mm/shmem.c | 531 | ||||
| -rw-r--r-- | mm/slab.c | 1622 | ||||
| -rw-r--r-- | mm/slab.h | 148 | ||||
| -rw-r--r-- | mm/slab_common.c | 499 | ||||
| -rw-r--r-- | mm/slob.c | 47 | ||||
| -rw-r--r-- | mm/slub.c | 933 | ||||
| -rw-r--r-- | mm/sparse-vmemmap.c | 33 | ||||
| -rw-r--r-- | mm/sparse.c | 293 | ||||
| -rw-r--r-- | mm/swap.c | 576 | ||||
| -rw-r--r-- | mm/swap_state.c | 167 | ||||
| -rw-r--r-- | mm/swapfile.c | 974 | ||||
| -rw-r--r-- | mm/truncate.c | 279 | ||||
| -rw-r--r-- | mm/util.c | 135 | ||||
| -rw-r--r-- | mm/vmacache.c | 132 | ||||
| -rw-r--r-- | mm/vmalloc.c | 488 | ||||
| -rw-r--r-- | mm/vmpressure.c | 380 | ||||
| -rw-r--r-- | mm/vmscan.c | 1555 | ||||
| -rw-r--r-- | mm/vmstat.c | 158 | ||||
| -rw-r--r-- | mm/workingset.c | 414 | ||||
| -rw-r--r-- | mm/zbud.c | 527 | ||||
| -rw-r--r-- | mm/zsmalloc.c | 1117 | ||||
| -rw-r--r-- | mm/zswap.c | 940 |
81 files changed, 23051 insertions, 12008 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 278e3ab1f16..3e9977a9d65 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1,6 +1,6 @@ config SELECT_MEMORY_MODEL def_bool y - depends on EXPERIMENTAL || ARCH_SELECT_MEMORY_MODEL + depends on ARCH_SELECT_MEMORY_MODEL choice prompt "Memory model" @@ -20,7 +20,7 @@ config FLATMEM_MANUAL Some users of more advanced features like NUMA and memory hotplug may have different options here. - DISCONTIGMEM is an more mature, better tested system, + DISCONTIGMEM is a more mature, better tested system, but is incompatible with memory hotplug and may suffer decreased performance over SPARSEMEM. If unsure between "Sparse Memory" and "Discontiguous Memory", choose @@ -134,6 +134,9 @@ config HAVE_MEMBLOCK config HAVE_MEMBLOCK_NODE_MAP boolean +config HAVE_MEMBLOCK_PHYS_MAP + boolean + config ARCH_DISCARD_MEMBLOCK boolean @@ -153,21 +156,34 @@ config MOVABLE_NODE help Allow a node to have only movable memory. Pages used by the kernel, such as direct mapping pages cannot be migrated. So the corresponding - memory device cannot be hotplugged. This option allows users to - online all the memory of a node as movable memory so that the whole - node can be hotplugged. Users who don't use the memory hotplug - feature are fine with this option on since they don't online memory - as movable. + memory device cannot be hotplugged. This option allows the following + two things: + - When the system is booting, node full of hotpluggable memory can + be arranged to have only movable memory so that the whole node can + be hot-removed. (need movable_node boot option specified). + - After the system is up, the option allows users to online all the + memory of a node as movable memory so that the whole node can be + hot-removed. + + Users who don't use the memory hotplug feature are fine with this + option on since they don't specify movable_node boot option or they + don't online memory as movable. Say Y here if you want to hotplug a whole node. Say N here if you want kernel to use memory on all nodes evenly. +# +# Only be set on architectures that have completely implemented memory hotplug +# feature. If you are not sure, don't touch it. +# +config HAVE_BOOTMEM_INFO_NODE + def_bool n + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" - select MEMORY_ISOLATION depends on SPARSEMEM || X86_64_ACPI_NUMA - depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG + depends on ARCH_ENABLE_MEMORY_HOTPLUG depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390) config MEMORY_HOTPLUG_SPARSE @@ -176,6 +192,8 @@ config MEMORY_HOTPLUG_SPARSE config MEMORY_HOTREMOVE bool "Allow for memory hot remove" + select MEMORY_ISOLATION + select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE depends on MIGRATION @@ -201,11 +219,14 @@ config PAGEFLAGS_EXTENDED # config SPLIT_PTLOCK_CPUS int + default "999999" if !MMU default "999999" if ARM && !CPU_CACHE_VIPT default "999999" if PARISC && !PA20 - default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC default "4" +config ARCH_ENABLE_SPLIT_PMD_PTLOCK + boolean + # # support for memory balloon compaction config BALLOON_COMPACTION @@ -237,7 +258,7 @@ config COMPACTION config MIGRATION bool "Page migration" def_bool y - depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA + depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU help Allows the migration of the physical location of pages of processes while the virtual addresses are not changed. This is useful in @@ -246,6 +267,9 @@ config MIGRATION pages as migration can relocate pages to satisfy a huge page allocation instead of reclaiming. +config ARCH_ENABLE_HUGEPAGE_MIGRATION + boolean + config PHYS_ADDR_T_64BIT def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT @@ -255,8 +279,27 @@ config ZONE_DMA_FLAG default "1" config BOUNCE - def_bool y + bool "Enable bounce buffers" + default y depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM) + help + Enable bounce buffers for devices that cannot access + the full range of memory available to the CPU. Enabled + by default when ZONE_DMA or HIGHMEM is selected, but you + may say n to override this. + +# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often +# have more than 4GB of memory, but we don't currently use the IOTLB to present +# a 32-bit address to OHCI. So we need to use a bounce pool instead. +# +# We also use the bounce pool to provide stable page writes for jbd. jbd +# initiates buffer writeback without locking the page or setting PG_writeback, +# and fixing that behavior (a second time; jbd2 doesn't have this problem) is +# a major rework effort. Instead, use the bounce buffer to snapshot pages +# (until jbd goes away). The only jbd user is ext3. +config NEED_BOUNCE_POOL + bool + default y if (TILE && USB_OHCI_HCD) || (BLK_DEV_INTEGRITY && JBD) config NR_QUICK int @@ -265,8 +308,12 @@ config NR_QUICK default "1" config VIRT_TO_BUS - def_bool y - depends on !ARCH_NO_VIRT_TO_BUS + bool + help + An architecture should select this if it implements the + deprecated interface virt_to_bus(). All new architectures + should probably not select this. + config MMU_NOTIFIER bool @@ -389,16 +436,6 @@ choice benefit. endchoice -config CROSS_MEMORY_ATTACH - bool "Cross Memory Support" - depends on MMU - default y - help - Enabling this option adds the system calls process_vm_readv and - process_vm_writev which allow a process with the correct privileges - to directly read from or write to to another process's address space. - See the man page for more details. - # # UP and nommu archs use km based percpu allocator # @@ -446,3 +483,112 @@ config FRONTSWAP and swap data is stored as normal on the matching swap device. If unsure, say Y to enable frontswap. + +config CMA + bool "Contiguous Memory Allocator" + depends on HAVE_MEMBLOCK && MMU + select MIGRATION + select MEMORY_ISOLATION + help + This enables the Contiguous Memory Allocator which allows other + subsystems to allocate big physically-contiguous blocks of memory. + CMA reserves a region of memory and allows only movable pages to + be allocated from it. This way, the kernel can use the memory for + pagecache and when a subsystem requests for contiguous area, the + allocated pages are migrated away to serve the contiguous request. + + If unsure, say "n". + +config CMA_DEBUG + bool "CMA debug messages (DEVELOPMENT)" + depends on DEBUG_KERNEL && CMA + help + Turns on debug messages in CMA. This produces KERN_DEBUG + messages for every CMA call as well as various messages while + processing calls such as dma_alloc_from_contiguous(). + This option does not affect warning and error messages. + +config ZBUD + tristate + default n + help + A special purpose allocator for storing compressed pages. + It is designed to store up to two compressed pages per physical + page. While this design limits storage density, it has simple and + deterministic reclaim properties that make it preferable to a higher + density approach when reclaim will be used. + +config ZSWAP + bool "Compressed cache for swap pages (EXPERIMENTAL)" + depends on FRONTSWAP && CRYPTO=y + select CRYPTO_LZO + select ZBUD + default n + help + A lightweight compressed cache for swap pages. It takes + pages that are in the process of being swapped out and attempts to + compress them into a dynamically allocated RAM-based memory pool. + This can result in a significant I/O reduction on swap device and, + in the case where decompressing from RAM is faster that swap device + reads, can also improve workload performance. + + This is marked experimental because it is a new feature (as of + v3.11) that interacts heavily with memory reclaim. While these + interactions don't cause any known issues on simple memory setups, + they have not be fully explored on the large set of potential + configurations and workloads that exist. + +config MEM_SOFT_DIRTY + bool "Track memory changes" + depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS + select PROC_PAGE_MONITOR + help + This option enables memory changes tracking by introducing a + soft-dirty bit on pte-s. This bit it set when someone writes + into a page just as regular dirty bit, but unlike the latter + it can be cleared by hands. + + See Documentation/vm/soft-dirty.txt for more details. + +config ZSMALLOC + tristate "Memory allocator for compressed pages" + depends on MMU + default n + help + zsmalloc is a slab-based memory allocator designed to store + compressed RAM pages. zsmalloc uses virtual memory mapping + in order to reduce fragmentation. However, this results in a + non-standard allocator interface where a handle, not a pointer, is + returned by an alloc(). This handle must be mapped in order to + access the allocated space. + +config PGTABLE_MAPPING + bool "Use page table mapping to access object in zsmalloc" + depends on ZSMALLOC + help + By default, zsmalloc uses a copy-based object mapping method to + access allocations that span two pages. However, if a particular + architecture (ex, ARM) performs VM mapping faster than copying, + then you should select this. This causes zsmalloc to use page table + mapping rather than copying for object mapping. + + You can check speed with zsmalloc benchmark: + https://github.com/spartacus06/zsmapbench + +config GENERIC_EARLY_IOREMAP + bool + +config MAX_STACK_SIZE_MB + int "Maximum user stack size for 32-bit processes (MB)" + default 80 + range 8 256 if METAG + range 8 2048 + depends on STACK_GROWSUP && (!64BIT || COMPAT) + help + This is the maximum stack size in Megabytes in the VM layout of 32-bit + user processes when the stack grows upwards (currently only on parisc + and metag arch). The stack will be located at the highest memory + address minus the given value, unless the RLIMIT_STACK hard limit is + changed to a smaller value in which case that is used. + + A sane initial value is 80 MB. diff --git a/mm/Makefile b/mm/Makefile index 3a4628751f8..4064f3ec145 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -3,7 +3,7 @@ # mmu-y := nommu.o -mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ +mmu-$(CONFIG_MMU) := fremap.o gup.o highmem.o madvise.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ vmalloc.o pagewalk.o pgtable-generic.o @@ -16,8 +16,9 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o balloon_compaction.o \ - interval_tree.o $(mmu-y) + compaction.o balloon_compaction.o vmacache.o \ + interval_tree.o list_lru.o workingset.o \ + iov_iter.o $(mmu-y) obj-y += init-mm.o @@ -29,9 +30,9 @@ endif obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o -obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o obj-$(CONFIG_FRONTSWAP) += frontswap.o +obj-$(CONFIG_ZSWAP) += zswap.o obj-$(CONFIG_HAS_DMA) += dmapool.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o obj-$(CONFIG_NUMA) += mempolicy.o @@ -50,7 +51,7 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o -obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o +obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o @@ -58,3 +59,6 @@ obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o +obj-$(CONFIG_ZBUD) += zbud.o +obj-$(CONFIG_ZSMALLOC) += zsmalloc.o +obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d3ca2b3ee17..1706cbbdf5f 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -31,13 +31,14 @@ EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; /* - * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as - * reader side protection for bdi_pending_list. bdi_list has RCU reader side + * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side * locking. */ DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); -LIST_HEAD(bdi_pending_list); + +/* bdi_wq serves all asynchronous writeback tasks */ +struct workqueue_struct *bdi_wq; void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2) { @@ -179,7 +180,8 @@ static ssize_t name##_show(struct device *dev, \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr); \ -} +} \ +static DEVICE_ATTR_RW(name); BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) @@ -221,14 +223,25 @@ static ssize_t max_ratio_store(struct device *dev, } BDI_SHOW(max_ratio, bdi->max_ratio) -#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store) +static ssize_t stable_pages_required_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); -static struct device_attribute bdi_dev_attrs[] = { - __ATTR_RW(read_ahead_kb), - __ATTR_RW(min_ratio), - __ATTR_RW(max_ratio), - __ATTR_NULL, + return snprintf(page, PAGE_SIZE-1, "%d\n", + bdi_cap_stable_pages_required(bdi) ? 1 : 0); +} +static DEVICE_ATTR_RO(stable_pages_required); + +static struct attribute *bdi_dev_attrs[] = { + &dev_attr_read_ahead_kb.attr, + &dev_attr_min_ratio.attr, + &dev_attr_max_ratio.attr, + &dev_attr_stable_pages_required.attr, + NULL, }; +ATTRIBUTE_GROUPS(bdi_dev); static __init int bdi_class_init(void) { @@ -236,7 +249,7 @@ static __init int bdi_class_init(void) if (IS_ERR(bdi_class)) return PTR_ERR(bdi_class); - bdi_class->dev_attrs = bdi_dev_attrs; + bdi_class->dev_groups = bdi_dev_groups; bdi_debug_init(); return 0; } @@ -246,6 +259,11 @@ static int __init default_bdi_init(void) { int err; + bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE | + WQ_UNBOUND | WQ_SYSFS, 0); + if (!bdi_wq) + return -ENOMEM; + err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); @@ -260,26 +278,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) return wb_has_dirty_io(&bdi->wb); } -static void wakeup_timer_fn(unsigned long data) -{ - struct backing_dev_info *bdi = (struct backing_dev_info *)data; - - spin_lock_bh(&bdi->wb_lock); - if (bdi->wb.task) { - trace_writeback_wake_thread(bdi); - wake_up_process(bdi->wb.task); - } else if (bdi->dev) { - /* - * When bdi tasks are inactive for long time, they are killed. - * In this case we have to wake-up the forker thread which - * should create and run the bdi thread. - */ - trace_writeback_wake_forker_thread(bdi); - wake_up_process(default_backing_dev_info.wb.task); - } - spin_unlock_bh(&bdi->wb_lock); -} - /* * This function is used when the first inode for this bdi is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the @@ -290,182 +288,19 @@ static void wakeup_timer_fn(unsigned long data) * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. + * + * We have to be careful not to postpone flush work if it is scheduled for + * earlier. Thus we use queue_delayed_work(). */ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); - mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout); -} - -/* - * Calculate the longest interval (jiffies) bdi threads are allowed to be - * inactive. - */ -static unsigned long bdi_longest_inactive(void) -{ - unsigned long interval; - - interval = msecs_to_jiffies(dirty_writeback_interval * 10); - return max(5UL * 60 * HZ, interval); -} - -/* - * Clear pending bit and wakeup anybody waiting for flusher thread creation or - * shutdown - */ -static void bdi_clear_pending(struct backing_dev_info *bdi) -{ - clear_bit(BDI_pending, &bdi->state); - smp_mb__after_clear_bit(); - wake_up_bit(&bdi->state, BDI_pending); -} - -static int bdi_forker_thread(void *ptr) -{ - struct bdi_writeback *me = ptr; - - current->flags |= PF_SWAPWRITE; - set_freezable(); - - /* - * Our parent may run at a different priority, just set us to normal - */ - set_user_nice(current, 0); - - for (;;) { - struct task_struct *task = NULL; - struct backing_dev_info *bdi; - enum { - NO_ACTION, /* Nothing to do */ - FORK_THREAD, /* Fork bdi thread */ - KILL_THREAD, /* Kill inactive bdi thread */ - } action = NO_ACTION; - - /* - * Temporary measure, we want to make sure we don't see - * dirty data on the default backing_dev_info - */ - if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) { - del_timer(&me->wakeup_timer); - wb_do_writeback(me, 0); - } - - spin_lock_bh(&bdi_lock); - /* - * In the following loop we are going to check whether we have - * some work to do without any synchronization with tasks - * waking us up to do work for them. Set the task state here - * so that we don't miss wakeups after verifying conditions. - */ - set_current_state(TASK_INTERRUPTIBLE); - - list_for_each_entry(bdi, &bdi_list, bdi_list) { - bool have_dirty_io; - - if (!bdi_cap_writeback_dirty(bdi) || - bdi_cap_flush_forker(bdi)) - continue; - - WARN(!test_bit(BDI_registered, &bdi->state), - "bdi %p/%s is not registered!\n", bdi, bdi->name); - - have_dirty_io = !list_empty(&bdi->work_list) || - wb_has_dirty_io(&bdi->wb); - - /* - * If the bdi has work to do, but the thread does not - * exist - create it. - */ - if (!bdi->wb.task && have_dirty_io) { - /* - * Set the pending bit - if someone will try to - * unregister this bdi - it'll wait on this bit. - */ - set_bit(BDI_pending, &bdi->state); - action = FORK_THREAD; - break; - } - - spin_lock(&bdi->wb_lock); - - /* - * If there is no work to do and the bdi thread was - * inactive long enough - kill it. The wb_lock is taken - * to make sure no-one adds more work to this bdi and - * wakes the bdi thread up. - */ - if (bdi->wb.task && !have_dirty_io && - time_after(jiffies, bdi->wb.last_active + - bdi_longest_inactive())) { - task = bdi->wb.task; - bdi->wb.task = NULL; - spin_unlock(&bdi->wb_lock); - set_bit(BDI_pending, &bdi->state); - action = KILL_THREAD; - break; - } - spin_unlock(&bdi->wb_lock); - } - spin_unlock_bh(&bdi_lock); - - /* Keep working if default bdi still has things to do */ - if (!list_empty(&me->bdi->work_list)) - __set_current_state(TASK_RUNNING); - - switch (action) { - case FORK_THREAD: - __set_current_state(TASK_RUNNING); - task = kthread_create(bdi_writeback_thread, &bdi->wb, - "flush-%s", dev_name(bdi->dev)); - if (IS_ERR(task)) { - /* - * If thread creation fails, force writeout of - * the bdi from the thread. Hopefully 1024 is - * large enough for efficient IO. - */ - writeback_inodes_wb(&bdi->wb, 1024, - WB_REASON_FORKER_THREAD); - } else { - /* - * The spinlock makes sure we do not lose - * wake-ups when racing with 'bdi_queue_work()'. - * And as soon as the bdi thread is visible, we - * can start it. - */ - spin_lock_bh(&bdi->wb_lock); - bdi->wb.task = task; - spin_unlock_bh(&bdi->wb_lock); - wake_up_process(task); - } - bdi_clear_pending(bdi); - break; - - case KILL_THREAD: - __set_current_state(TASK_RUNNING); - kthread_stop(task); - bdi_clear_pending(bdi); - break; - - case NO_ACTION: - if (!wb_has_dirty_io(me) || !dirty_writeback_interval) - /* - * There are no dirty data. The only thing we - * should now care about is checking for - * inactive bdi threads and killing them. Thus, - * let's sleep for longer time, save energy and - * be friendly for battery-driven devices. - */ - schedule_timeout(bdi_longest_inactive()); - else - schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10)); - try_to_freeze(); - break; - } - } - - return 0; + spin_lock_bh(&bdi->wb_lock); + if (test_bit(BDI_registered, &bdi->state)) + queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout); + spin_unlock_bh(&bdi->wb_lock); } /* @@ -497,20 +332,6 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, bdi->dev = dev; - /* - * Just start the forker thread for our default backing_dev_info, - * and add other bdi's to the list. They will get a thread created - * on-demand when they need it. - */ - if (bdi_cap_flush_forker(bdi)) { - struct bdi_writeback *wb = &bdi->wb; - - wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s", - dev_name(dev)); - if (IS_ERR(wb->task)) - return PTR_ERR(wb->task); - } - bdi_debug_register(bdi, dev_name(dev)); set_bit(BDI_registered, &bdi->state); @@ -534,8 +355,6 @@ EXPORT_SYMBOL(bdi_register_dev); */ static void bdi_wb_shutdown(struct backing_dev_info *bdi) { - struct task_struct *task; - if (!bdi_cap_writeback_dirty(bdi)) return; @@ -544,23 +363,26 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) */ bdi_remove_from_list(bdi); + /* Make sure nobody queues further work */ + spin_lock_bh(&bdi->wb_lock); + clear_bit(BDI_registered, &bdi->state); + spin_unlock_bh(&bdi->wb_lock); + /* - * If setup is pending, wait for that to complete first + * Drain work list and shutdown the delayed_work. At this point, + * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi + * is dying and its work_list needs to be drained no matter what. */ - wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait, - TASK_UNINTERRUPTIBLE); + mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + flush_delayed_work(&bdi->wb.dwork); + WARN_ON(!list_empty(&bdi->work_list)); /* - * Finally, kill the kernel thread. We don't need to be RCU - * safe anymore, since the bdi is gone from visibility. + * This shouldn't be necessary unless @bdi for some reason has + * unflushed dirty IO after work_list is drained. Do it anyway + * just in case. */ - spin_lock_bh(&bdi->wb_lock); - task = bdi->wb.task; - bdi->wb.task = NULL; - spin_unlock_bh(&bdi->wb_lock); - - if (task) - kthread_stop(task); + cancel_delayed_work_sync(&bdi->wb.dwork); } /* @@ -586,10 +408,8 @@ void bdi_unregister(struct backing_dev_info *bdi) bdi_set_min_ratio(bdi, 0); trace_writeback_bdi_unregister(bdi); bdi_prune_sb(bdi); - del_timer_sync(&bdi->wb.wakeup_timer); - if (!bdi_cap_flush_forker(bdi)) - bdi_wb_shutdown(bdi); + bdi_wb_shutdown(bdi); bdi_debug_unregister(bdi); spin_lock_bh(&bdi->wb_lock); @@ -611,7 +431,7 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); spin_lock_init(&wb->list_lock); - setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi); + INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn); } /* @@ -684,12 +504,11 @@ void bdi_destroy(struct backing_dev_info *bdi) bdi_unregister(bdi); /* - * If bdi_unregister() had already been called earlier, the - * wakeup_timer could still be armed because bdi_prune_sb() - * can race with the bdi_wakeup_thread_delayed() calls from - * __mark_inode_dirty(). + * If bdi_unregister() had already been called earlier, the dwork + * could still be pending because bdi_prune_sb() can race with the + * bdi_wakeup_thread_delayed() calls from __mark_inode_dirty(). */ - del_timer_sync(&bdi->wb.wakeup_timer); + cancel_delayed_work_sync(&bdi->wb.dwork); for (i = 0; i < NR_BDI_STAT_ITEMS; i++) percpu_counter_destroy(&bdi->bdi_stat[i]); @@ -705,7 +524,6 @@ EXPORT_SYMBOL(bdi_destroy); int bdi_setup_and_register(struct backing_dev_info *bdi, char *name, unsigned int cap) { - char tmp[32]; int err; bdi->name = name; @@ -714,8 +532,8 @@ int bdi_setup_and_register(struct backing_dev_info *bdi, char *name, if (err) return err; - sprintf(tmp, "%.28s%s", name, "-%d"); - err = bdi_register(bdi, NULL, tmp, atomic_long_inc_return(&bdi_seq)); + err = bdi_register(bdi, NULL, "%.28s-%ld", name, + atomic_long_inc_return(&bdi_seq)); if (err) { bdi_destroy(bdi); return err; @@ -739,7 +557,7 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync) bit = sync ? BDI_sync_congested : BDI_async_congested; if (test_and_clear_bit(bit, &bdi->state)) atomic_dec(&nr_bdi_congested[sync]); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); if (waitqueue_active(wqh)) wake_up(wqh); } @@ -842,7 +660,7 @@ int pdflush_proc_obsolete(struct ctl_table *table, int write, { char kbuf[] = "0\n"; - if (*ppos) { + if (*ppos || *lenp < sizeof(kbuf)) { *lenp = 0; return 0; } diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 07dbc8ec46c..6e45a5074bf 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -267,7 +267,7 @@ void balloon_page_putback(struct page *page) put_page(page); } else { WARN_ON(1); - dump_page(page); + dump_page(page, "not movable balloon page"); } unlock_page(page); } @@ -287,7 +287,7 @@ int balloon_page_migrate(struct page *newpage, BUG_ON(!trylock_page(newpage)); if (WARN_ON(!__is_movable_balloon_page(page))) { - dump_page(page); + dump_page(page, "not movable balloon page"); unlock_page(newpage); return rc; } diff --git a/mm/bootmem.c b/mm/bootmem.c index b93376c39b6..90bd3507b41 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -172,11 +172,12 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size) static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) { struct page *page; - unsigned long start, end, pages, count = 0; + unsigned long *map, start, end, pages, count = 0; if (!bdata->node_bootmem_map) return 0; + map = bdata->node_bootmem_map; start = bdata->node_min_pfn; end = bdata->node_low_pfn; @@ -184,10 +185,9 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) bdata - bootmem_node_data, start, end); while (start < end) { - unsigned long *map, idx, vec; + unsigned long idx, vec; unsigned shift; - map = bdata->node_bootmem_map; idx = start - bdata->node_min_pfn; shift = idx & (BITS_PER_LONG - 1); /* @@ -241,33 +241,26 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) return count; } -static void reset_node_lowmem_managed_pages(pg_data_t *pgdat) +static int reset_managed_pages_done __initdata; + +static inline void __init reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; - /* - * In free_area_init_core(), highmem zone's managed_pages is set to - * present_pages, and bootmem allocator doesn't allocate from highmem - * zones. So there's no need to recalculate managed_pages because all - * highmem pages will be managed by the buddy system. Here highmem - * zone also includes highmem movable zone. - */ + if (reset_managed_pages_done) + return; + for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) - if (!is_highmem(z)) - z->managed_pages = 0; + z->managed_pages = 0; } -/** - * free_all_bootmem_node - release a node's free pages to the buddy allocator - * @pgdat: node to be released - * - * Returns the number of pages actually released. - */ -unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) +void __init reset_all_zones_managed_pages(void) { - register_page_bootmem_info_node(pgdat); - reset_node_lowmem_managed_pages(pgdat); - return free_all_bootmem_core(pgdat->bdata); + struct pglist_data *pgdat; + + for_each_online_pgdat(pgdat) + reset_node_managed_pages(pgdat); + reset_managed_pages_done = 1; } /** @@ -279,14 +272,14 @@ unsigned long __init free_all_bootmem(void) { unsigned long total_pages = 0; bootmem_data_t *bdata; - struct pglist_data *pgdat; - for_each_online_pgdat(pgdat) - reset_node_lowmem_managed_pages(pgdat); + reset_all_zones_managed_pages(); list_for_each_entry(bdata, &bdata_list, list) total_pages += free_all_bootmem_core(bdata); + totalram_pages += total_pages; + return total_pages; } @@ -791,7 +784,7 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); /* update goal according ...MAX_DMA32_PFN */ - end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages; + end_pfn = pgdat_end_pfn(pgdat); if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) && (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) { @@ -833,6 +826,14 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); } +void * __init __alloc_bootmem_low_nopanic(unsigned long size, + unsigned long align, + unsigned long goal) +{ + return ___alloc_bootmem_nopanic(size, align, goal, + ARCH_LOW_ADDRESS_LIMIT); +} + /** * __alloc_bootmem_low_node - allocate low boot memory from a specific node * @pgdat: node to allocate from diff --git a/mm/bounce.c b/mm/bounce.c deleted file mode 100644 index 04208677556..00000000000 --- a/mm/bounce.c +++ /dev/null @@ -1,301 +0,0 @@ -/* bounce buffer handling for block devices - * - * - Split from highmem.c - */ - -#include <linux/mm.h> -#include <linux/export.h> -#include <linux/swap.h> -#include <linux/gfp.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/bootmem.h> -#include <asm/tlbflush.h> - -#include <trace/events/block.h> - -#define POOL_SIZE 64 -#define ISA_POOL_SIZE 16 - -static mempool_t *page_pool, *isa_page_pool; - -#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL) -static __init int init_emergency_pool(void) -{ -#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG) - if (max_pfn <= max_low_pfn) - return 0; -#endif - - page_pool = mempool_create_page_pool(POOL_SIZE, 0); - BUG_ON(!page_pool); - printk("bounce pool size: %d pages\n", POOL_SIZE); - - return 0; -} - -__initcall(init_emergency_pool); -#endif - -#ifdef CONFIG_HIGHMEM -/* - * 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); - memcpy(vto + to->bv_offset, vfrom, to->bv_len); - kunmap_atomic(vto); - 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; - - bounce_copy_vec(tovec, vfrom); - flush_dcache_page(tovec->bv_page); - } -} - -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, err); - bio_put(bio); -} - -static void bounce_end_io_write(struct bio *bio, int err) -{ - bounce_end_io(bio, page_pool, err); -} - -static void bounce_end_io_write_isa(struct bio *bio, int err) -{ - - bounce_end_io(bio, isa_page_pool, err); -} - -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 void bounce_end_io_read(struct bio *bio, int err) -{ - __bounce_end_io_read(bio, page_pool, err); -} - -static void bounce_end_io_read_isa(struct bio *bio, int err) -{ - __bounce_end_io_read(bio, isa_page_pool, err); -} - -static void __blk_queue_bounce(struct request_queue *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) <= queue_bounce_pfn(q)) - continue; - - /* - * irk, bounce it - */ - if (!bio) { - unsigned int cnt = (*bio_orig)->bi_vcnt; - - bio = bio_alloc(GFP_NOIO, cnt); - memset(bio->bi_io_vec, 0, cnt * sizeof(struct bio_vec)); - } - - - 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; - - trace_block_bio_bounce(q, *bio_orig); - - /* - * 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(struct request_queue *q, struct bio **bio_orig) -{ - mempool_t *pool; - - /* - * Data-less bio, nothing to bounce - */ - if (!bio_has_data(*bio_orig)) - return; - - /* - * 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 (queue_bounce_pfn(q) >= blk_max_pfn) - return; - pool = page_pool; - } else { - BUG_ON(!isa_page_pool); - pool = isa_page_pool; - } - - /* - * slow path - */ - __blk_queue_bounce(q, bio_orig, pool); -} - -EXPORT_SYMBOL(blk_queue_bounce); diff --git a/mm/cleancache.c b/mm/cleancache.c index 32e6f4136fa..d0eac435040 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -19,20 +19,10 @@ #include <linux/cleancache.h> /* - * This global enablement flag may be read thousands of times per second - * by cleancache_get/put/invalidate even on systems where cleancache_ops - * is not claimed (e.g. cleancache is config'ed on but remains - * disabled), so is preferred to the slower alternative: a function - * call that checks a non-global. - */ -int cleancache_enabled __read_mostly; -EXPORT_SYMBOL(cleancache_enabled); - -/* * cleancache_ops is set by cleancache_ops_register to contain the pointers * to the cleancache "backend" implementation functions. */ -static struct cleancache_ops cleancache_ops __read_mostly; +static struct cleancache_ops *cleancache_ops __read_mostly; /* * Counters available via /sys/kernel/debug/frontswap (if debugfs is @@ -45,15 +35,101 @@ static u64 cleancache_puts; static u64 cleancache_invalidates; /* - * register operations for cleancache, returning previous thus allowing - * detection of multiple backends and possible nesting + * When no backend is registered all calls to init_fs and init_shared_fs + * are registered and fake poolids (FAKE_FS_POOLID_OFFSET or + * FAKE_SHARED_FS_POOLID_OFFSET, plus offset in the respective array + * [shared_|]fs_poolid_map) are given to the respective super block + * (sb->cleancache_poolid) and no tmem_pools are created. When a backend + * registers with cleancache the previous calls to init_fs and init_shared_fs + * are executed to create tmem_pools and set the respective poolids. While no + * backend is registered all "puts", "gets" and "flushes" are ignored or failed. + */ +#define MAX_INITIALIZABLE_FS 32 +#define FAKE_FS_POOLID_OFFSET 1000 +#define FAKE_SHARED_FS_POOLID_OFFSET 2000 + +#define FS_NO_BACKEND (-1) +#define FS_UNKNOWN (-2) +static int fs_poolid_map[MAX_INITIALIZABLE_FS]; +static int shared_fs_poolid_map[MAX_INITIALIZABLE_FS]; +static char *uuids[MAX_INITIALIZABLE_FS]; +/* + * Mutex for the [shared_|]fs_poolid_map to guard against multiple threads + * invoking umount (and ending in __cleancache_invalidate_fs) and also multiple + * threads calling mount (and ending up in __cleancache_init_[shared|]fs). + */ +static DEFINE_MUTEX(poolid_mutex); +/* + * When set to false (default) all calls to the cleancache functions, except + * the __cleancache_invalidate_fs and __cleancache_init_[shared|]fs are guarded + * by the if (!cleancache_ops) return. This means multiple threads (from + * different filesystems) will be checking cleancache_ops. The usage of a + * bool instead of a atomic_t or a bool guarded by a spinlock is OK - we are + * OK if the time between the backend's have been initialized (and + * cleancache_ops has been set to not NULL) and when the filesystems start + * actually calling the backends. The inverse (when unloading) is obviously + * not good - but this shim does not do that (yet). + */ + +/* + * The backends and filesystems work all asynchronously. This is b/c the + * backends can be built as modules. + * The usual sequence of events is: + * a) mount / -> __cleancache_init_fs is called. We set the + * [shared_|]fs_poolid_map and uuids for. + * + * b). user does I/Os -> we call the rest of __cleancache_* functions + * which return immediately as cleancache_ops is false. + * + * c). modprobe zcache -> cleancache_register_ops. We init the backend + * and set cleancache_ops to true, and for any fs_poolid_map + * (which is set by __cleancache_init_fs) we initialize the poolid. + * + * d). user does I/Os -> now that cleancache_ops is true all the + * __cleancache_* functions can call the backend. They all check + * that fs_poolid_map is valid and if so invoke the backend. + * + * e). umount / -> __cleancache_invalidate_fs, the fs_poolid_map is + * reset (which is the second check in the __cleancache_* ops + * to call the backend). + * + * The sequence of event could also be c), followed by a), and d). and e). The + * c) would not happen anymore. There is also the chance of c), and one thread + * doing a) + d), and another doing e). For that case we depend on the + * filesystem calling __cleancache_invalidate_fs in the proper sequence (so + * that it handles all I/Os before it invalidates the fs (which is last part + * of unmounting process). + * + * Note: The acute reader will notice that there is no "rmmod zcache" case. + * This is b/c the functionality for that is not yet implemented and when + * done, will require some extra locking not yet devised. + */ + +/* + * Register operations for cleancache, returning previous thus allowing + * detection of multiple backends and possible nesting. */ -struct cleancache_ops cleancache_register_ops(struct cleancache_ops *ops) +struct cleancache_ops *cleancache_register_ops(struct cleancache_ops *ops) { - struct cleancache_ops old = cleancache_ops; + struct cleancache_ops *old = cleancache_ops; + int i; - cleancache_ops = *ops; - cleancache_enabled = 1; + mutex_lock(&poolid_mutex); + for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { + if (fs_poolid_map[i] == FS_NO_BACKEND) + fs_poolid_map[i] = ops->init_fs(PAGE_SIZE); + if (shared_fs_poolid_map[i] == FS_NO_BACKEND) + shared_fs_poolid_map[i] = ops->init_shared_fs + (uuids[i], PAGE_SIZE); + } + /* + * We MUST set cleancache_ops _after_ we have called the backends + * init_fs or init_shared_fs functions. Otherwise the compiler might + * re-order where cleancache_ops is set in this function. + */ + barrier(); + cleancache_ops = ops; + mutex_unlock(&poolid_mutex); return old; } EXPORT_SYMBOL(cleancache_register_ops); @@ -61,15 +137,42 @@ EXPORT_SYMBOL(cleancache_register_ops); /* Called by a cleancache-enabled filesystem at time of mount */ void __cleancache_init_fs(struct super_block *sb) { - sb->cleancache_poolid = (*cleancache_ops.init_fs)(PAGE_SIZE); + int i; + + mutex_lock(&poolid_mutex); + for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { + if (fs_poolid_map[i] == FS_UNKNOWN) { + sb->cleancache_poolid = i + FAKE_FS_POOLID_OFFSET; + if (cleancache_ops) + fs_poolid_map[i] = cleancache_ops->init_fs(PAGE_SIZE); + else + fs_poolid_map[i] = FS_NO_BACKEND; + break; + } + } + mutex_unlock(&poolid_mutex); } EXPORT_SYMBOL(__cleancache_init_fs); /* Called by a cleancache-enabled clustered filesystem at time of mount */ void __cleancache_init_shared_fs(char *uuid, struct super_block *sb) { - sb->cleancache_poolid = - (*cleancache_ops.init_shared_fs)(uuid, PAGE_SIZE); + int i; + + mutex_lock(&poolid_mutex); + for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { + if (shared_fs_poolid_map[i] == FS_UNKNOWN) { + sb->cleancache_poolid = i + FAKE_SHARED_FS_POOLID_OFFSET; + uuids[i] = uuid; + if (cleancache_ops) + shared_fs_poolid_map[i] = cleancache_ops->init_shared_fs + (uuid, PAGE_SIZE); + else + shared_fs_poolid_map[i] = FS_NO_BACKEND; + break; + } + } + mutex_unlock(&poolid_mutex); } EXPORT_SYMBOL(__cleancache_init_shared_fs); @@ -89,7 +192,7 @@ static int cleancache_get_key(struct inode *inode, fhfn = sb->s_export_op->encode_fh; if (fhfn) { len = (*fhfn)(inode, &key->u.fh[0], &maxlen, NULL); - if (len <= 0 || len == 255) + if (len <= FILEID_ROOT || len == FILEID_INVALID) return -1; if (maxlen > CLEANCACHE_KEY_MAX) return -1; @@ -99,27 +202,53 @@ static int cleancache_get_key(struct inode *inode, } /* + * Returns a pool_id that is associated with a given fake poolid. + */ +static int get_poolid_from_fake(int fake_pool_id) +{ + if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) + return shared_fs_poolid_map[fake_pool_id - + FAKE_SHARED_FS_POOLID_OFFSET]; + else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) + return fs_poolid_map[fake_pool_id - FAKE_FS_POOLID_OFFSET]; + return FS_NO_BACKEND; +} + +/* * "Get" data from cleancache associated with the poolid/inode/index * that were specified when the data was put to cleanache and, if * successful, use it to fill the specified page with data and return 0. * The pageframe is unchanged and returns -1 if the get fails. * Page must be locked by caller. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. */ int __cleancache_get_page(struct page *page) { int ret = -1; int pool_id; + int fake_pool_id; struct cleancache_filekey key = { .u.key = { 0 } }; - VM_BUG_ON(!PageLocked(page)); - pool_id = page->mapping->host->i_sb->cleancache_poolid; - if (pool_id < 0) + if (!cleancache_ops) { + cleancache_failed_gets++; + goto out; + } + + VM_BUG_ON_PAGE(!PageLocked(page), page); + fake_pool_id = page->mapping->host->i_sb->cleancache_poolid; + if (fake_pool_id < 0) goto out; + pool_id = get_poolid_from_fake(fake_pool_id); if (cleancache_get_key(page->mapping->host, &key) < 0) goto out; - ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page); + if (pool_id >= 0) + ret = cleancache_ops->get_page(pool_id, + key, page->index, page); if (ret == 0) cleancache_succ_gets++; else @@ -134,17 +263,32 @@ EXPORT_SYMBOL(__cleancache_get_page); * (previously-obtained per-filesystem) poolid and the page's, * inode and page index. Page must be locked. Note that a put_page * always "succeeds", though a subsequent get_page may succeed or fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. */ void __cleancache_put_page(struct page *page) { int pool_id; + int fake_pool_id; struct cleancache_filekey key = { .u.key = { 0 } }; - VM_BUG_ON(!PageLocked(page)); - pool_id = page->mapping->host->i_sb->cleancache_poolid; + if (!cleancache_ops) { + cleancache_puts++; + return; + } + + VM_BUG_ON_PAGE(!PageLocked(page), page); + fake_pool_id = page->mapping->host->i_sb->cleancache_poolid; + if (fake_pool_id < 0) + return; + + pool_id = get_poolid_from_fake(fake_pool_id); + if (pool_id >= 0 && - cleancache_get_key(page->mapping->host, &key) >= 0) { - (*cleancache_ops.put_page)(pool_id, key, page->index, page); + cleancache_get_key(page->mapping->host, &key) >= 0) { + cleancache_ops->put_page(pool_id, key, page->index, page); cleancache_puts++; } } @@ -153,19 +297,31 @@ EXPORT_SYMBOL(__cleancache_put_page); /* * Invalidate any data from cleancache associated with the poolid and the * page's inode and page index so that a subsequent "get" will fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. */ void __cleancache_invalidate_page(struct address_space *mapping, struct page *page) { /* careful... page->mapping is NULL sometimes when this is called */ - int pool_id = mapping->host->i_sb->cleancache_poolid; + int pool_id; + int fake_pool_id = mapping->host->i_sb->cleancache_poolid; struct cleancache_filekey key = { .u.key = { 0 } }; - if (pool_id >= 0) { - VM_BUG_ON(!PageLocked(page)); + if (!cleancache_ops) + return; + + if (fake_pool_id >= 0) { + pool_id = get_poolid_from_fake(fake_pool_id); + if (pool_id < 0) + return; + + VM_BUG_ON_PAGE(!PageLocked(page), page); if (cleancache_get_key(mapping->host, &key) >= 0) { - (*cleancache_ops.invalidate_page)(pool_id, - key, page->index); + cleancache_ops->invalidate_page(pool_id, + key, page->index); cleancache_invalidates++; } } @@ -176,34 +332,63 @@ EXPORT_SYMBOL(__cleancache_invalidate_page); * Invalidate all data from cleancache associated with the poolid and the * mappings's inode so that all subsequent gets to this poolid/inode * will fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. */ void __cleancache_invalidate_inode(struct address_space *mapping) { - int pool_id = mapping->host->i_sb->cleancache_poolid; + int pool_id; + int fake_pool_id = mapping->host->i_sb->cleancache_poolid; struct cleancache_filekey key = { .u.key = { 0 } }; + if (!cleancache_ops) + return; + + if (fake_pool_id < 0) + return; + + pool_id = get_poolid_from_fake(fake_pool_id); + if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0) - (*cleancache_ops.invalidate_inode)(pool_id, key); + cleancache_ops->invalidate_inode(pool_id, key); } EXPORT_SYMBOL(__cleancache_invalidate_inode); /* * Called by any cleancache-enabled filesystem at time of unmount; - * note that pool_id is surrendered and may be reutrned by a subsequent - * cleancache_init_fs or cleancache_init_shared_fs + * note that pool_id is surrendered and may be returned by a subsequent + * cleancache_init_fs or cleancache_init_shared_fs. */ void __cleancache_invalidate_fs(struct super_block *sb) { - if (sb->cleancache_poolid >= 0) { - int old_poolid = sb->cleancache_poolid; - sb->cleancache_poolid = -1; - (*cleancache_ops.invalidate_fs)(old_poolid); + int index; + int fake_pool_id = sb->cleancache_poolid; + int old_poolid = fake_pool_id; + + mutex_lock(&poolid_mutex); + if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) { + index = fake_pool_id - FAKE_SHARED_FS_POOLID_OFFSET; + old_poolid = shared_fs_poolid_map[index]; + shared_fs_poolid_map[index] = FS_UNKNOWN; + uuids[index] = NULL; + } else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) { + index = fake_pool_id - FAKE_FS_POOLID_OFFSET; + old_poolid = fs_poolid_map[index]; + fs_poolid_map[index] = FS_UNKNOWN; } + sb->cleancache_poolid = -1; + if (cleancache_ops) + cleancache_ops->invalidate_fs(old_poolid); + mutex_unlock(&poolid_mutex); } EXPORT_SYMBOL(__cleancache_invalidate_fs); static int __init init_cleancache(void) { + int i; + #ifdef CONFIG_DEBUG_FS struct dentry *root = debugfs_create_dir("cleancache", NULL); if (root == NULL) @@ -215,6 +400,10 @@ static int __init init_cleancache(void) debugfs_create_u64("invalidates", S_IRUGO, root, &cleancache_invalidates); #endif + for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { + fs_poolid_map[i] = FS_UNKNOWN; + shared_fs_poolid_map[i] = FS_UNKNOWN; + } return 0; } module_init(init_cleancache) diff --git a/mm/compaction.c b/mm/compaction.c index c62bd063d76..21bf292b642 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -15,6 +15,7 @@ #include <linux/sysctl.h> #include <linux/sysfs.h> #include <linux/balloon_compaction.h> +#include <linux/page-isolation.h> #include "internal.h" #ifdef CONFIG_COMPACTION @@ -85,10 +86,11 @@ static inline bool isolation_suitable(struct compact_control *cc, static void __reset_isolation_suitable(struct zone *zone) { unsigned long start_pfn = zone->zone_start_pfn; - unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages; + unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; - zone->compact_cached_migrate_pfn = start_pfn; + zone->compact_cached_migrate_pfn[0] = start_pfn; + zone->compact_cached_migrate_pfn[1] = start_pfn; zone->compact_cached_free_pfn = end_pfn; zone->compact_blockskip_flush = false; @@ -130,26 +132,43 @@ void reset_isolation_suitable(pg_data_t *pgdat) */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { struct zone *zone = cc->zone; + unsigned long pfn; + + if (cc->ignore_skip_hint) + return; + if (!page) return; - if (!nr_isolated) { - unsigned long pfn = page_to_pfn(page); + if (nr_isolated) + return; + + /* + * Only skip pageblocks when all forms of compaction will be known to + * fail in the near future. + */ + if (set_unsuitable) set_pageblock_skip(page); - /* Update where compaction should restart */ - if (migrate_scanner) { - if (!cc->finished_update_migrate && - pfn > zone->compact_cached_migrate_pfn) - zone->compact_cached_migrate_pfn = pfn; - } else { - if (!cc->finished_update_free && - pfn < zone->compact_cached_free_pfn) - zone->compact_cached_free_pfn = pfn; - } + pfn = page_to_pfn(page); + + /* Update where async and sync compaction should restart */ + if (migrate_scanner) { + if (cc->finished_update_migrate) + return; + if (pfn > zone->compact_cached_migrate_pfn[0]) + zone->compact_cached_migrate_pfn[0] = pfn; + if (cc->mode != MIGRATE_ASYNC && + pfn > zone->compact_cached_migrate_pfn[1]) + zone->compact_cached_migrate_pfn[1] = pfn; + } else { + if (cc->finished_update_free) + return; + if (pfn < zone->compact_cached_free_pfn) + zone->compact_cached_free_pfn = pfn; } } #else @@ -161,7 +180,7 @@ static inline bool isolation_suitable(struct compact_control *cc, static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { } #endif /* CONFIG_COMPACTION */ @@ -190,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, } /* async aborts if taking too long or contended */ - if (!cc->sync) { + if (cc->mode == MIGRATE_ASYNC) { cc->contended = true; return false; } @@ -203,27 +222,39 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, return true; } -static inline bool compact_trylock_irqsave(spinlock_t *lock, - unsigned long *flags, struct compact_control *cc) +/* + * Aside from avoiding lock contention, compaction also periodically checks + * need_resched() and either schedules in sync compaction or aborts async + * compaction. This is similar to what compact_checklock_irqsave() does, but + * is used where no lock is concerned. + * + * Returns false when no scheduling was needed, or sync compaction scheduled. + * Returns true when async compaction should abort. + */ +static inline bool compact_should_abort(struct compact_control *cc) { - return compact_checklock_irqsave(lock, flags, false, cc); + /* async compaction aborts if contended */ + if (need_resched()) { + if (cc->mode == MIGRATE_ASYNC) { + cc->contended = true; + return true; + } + + cond_resched(); + } + + return false; } /* Returns true if the page is within a block suitable for migration to */ static bool suitable_migration_target(struct page *page) { - int migratetype = get_pageblock_migratetype(page); - - /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) - return false; - - /* If the page is a large free page, then allow migration */ + /* If the page is a large free page, then disallow migration */ if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; + return false; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(migratetype)) + if (migrate_async_suitable(get_pageblock_migratetype(page))) return true; /* Otherwise skip the block */ @@ -231,10 +262,9 @@ static bool suitable_migration_target(struct page *page) } /* - * Isolate free pages onto a private freelist. Caller must hold zone->lock. - * If @strict is true, will abort returning 0 on any invalid PFNs or non-free - * pages inside of the pageblock (even though it may still end up isolating - * some pages). + * Isolate free pages onto a private freelist. If @strict is true, will abort + * returning 0 on any invalid PFNs or non-free pages inside of the pageblock + * (even though it may still end up isolating some pages). */ static unsigned long isolate_freepages_block(struct compact_control *cc, unsigned long blockpfn, @@ -244,9 +274,9 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, { int nr_scanned = 0, total_isolated = 0; struct page *cursor, *valid_page = NULL; - unsigned long nr_strict_required = end_pfn - blockpfn; unsigned long flags; bool locked = false; + bool checked_pageblock = false; cursor = pfn_to_page(blockpfn); @@ -257,11 +287,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, nr_scanned++; if (!pfn_valid_within(blockpfn)) - continue; + goto isolate_fail; + if (!valid_page) valid_page = page; if (!PageBuddy(page)) - continue; + goto isolate_fail; /* * The zone lock must be held to isolate freepages. @@ -277,17 +308,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, break; /* Recheck this is a suitable migration target under lock */ - if (!strict && !suitable_migration_target(page)) - break; + if (!strict && !checked_pageblock) { + /* + * We need to check suitability of pageblock only once + * and this isolate_freepages_block() is called with + * pageblock range, so just check once is sufficient. + */ + checked_pageblock = true; + if (!suitable_migration_target(page)) + break; + } /* Recheck this is a buddy page under lock */ if (!PageBuddy(page)) - continue; + goto isolate_fail; /* Found a free page, break it into order-0 pages */ isolated = split_free_page(page); - if (!isolated && strict) - break; total_isolated += isolated; for (i = 0; i < isolated; i++) { list_add(&page->lru, freelist); @@ -298,7 +335,15 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (isolated) { blockpfn += isolated - 1; cursor += isolated - 1; + continue; } + +isolate_fail: + if (strict) + break; + else + continue; + } trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated); @@ -308,7 +353,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, * pages requested were isolated. If there were any failures, 0 is * returned and CMA will fail. */ - if (strict && nr_strict_required > total_isolated) + if (strict && blockpfn < end_pfn) total_isolated = 0; if (locked) @@ -316,7 +361,8 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) - update_pageblock_skip(cc, valid_page, total_isolated, false); + update_pageblock_skip(cc, valid_page, total_isolated, true, + false); count_compact_events(COMPACTFREE_SCANNED, nr_scanned); if (total_isolated) @@ -447,11 +493,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; - isolate_mode_t mode = 0; struct lruvec *lruvec; unsigned long flags; bool locked = false; struct page *page = NULL, *valid_page = NULL; + bool set_unsuitable = true; + const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ? + ISOLATE_ASYNC_MIGRATE : 0) | + (unevictable ? ISOLATE_UNEVICTABLE : 0); /* * Ensure that there are not too many pages isolated from the LRU @@ -460,7 +509,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ - if (!cc->sync) + if (cc->mode == MIGRATE_ASYNC) return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -469,11 +518,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, return 0; } + if (compact_should_abort(cc)) + return 0; + /* Time to isolate some pages for migration */ - cond_resched(); for (; low_pfn < end_pfn; low_pfn++) { /* give a chance to irqs before checking need_resched() */ - if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) { + if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) { if (should_release_lock(&zone->lru_lock)) { spin_unlock_irqrestore(&zone->lru_lock, flags); locked = false; @@ -512,23 +563,32 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, /* If isolation recently failed, do not retry */ pageblock_nr = low_pfn >> pageblock_order; - if (!isolation_suitable(cc, page)) - goto next_pageblock; + if (last_pageblock_nr != pageblock_nr) { + int mt; - /* Skip if free */ - if (PageBuddy(page)) - continue; + last_pageblock_nr = pageblock_nr; + if (!isolation_suitable(cc, page)) + goto next_pageblock; + + /* + * For async migration, also only scan in MOVABLE + * blocks. Async migration is optimistic to see if + * the minimum amount of work satisfies the allocation + */ + mt = get_pageblock_migratetype(page); + if (cc->mode == MIGRATE_ASYNC && + !migrate_async_suitable(mt)) { + set_unsuitable = false; + goto next_pageblock; + } + } /* - * For async migration, also only scan in MOVABLE blocks. Async - * migration is optimistic to see if the minimum amount of work - * satisfies the allocation + * Skip if free. page_order cannot be used without zone->lock + * as nothing prevents parallel allocations or buddy merging. */ - if (!cc->sync && last_pageblock_nr != pageblock_nr && - !migrate_async_suitable(get_pageblock_migratetype(page))) { - cc->finished_update_migrate = true; - goto next_pageblock; - } + if (PageBuddy(page)) + continue; /* * Check may be lockless but that's ok as we recheck later. @@ -539,11 +599,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, if (unlikely(balloon_page_movable(page))) { if (locked && balloon_page_isolate(page)) { /* Successfully isolated */ - cc->finished_update_migrate = true; - list_add(&page->lru, migratelist); - cc->nr_migratepages++; - nr_isolated++; - goto check_compact_cluster; + goto isolate_success; } } continue; @@ -566,6 +622,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } + /* + * Migration will fail if an anonymous page is pinned in memory, + * so avoid taking lru_lock and isolating it unnecessarily in an + * admittedly racy check. + */ + if (!page_mapping(page) && + page_count(page) > page_mapcount(page)) + continue; + /* Check if it is ok to still hold the lock */ locked = compact_checklock_irqsave(&zone->lru_lock, &flags, locked, cc); @@ -580,28 +645,23 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } - if (!cc->sync) - mode |= ISOLATE_ASYNC_MIGRATE; - - if (unevictable) - mode |= ISOLATE_UNEVICTABLE; - lruvec = mem_cgroup_page_lruvec(page, zone); /* Try isolate the page */ if (__isolate_lru_page(page, mode) != 0) continue; - VM_BUG_ON(PageTransCompound(page)); + VM_BUG_ON_PAGE(PageTransCompound(page), page); /* Successfully isolated */ - cc->finished_update_migrate = true; del_page_from_lru_list(page, lruvec, page_lru(page)); + +isolate_success: + cc->finished_update_migrate = true; list_add(&page->lru, migratelist); cc->nr_migratepages++; nr_isolated++; -check_compact_cluster: /* Avoid isolating too much */ if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) { ++low_pfn; @@ -611,9 +671,7 @@ check_compact_cluster: continue; next_pageblock: - low_pfn += pageblock_nr_pages; - low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1; - last_pageblock_nr = pageblock_nr; + low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1; } acct_isolated(zone, locked, cc); @@ -621,9 +679,13 @@ next_pageblock: if (locked) spin_unlock_irqrestore(&zone->lru_lock, flags); - /* Update the pageblock-skip if the whole pageblock was scanned */ + /* + * Update the pageblock-skip information and cached scanner pfn, + * if the whole pageblock was scanned without isolating any page. + */ if (low_pfn == end_pfn) - update_pageblock_skip(cc, valid_page, nr_isolated, true); + update_pageblock_skip(cc, valid_page, nr_isolated, + set_unsuitable, true); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -644,37 +706,48 @@ static void isolate_freepages(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn; + unsigned long block_start_pfn; /* start of current pageblock */ + unsigned long block_end_pfn; /* end of current pageblock */ + unsigned long low_pfn; /* lowest pfn scanner is able to scan */ int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; /* * Initialise the free scanner. The starting point is where we last - * scanned from (or the end of the zone if starting). The low point - * is the end of the pageblock the migration scanner is using. + * successfully isolated from, zone-cached value, or the end of the + * zone when isolating for the first time. We need this aligned to + * the pageblock boundary, because we do + * block_start_pfn -= pageblock_nr_pages in the for loop. + * For ending point, take care when isolating in last pageblock of a + * a zone which ends in the middle of a pageblock. + * The low boundary is the end of the pageblock the migration scanner + * is using. */ - pfn = cc->free_pfn; - low_pfn = cc->migrate_pfn + pageblock_nr_pages; - - /* - * Take care that if the migration scanner is at the end of the zone - * that the free scanner does not accidentally move to the next zone - * in the next isolation cycle. - */ - high_pfn = min(low_pfn, pfn); - - zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; + block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_end_pfn = min(block_start_pfn + pageblock_nr_pages, + zone_end_pfn(zone)); + low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages); /* * Isolate free pages until enough are available to migrate the * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ - for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; - pfn -= pageblock_nr_pages) { + for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages; + block_end_pfn = block_start_pfn, + block_start_pfn -= pageblock_nr_pages) { unsigned long isolated; - if (!pfn_valid(pfn)) + /* + * This can iterate a massively long zone without finding any + * suitable migration targets, so periodically check if we need + * to schedule, or even abort async compaction. + */ + if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)) + && compact_should_abort(cc)) + break; + + if (!pfn_valid(block_start_pfn)) continue; /* @@ -684,7 +757,7 @@ static void isolate_freepages(struct zone *zone, * i.e. it's possible that all pages within a zones range of * pages do not belong to a single zone. */ - page = pfn_to_page(pfn); + page = pfn_to_page(block_start_pfn); if (page_zone(page) != zone) continue; @@ -697,35 +770,38 @@ static void isolate_freepages(struct zone *zone, continue; /* Found a block suitable for isolating free pages from */ - isolated = 0; + cc->free_pfn = block_start_pfn; + isolated = isolate_freepages_block(cc, block_start_pfn, + block_end_pfn, freelist, false); + nr_freepages += isolated; /* - * As pfn may not start aligned, pfn+pageblock_nr_page - * may cross a MAX_ORDER_NR_PAGES boundary and miss - * a pfn_valid check. Ensure isolate_freepages_block() - * only scans within a pageblock + * Set a flag that we successfully isolated in this pageblock. + * In the next loop iteration, zone->compact_cached_free_pfn + * will not be updated and thus it will effectively contain the + * highest pageblock we isolated pages from. */ - end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); - end_pfn = min(end_pfn, zone_end_pfn); - isolated = isolate_freepages_block(cc, pfn, end_pfn, - freelist, false); - nr_freepages += isolated; + if (isolated) + cc->finished_update_free = true; /* - * Record the highest PFN we isolated pages from. When next - * looking for free pages, the search will restart here as - * page migration may have returned some pages to the allocator + * isolate_freepages_block() might have aborted due to async + * compaction being contended */ - if (isolated) { - cc->finished_update_free = true; - high_pfn = max(high_pfn, pfn); - } + if (cc->contended) + break; } /* split_free_page does not map the pages */ map_pages(freelist); - cc->free_pfn = high_pfn; + /* + * If we crossed the migrate scanner, we want to keep it that way + * so that compact_finished() may detect this + */ + if (block_start_pfn < low_pfn) + cc->free_pfn = cc->migrate_pfn; + cc->nr_freepages = nr_freepages; } @@ -740,9 +816,13 @@ static struct page *compaction_alloc(struct page *migratepage, struct compact_control *cc = (struct compact_control *)data; struct page *freepage; - /* Isolate free pages if necessary */ + /* + * Isolate free pages if necessary, and if we are not aborting due to + * contention. + */ if (list_empty(&cc->freepages)) { - isolate_freepages(cc->zone, cc); + if (!cc->contended) + isolate_freepages(cc->zone, cc); if (list_empty(&cc->freepages)) return NULL; @@ -756,23 +836,16 @@ static struct page *compaction_alloc(struct page *migratepage, } /* - * We cannot control nr_migratepages and nr_freepages fully when migration is - * running as migrate_pages() has no knowledge of compact_control. When - * migration is complete, we count the number of pages on the lists by hand. + * This is a migrate-callback that "frees" freepages back to the isolated + * freelist. All pages on the freelist are from the same zone, so there is no + * special handling needed for NUMA. */ -static void update_nr_listpages(struct compact_control *cc) +static void compaction_free(struct page *page, unsigned long data) { - int nr_migratepages = 0; - int nr_freepages = 0; - struct page *page; - - list_for_each_entry(page, &cc->migratepages, lru) - nr_migratepages++; - list_for_each_entry(page, &cc->freepages, lru) - nr_freepages++; + struct compact_control *cc = (struct compact_control *)data; - cc->nr_migratepages = nr_migratepages; - cc->nr_freepages = nr_freepages; + list_add(&page->lru, &cc->freepages); + cc->nr_freepages++; } /* possible outcome of isolate_migratepages */ @@ -795,7 +868,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); /* Only scan within a pageblock boundary */ - end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages); + end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages); /* Do not cross the free scanner or scan within a memory hole */ if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { @@ -819,11 +892,16 @@ static int compact_finished(struct zone *zone, unsigned int order; unsigned long watermark; - if (fatal_signal_pending(current)) + if (cc->contended || fatal_signal_pending(current)) return COMPACT_PARTIAL; /* Compaction run completes if the migrate and free scanner meet */ if (cc->free_pfn <= cc->migrate_pfn) { + /* Let the next compaction start anew. */ + zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; + zone->compact_cached_free_pfn = zone_end_pfn(zone); + /* * Mark that the PG_migrate_skip information should be cleared * by kswapd when it goes to sleep. kswapd does not set the @@ -920,7 +998,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) { int ret; unsigned long start_pfn = zone->zone_start_pfn; - unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages; + unsigned long end_pfn = zone_end_pfn(zone); + const bool sync = cc->mode != MIGRATE_ASYNC; ret = compaction_suitable(zone, cc->order); switch (ret) { @@ -934,11 +1013,19 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } /* + * Clear pageblock skip if there were failures recently and compaction + * is about to be retried after being deferred. kswapd does not do + * this reset as it'll reset the cached information when going to sleep. + */ + if (compaction_restarting(zone, cc->order) && !current_is_kswapd()) + __reset_isolation_suitable(zone); + + /* * Setup to move all movable pages to the end of the zone. Used cached * information on where the scanners should start but check that it * is initialised by ensuring the values are within zone boundaries. */ - cc->migrate_pfn = zone->compact_cached_migrate_pfn; + cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); @@ -946,21 +1033,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) { cc->migrate_pfn = start_pfn; - zone->compact_cached_migrate_pfn = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } - /* - * Clear pageblock skip if there were failures recently and compaction - * is about to be retried after being deferred. kswapd does not do - * this reset as it'll reset the cached information when going to sleep. - */ - if (compaction_restarting(zone, cc->order) && !current_is_kswapd()) - __reset_isolation_suitable(zone); + trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); migrate_prep_local(); while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) { - unsigned long nr_migrate, nr_remaining; int err; switch (isolate_migratepages(zone, cc)) { @@ -975,22 +1056,25 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) ; } - nr_migrate = cc->nr_migratepages; + if (!cc->nr_migratepages) + continue; + err = migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, false, - cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, + compaction_free, (unsigned long)cc, cc->mode, MR_COMPACTION); - update_nr_listpages(cc); - nr_remaining = cc->nr_migratepages; - trace_mm_compaction_migratepages(nr_migrate - nr_remaining, - nr_remaining); + trace_mm_compaction_migratepages(cc->nr_migratepages, err, + &cc->migratepages); - /* Release isolated pages not migrated */ + /* All pages were either migrated or will be released */ + cc->nr_migratepages = 0; if (err) { putback_movable_pages(&cc->migratepages); - cc->nr_migratepages = 0; - if (err == -ENOMEM) { + /* + * migrate_pages() may return -ENOMEM when scanners meet + * and we want compact_finished() to detect it + */ + if (err == -ENOMEM && cc->free_pfn > cc->migrate_pfn) { ret = COMPACT_PARTIAL; goto out; } @@ -1002,12 +1086,13 @@ out: cc->nr_freepages -= release_freepages(&cc->freepages); VM_BUG_ON(cc->nr_freepages != 0); + trace_mm_compaction_end(ret); + return ret; } -static unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask, - bool sync, bool *contended) +static unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask, enum migrate_mode mode, bool *contended) { unsigned long ret; struct compact_control cc = { @@ -1016,7 +1101,7 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, - .sync = sync, + .mode = mode, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -1038,7 +1123,7 @@ int sysctl_extfrag_threshold = 500; * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation * @nodemask: The allowed nodes to allocate from - * @sync: Whether migration is synchronous or not + * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that is true if compaction was aborted due to lock contention * @page: Optionally capture a free page of the requested order during compaction * @@ -1046,7 +1131,7 @@ int sysctl_extfrag_threshold = 500; */ unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; @@ -1071,7 +1156,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync, + status = compact_zone_order(zone, order, gfp_mask, mode, contended); rc = max(status, rc); @@ -1086,7 +1171,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, /* Compact all zones within a node */ -static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) +static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) { int zoneid; struct zone *zone; @@ -1107,40 +1192,38 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) compact_zone(zone, cc); if (cc->order > 0) { - int ok = zone_watermark_ok(zone, cc->order, - low_wmark_pages(zone), 0, 0); - if (ok && cc->order >= zone->compact_order_failed) - zone->compact_order_failed = cc->order + 1; - /* Currently async compaction is never deferred. */ - else if (!ok && cc->sync) - defer_compaction(zone, cc->order); + if (zone_watermark_ok(zone, cc->order, + low_wmark_pages(zone), 0, 0)) + compaction_defer_reset(zone, cc->order, false); } VM_BUG_ON(!list_empty(&cc->freepages)); VM_BUG_ON(!list_empty(&cc->migratepages)); } - - return 0; } -int compact_pgdat(pg_data_t *pgdat, int order) +void compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .sync = false, + .mode = MIGRATE_ASYNC, }; - return __compact_pgdat(pgdat, &cc); + if (!order) + return; + + __compact_pgdat(pgdat, &cc); } -static int compact_node(int nid) +static void compact_node(int nid) { struct compact_control cc = { .order = -1, - .sync = true, + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, }; - return __compact_pgdat(NODE_DATA(nid), &cc); + __compact_pgdat(NODE_DATA(nid), &cc); } /* Compact all nodes in the system */ @@ -1177,7 +1260,7 @@ int sysctl_extfrag_handler(struct ctl_table *table, int write, } #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) -ssize_t sysfs_compact_node(struct device *dev, +static ssize_t sysfs_compact_node(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { diff --git a/mm/dmapool.c b/mm/dmapool.c index c69781e97cf..306baa594f9 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -170,24 +170,16 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, retval->boundary = boundary; retval->allocation = allocation; - if (dev) { - int ret; + INIT_LIST_HEAD(&retval->pools); - mutex_lock(&pools_lock); - if (list_empty(&dev->dma_pools)) - ret = device_create_file(dev, &dev_attr_pools); - else - ret = 0; - /* note: not currently insisting "name" be unique */ - if (!ret) - list_add(&retval->pools, &dev->dma_pools); - else { - kfree(retval); - retval = NULL; - } - mutex_unlock(&pools_lock); + mutex_lock(&pools_lock); + if (list_empty(&dev->dma_pools) && + device_create_file(dev, &dev_attr_pools)) { + kfree(retval); + return NULL; } else - INIT_LIST_HEAD(&retval->pools); + list_add(&retval->pools, &dev->dma_pools); + mutex_unlock(&pools_lock); return retval; } @@ -341,10 +333,10 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, continue; if (pool->dev) dev_err(pool->dev, - "dma_pool_alloc %s, %p (corruped)\n", + "dma_pool_alloc %s, %p (corrupted)\n", pool->name, retval); else - pr_err("dma_pool_alloc %s, %p (corruped)\n", + pr_err("dma_pool_alloc %s, %p (corrupted)\n", pool->name, retval); /* @@ -508,7 +500,6 @@ void dmam_pool_destroy(struct dma_pool *pool) { struct device *dev = pool->dev; - WARN_ON(devres_destroy(dev, dmam_pool_release, dmam_pool_match, pool)); - dma_pool_destroy(pool); + WARN_ON(devres_release(dev, dmam_pool_release, dmam_pool_match, pool)); } EXPORT_SYMBOL(dmam_pool_destroy); diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c new file mode 100644 index 00000000000..e10ccd299d6 --- /dev/null +++ b/mm/early_ioremap.c @@ -0,0 +1,245 @@ +/* + * Provide common bits of early_ioremap() support for architectures needing + * temporary mappings during boot before ioremap() is available. + * + * This is mostly a direct copy of the x86 early_ioremap implementation. + * + * (C) Copyright 1995 1996, 2014 Linus Torvalds + * + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> +#include <asm/fixmap.h> + +#ifdef CONFIG_MMU +static int early_ioremap_debug __initdata; + +static int __init early_ioremap_debug_setup(char *str) +{ + early_ioremap_debug = 1; + + return 0; +} +early_param("early_ioremap_debug", early_ioremap_debug_setup); + +static int after_paging_init __initdata; + +void __init __weak early_ioremap_shutdown(void) +{ +} + +void __init early_ioremap_reset(void) +{ + early_ioremap_shutdown(); + after_paging_init = 1; +} + +/* + * Generally, ioremap() is available after paging_init() has been called. + * Architectures wanting to allow early_ioremap after paging_init() can + * define __late_set_fixmap and __late_clear_fixmap to do the right thing. + */ +#ifndef __late_set_fixmap +static inline void __init __late_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t prot) +{ + BUG(); +} +#endif + +#ifndef __late_clear_fixmap +static inline void __init __late_clear_fixmap(enum fixed_addresses idx) +{ + BUG(); +} +#endif + +static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata; + +void __init early_ioremap_setup(void) +{ + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (WARN_ON(prev_map[i])) + break; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i); +} + +static int __init check_early_ioremap_leak(void) +{ + int count = 0; + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (prev_map[i]) + count++; + + if (WARN(count, KERN_WARNING + "Debug warning: early ioremap leak of %d areas detected.\n" + "please boot with early_ioremap_debug and report the dmesg.\n", + count)) + return 1; + return 0; +} +late_initcall(check_early_ioremap_leak); + +static void __init __iomem * +__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) +{ + unsigned long offset; + resource_size_t last_addr; + unsigned int nrpages; + enum fixed_addresses idx; + int i, slot; + + WARN_ON(system_state != SYSTEM_BOOTING); + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (!prev_map[i]) { + slot = i; + break; + } + } + + if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n", + __func__, (u64)phys_addr, size)) + return NULL; + + /* Don't allow wraparound or zero size */ + last_addr = phys_addr + size - 1; + if (WARN_ON(!size || last_addr < phys_addr)) + return NULL; + + prev_size[slot] = size; + /* + * Mappings have to be page-aligned + */ + offset = phys_addr & ~PAGE_MASK; + phys_addr &= PAGE_MASK; + size = PAGE_ALIGN(last_addr + 1) - phys_addr; + + /* + * Mappings have to fit in the FIX_BTMAP area. + */ + nrpages = size >> PAGE_SHIFT; + if (WARN_ON(nrpages > NR_FIX_BTMAPS)) + return NULL; + + /* + * Ok, go for it.. + */ + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; + while (nrpages > 0) { + if (after_paging_init) + __late_set_fixmap(idx, phys_addr, prot); + else + __early_set_fixmap(idx, phys_addr, prot); + phys_addr += PAGE_SIZE; + --idx; + --nrpages; + } + WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n", + __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]); + + prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]); + return prev_map[slot]; +} + +void __init early_iounmap(void __iomem *addr, unsigned long size) +{ + unsigned long virt_addr; + unsigned long offset; + unsigned int nrpages; + enum fixed_addresses idx; + int i, slot; + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (prev_map[i] == addr) { + slot = i; + break; + } + } + + if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n", + addr, size)) + return; + + if (WARN(prev_size[slot] != size, + "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n", + addr, size, slot, prev_size[slot])) + return; + + WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n", + addr, size, slot); + + virt_addr = (unsigned long)addr; + if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN))) + return; + + offset = virt_addr & ~PAGE_MASK; + nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT; + + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; + while (nrpages > 0) { + if (after_paging_init) + __late_clear_fixmap(idx); + else + __early_set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR); + --idx; + --nrpages; + } + prev_map[slot] = NULL; +} + +/* Remap an IO device */ +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) +{ + return __early_ioremap(phys_addr, size, FIXMAP_PAGE_IO); +} + +/* Remap memory */ +void __init * +early_memremap(resource_size_t phys_addr, unsigned long size) +{ + return (__force void *)__early_ioremap(phys_addr, size, + FIXMAP_PAGE_NORMAL); +} +#else /* CONFIG_MMU */ + +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) +{ + return (__force void __iomem *)phys_addr; +} + +/* Remap memory */ +void __init * +early_memremap(resource_size_t phys_addr, unsigned long size) +{ + return (void *)phys_addr; +} + +void __init early_iounmap(void __iomem *addr, unsigned long size) +{ +} + +#endif /* CONFIG_MMU */ + + +void __init early_memunmap(void *addr, unsigned long size) +{ + early_iounmap((__force void __iomem *)addr, size); +} diff --git a/mm/fadvise.c b/mm/fadvise.c index a47f0f50c89..3bcfd81db45 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -17,6 +17,7 @@ #include <linux/fadvise.h> #include <linux/writeback.h> #include <linux/syscalls.h> +#include <linux/swap.h> #include <asm/unistd.h> @@ -24,7 +25,7 @@ * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could * deactivate the pages and clear PG_Referenced. */ -SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) +SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) { struct fd f = fdget(fd); struct address_space *mapping; @@ -38,7 +39,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) if (!f.file) return -EBADF; - if (S_ISFIFO(f.file->f_path.dentry->d_inode->i_mode)) { + if (S_ISFIFO(file_inode(f.file)->i_mode)) { ret = -ESPIPE; goto out; } @@ -120,9 +121,22 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT; end_index = (endbyte >> PAGE_CACHE_SHIFT); - if (end_index >= start_index) - invalidate_mapping_pages(mapping, start_index, + if (end_index >= start_index) { + unsigned long count = invalidate_mapping_pages(mapping, + start_index, end_index); + + /* + * If fewer pages were invalidated than expected then + * it is possible that some of the pages were on + * a per-cpu pagevec for a remote CPU. Drain all + * pagevecs and try again. + */ + if (count < (end_index - start_index + 1)) { + lru_add_drain_all(); + invalidate_mapping_pages(mapping, start_index, end_index); + } + } break; default: ret = -EINVAL; @@ -131,26 +145,12 @@ out: fdput(f); return ret; } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_fadvise64_64(long fd, loff_t offset, loff_t len, long advice) -{ - return SYSC_fadvise64_64((int) fd, offset, len, (int) advice); -} -SYSCALL_ALIAS(sys_fadvise64_64, SyS_fadvise64_64); -#endif #ifdef __ARCH_WANT_SYS_FADVISE64 -SYSCALL_DEFINE(fadvise64)(int fd, loff_t offset, size_t len, int advice) +SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice) { return sys_fadvise64_64(fd, offset, len, advice); } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_fadvise64(long fd, loff_t offset, long len, long advice) -{ - return SYSC_fadvise64((int) fd, offset, (size_t)len, (int)advice); -} -SYSCALL_ALIAS(sys_fadvise64, SyS_fadvise64); -#endif #endif diff --git a/mm/filemap.c b/mm/filemap.c index 83efee76a5c..900edfaf6df 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -33,8 +33,12 @@ #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */ #include <linux/memcontrol.h> #include <linux/cleancache.h> +#include <linux/rmap.h> #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/filemap.h> + /* * FIXME: remove all knowledge of the buffer layer from the core VM */ @@ -73,7 +77,7 @@ * ->mmap_sem * ->lock_page (access_process_vm) * - * ->i_mutex (generic_file_buffered_write) + * ->i_mutex (generic_perform_write) * ->mmap_sem (fault_in_pages_readable->do_page_fault) * * bdi->wb.list_lock @@ -104,15 +108,79 @@ * ->tasklist_lock (memory_failure, collect_procs_ao) */ +static void page_cache_tree_delete(struct address_space *mapping, + struct page *page, void *shadow) +{ + struct radix_tree_node *node; + unsigned long index; + unsigned int offset; + unsigned int tag; + void **slot; + + VM_BUG_ON(!PageLocked(page)); + + __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); + + if (shadow) { + mapping->nrshadows++; + /* + * Make sure the nrshadows update is committed before + * the nrpages update so that final truncate racing + * with reclaim does not see both counters 0 at the + * same time and miss a shadow entry. + */ + smp_wmb(); + } + mapping->nrpages--; + + if (!node) { + /* Clear direct pointer tags in root node */ + mapping->page_tree.gfp_mask &= __GFP_BITS_MASK; + radix_tree_replace_slot(slot, shadow); + return; + } + + /* Clear tree tags for the removed page */ + index = page->index; + offset = index & RADIX_TREE_MAP_MASK; + for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { + if (test_bit(offset, node->tags[tag])) + radix_tree_tag_clear(&mapping->page_tree, index, tag); + } + + /* Delete page, swap shadow entry */ + radix_tree_replace_slot(slot, shadow); + workingset_node_pages_dec(node); + if (shadow) + workingset_node_shadows_inc(node); + else + if (__radix_tree_delete_node(&mapping->page_tree, node)) + return; + + /* + * Track node that only contains shadow entries. + * + * Avoid acquiring the list_lru lock if already tracked. The + * list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_pages(node) && + list_empty(&node->private_list)) { + node->private_data = mapping; + list_lru_add(&workingset_shadow_nodes, &node->private_list); + } +} + /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the mapping's tree_lock. */ -void __delete_from_page_cache(struct page *page) +void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; + trace_mm_filemap_delete_from_page_cache(page); /* * if we're uptodate, flush out into the cleancache, otherwise * invalidate any existing cleancache entries. We can't leave @@ -123,10 +191,11 @@ void __delete_from_page_cache(struct page *page) else cleancache_invalidate_page(mapping, page); - radix_tree_delete(&mapping->page_tree, page->index); + page_cache_tree_delete(mapping, page, shadow); + page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ - mapping->nrpages--; + __dec_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) __dec_zone_page_state(page, NR_SHMEM); @@ -162,7 +231,7 @@ void delete_from_page_cache(struct page *page) freepage = mapping->a_ops->freepage; spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(page); + __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -184,6 +253,19 @@ static int sleep_on_page_killable(void *word) return fatal_signal_pending(current) ? -EINTR : 0; } +static int filemap_check_errors(struct address_space *mapping) +{ + int ret = 0; + /* Check for outstanding write errors */ + if (test_bit(AS_ENOSPC, &mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &mapping->flags)) + ret = -ENOSPC; + if (test_bit(AS_EIO, &mapping->flags) && + test_and_clear_bit(AS_EIO, &mapping->flags)) + ret = -EIO; + return ret; +} + /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write @@ -265,10 +347,10 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, pgoff_t end = end_byte >> PAGE_CACHE_SHIFT; struct pagevec pvec; int nr_pages; - int ret = 0; + int ret2, ret = 0; if (end_byte < start_byte) - return 0; + goto out; pagevec_init(&pvec, 0); while ((index <= end) && @@ -291,12 +373,10 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, pagevec_release(&pvec); cond_resched(); } - - /* Check for outstanding write errors */ - if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) - ret = -ENOSPC; - if (test_and_clear_bit(AS_EIO, &mapping->flags)) - ret = -EIO; +out: + ret2 = filemap_check_errors(mapping); + if (!ret) + ret = ret2; return ret; } @@ -337,6 +417,8 @@ int filemap_write_and_wait(struct address_space *mapping) if (!err) err = err2; } + } else { + err = filemap_check_errors(mapping); } return err; } @@ -368,6 +450,8 @@ int filemap_write_and_wait_range(struct address_space *mapping, if (!err) err = err2; } + } else { + err = filemap_check_errors(mapping); } return err; } @@ -392,9 +476,9 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { int error; - VM_BUG_ON(!PageLocked(old)); - VM_BUG_ON(!PageLocked(new)); - VM_BUG_ON(new->mapping); + VM_BUG_ON_PAGE(!PageLocked(old), old); + VM_BUG_ON_PAGE(!PageLocked(new), new); + VM_BUG_ON_PAGE(new->mapping, new); error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); if (!error) { @@ -409,7 +493,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->index = offset; spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(old); + __delete_from_page_cache(old, NULL); error = radix_tree_insert(&mapping->page_tree, offset, new); BUG_ON(error); mapping->nrpages++; @@ -429,6 +513,91 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); +static int page_cache_tree_insert(struct address_space *mapping, + struct page *page, void **shadowp) +{ + struct radix_tree_node *node; + void **slot; + int error; + + error = __radix_tree_create(&mapping->page_tree, page->index, + &node, &slot); + if (error) + return error; + if (*slot) { + void *p; + + p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + if (!radix_tree_exceptional_entry(p)) + return -EEXIST; + if (shadowp) + *shadowp = p; + mapping->nrshadows--; + if (node) + workingset_node_shadows_dec(node); + } + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + if (node) { + workingset_node_pages_inc(node); + /* + * Don't track node that contains actual pages. + * + * Avoid acquiring the list_lru lock if already + * untracked. The list_empty() test is safe as + * node->private_list is protected by + * mapping->tree_lock. + */ + if (!list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, + &node->private_list); + } + return 0; +} + +static int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask, + void **shadowp) +{ + int error; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageSwapBacked(page), page); + + error = mem_cgroup_charge_file(page, current->mm, + gfp_mask & GFP_RECLAIM_MASK); + if (error) + return error; + + error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM); + if (error) { + mem_cgroup_uncharge_cache_page(page); + return error; + } + + page_cache_get(page); + page->mapping = mapping; + page->index = offset; + + spin_lock_irq(&mapping->tree_lock); + error = page_cache_tree_insert(mapping, page, shadowp); + radix_tree_preload_end(); + if (unlikely(error)) + goto err_insert; + __inc_zone_page_state(page, NR_FILE_PAGES); + spin_unlock_irq(&mapping->tree_lock); + trace_mm_filemap_add_to_page_cache(page); + return 0; +err_insert: + page->mapping = NULL; + /* Leave page->index set: truncation relies upon it */ + spin_unlock_irq(&mapping->tree_lock); + mem_cgroup_uncharge_cache_page(page); + page_cache_release(page); + return error; +} + /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add @@ -442,51 +611,35 @@ EXPORT_SYMBOL_GPL(replace_page_cache_page); int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { - int error; - - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageSwapBacked(page)); - - error = mem_cgroup_cache_charge(page, current->mm, - gfp_mask & GFP_RECLAIM_MASK); - if (error) - goto out; - - error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); - if (error == 0) { - page_cache_get(page); - page->mapping = mapping; - page->index = offset; - - spin_lock_irq(&mapping->tree_lock); - error = radix_tree_insert(&mapping->page_tree, offset, page); - if (likely(!error)) { - mapping->nrpages++; - __inc_zone_page_state(page, NR_FILE_PAGES); - spin_unlock_irq(&mapping->tree_lock); - } else { - page->mapping = NULL; - /* Leave page->index set: truncation relies upon it */ - spin_unlock_irq(&mapping->tree_lock); - mem_cgroup_uncharge_cache_page(page); - page_cache_release(page); - } - radix_tree_preload_end(); - } else - mem_cgroup_uncharge_cache_page(page); -out: - return error; + return __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, NULL); } EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { + void *shadow = NULL; int ret; - ret = add_to_page_cache(page, mapping, offset, gfp_mask); - if (ret == 0) - lru_cache_add_file(page); + __set_page_locked(page); + ret = __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, &shadow); + if (unlikely(ret)) + __clear_page_locked(page); + else { + /* + * The page might have been evicted from cache only + * recently, in which case it should be activated like + * any other repeatedly accessed page. + */ + if (shadow && workingset_refault(shadow)) { + SetPageActive(page); + workingset_activation(page); + } else + ClearPageActive(page); + lru_cache_add(page); + } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); @@ -500,10 +653,10 @@ struct page *__page_cache_alloc(gfp_t gfp) if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = alloc_pages_exact_node(n, gfp, 0); - } while (!put_mems_allowed(cpuset_mems_cookie) && !page); + } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } @@ -587,9 +740,9 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue); */ void unlock_page(struct page *page) { - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); clear_bit_unlock(PG_locked, &page->flags); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); wake_up_page(page, PG_locked); } EXPORT_SYMBOL(unlock_page); @@ -600,17 +753,51 @@ EXPORT_SYMBOL(unlock_page); */ void end_page_writeback(struct page *page) { - if (TestClearPageReclaim(page)) + /* + * TestClearPageReclaim could be used here but it is an atomic + * operation and overkill in this particular case. Failing to + * shuffle a page marked for immediate reclaim is too mild to + * justify taking an atomic operation penalty at the end of + * ever page writeback. + */ + if (PageReclaim(page)) { + ClearPageReclaim(page); rotate_reclaimable_page(page); + } if (!test_clear_page_writeback(page)) BUG(); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); wake_up_page(page, PG_writeback); } EXPORT_SYMBOL(end_page_writeback); +/* + * After completing I/O on a page, call this routine to update the page + * flags appropriately + */ +void page_endio(struct page *page, int rw, int err) +{ + if (rw == READ) { + if (!err) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } else { /* rw == WRITE */ + if (err) { + SetPageError(page); + if (page->mapping) + mapping_set_error(page->mapping, err); + } + end_page_writeback(page); + } +} +EXPORT_SYMBOL_GPL(page_endio); + /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @page: the page to lock @@ -666,14 +853,101 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, } /** - * find_get_page - find and get a page reference + * page_cache_next_hole - find the next hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the + * lowest indexed hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'return - index >= + * max_scan' will be true). In rare cases of index wrap-around, 0 will + * be returned. + * + * page_cache_next_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 5, then subsequently a hole is created at + * index 10, page_cache_next_hole covering both indexes may return 10 + * if called under rcu_read_lock. + */ +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index++; + if (index == 0) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_next_hole); + +/** + * page_cache_prev_hole - find the prev hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search backwards in the range [max(index-max_scan+1, 0), index] for + * the first hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'index - return >= + * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX + * will be returned. + * + * page_cache_prev_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 10, then subsequently a hole is created at + * index 5, page_cache_prev_hole covering both indexes may return 5 if + * called under rcu_read_lock. + */ +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index--; + if (index == ULONG_MAX) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_prev_hole); + +/** + * find_get_entry - find and get a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. * - * Is there a pagecache struct page at the given (mapping, offset) tuple? - * If yes, increment its refcount and return it; if no, return NULL. + * If the slot holds a shadow entry of a previously evicted page, or a + * swap entry from shmem/tmpfs, it is returned. + * + * Otherwise, %NULL is returned. */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { void **pagep; struct page *page; @@ -690,9 +964,9 @@ repeat: if (radix_tree_deref_retry(page)) goto repeat; /* - * Otherwise, shmem/tmpfs must be storing a swap entry - * here as an exceptional entry: so return it without - * attempting to raise page count. + * A shadow entry of a recently evicted page, + * or a swap entry from shmem/tmpfs. Return + * it without attempting to raise page count. */ goto out; } @@ -714,24 +988,30 @@ out: return page; } -EXPORT_SYMBOL(find_get_page); +EXPORT_SYMBOL(find_get_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the slot holds a shadow entry of a previously evicted page, or a + * swap entry from shmem/tmpfs, it is returned. * - * Locates the desired pagecache page, locks it, increments its reference - * count and returns its address. + * Otherwise, %NULL is returned. * - * Returns zero if the page was not present. find_lock_page() may sleep. + * find_lock_entry() may sleep. */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: - page = find_get_page(mapping, offset); + page = find_get_entry(mapping, offset); if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ @@ -740,48 +1020,94 @@ repeat: page_cache_release(page); goto repeat; } - VM_BUG_ON(page->index != offset); + VM_BUG_ON_PAGE(page->index != offset, page); } return page; } -EXPORT_SYMBOL(find_lock_page); +EXPORT_SYMBOL(find_lock_entry); /** - * find_or_create_page - locate or add a pagecache page - * @mapping: the page's address_space - * @index: the page's index into the mapping - * @gfp_mask: page allocation mode + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * @fgp_flags: PCG flags + * @cache_gfp_mask: gfp mask to use for the page cache data page allocation + * @radix_gfp_mask: gfp mask to use for radix tree node allocation * - * Locates a page in the pagecache. If the page is not present, a new page - * is allocated using @gfp_mask and is added to the pagecache and to the VM's - * LRU list. The returned page is locked and has its reference count - * incremented. + * Looks up the page cache slot at @mapping & @offset. * - * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic - * allocation! + * PCG flags modify how the page is returned. * - * find_or_create_page() returns the desired page's address, or zero on - * memory exhaustion. + * FGP_ACCESSED: the page will be marked accessed + * FGP_LOCK: Page is return locked + * FGP_CREAT: If page is not present then a new page is allocated using + * @cache_gfp_mask and added to the page cache and the VM's LRU + * list. If radix tree nodes are allocated during page cache + * insertion then @radix_gfp_mask is used. The page is returned + * locked and with an increased refcount. Otherwise, %NULL is + * returned. + * + * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even + * if the GFP flags specified for FGP_CREAT are atomic. + * + * If there is a page cache page, it is returned with an increased refcount. */ -struct page *find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask) +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask) { struct page *page; - int err; + repeat: - page = find_lock_page(mapping, index); - if (!page) { - page = __page_cache_alloc(gfp_mask); + page = find_get_entry(mapping, offset); + if (radix_tree_exceptional_entry(page)) + page = NULL; + if (!page) + goto no_page; + + if (fgp_flags & FGP_LOCK) { + if (fgp_flags & FGP_NOWAIT) { + if (!trylock_page(page)) { + page_cache_release(page); + return NULL; + } + } else { + lock_page(page); + } + + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + page_cache_release(page); + goto repeat; + } + VM_BUG_ON_PAGE(page->index != offset, page); + } + + if (page && (fgp_flags & FGP_ACCESSED)) + mark_page_accessed(page); + +no_page: + if (!page && (fgp_flags & FGP_CREAT)) { + int err; + if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) + cache_gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) { + cache_gfp_mask &= ~__GFP_FS; + radix_gfp_mask &= ~__GFP_FS; + } + + page = __page_cache_alloc(cache_gfp_mask); if (!page) return NULL; - /* - * We want a regular kernel memory (not highmem or DMA etc) - * allocation for the radix tree nodes, but we need to honour - * the context-specific requirements the caller has asked for. - * GFP_RECLAIM_MASK collects those requirements. - */ - err = add_to_page_cache_lru(page, mapping, index, - (gfp_mask & GFP_RECLAIM_MASK)); + + if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK))) + fgp_flags |= FGP_LOCK; + + /* Init accessed so avoit atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + init_page_accessed(page); + + err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -789,9 +1115,80 @@ repeat: goto repeat; } } + return page; } -EXPORT_SYMBOL(find_or_create_page); +EXPORT_SYMBOL(pagecache_get_page); + +/** + * find_get_entries - gang pagecache lookup + * @mapping: The address_space to search + * @start: The starting page cache index + * @nr_entries: The maximum number of entries + * @entries: Where the resulting entries are placed + * @indices: The cache indices corresponding to the entries in @entries + * + * find_get_entries() will search for and return a group of up to + * @nr_entries entries in the mapping. The entries are placed at + * @entries. find_get_entries() takes a reference against any actual + * pages it returns. + * + * The search returns a group of mapping-contiguous page cache entries + * with ascending indexes. There may be holes in the indices due to + * not-present pages. + * + * Any shadow entries of evicted pages, or swap entries from + * shmem/tmpfs, are included in the returned array. + * + * find_get_entries() returns the number of pages and shadow entries + * which were found. + */ +unsigned find_get_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_entries) + return 0; + + rcu_read_lock(); +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + struct page *page; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + /* + * A shadow entry of a recently evicted page, + * or a swap entry from shmem/tmpfs. Return + * it without attempting to raise page count. + */ + goto export; + } + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } +export: + indices[ret] = iter.index; + entries[ret] = page; + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + return ret; +} /** * find_get_pages - gang pagecache lookup @@ -839,9 +1236,9 @@ repeat: goto restart; } /* - * Otherwise, shmem/tmpfs must be storing a swap entry - * here as an exceptional entry: so skip over it - - * we only reach this from invalidate_mapping_pages(). + * A shadow entry of a recently evicted page, + * or a swap entry from shmem/tmpfs. Skip + * over it. */ continue; } @@ -906,9 +1303,9 @@ repeat: goto restart; } /* - * Otherwise, shmem/tmpfs must be storing a swap entry - * here as an exceptional entry: so stop looking for - * contiguous pages. + * A shadow entry of a recently evicted page, + * or a swap entry from shmem/tmpfs. Stop + * looking for contiguous pages. */ break; } @@ -982,10 +1379,17 @@ repeat: goto restart; } /* - * This function is never used on a shmem/tmpfs - * mapping, so a swap entry won't be found here. + * A shadow entry of a recently evicted page. + * + * Those entries should never be tagged, but + * this tree walk is lockless and the tags are + * looked up in bulk, one radix tree node at a + * time, so there is a sizable window for page + * reclaim to evict a page we saw tagged. + * + * Skip over it. */ - BUG(); + continue; } if (!page_cache_get_speculative(page)) @@ -1011,39 +1415,6 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); -/** - * grab_cache_page_nowait - returns locked page at given index in given cache - * @mapping: target address_space - * @index: the page index - * - * Same as grab_cache_page(), but do not wait if the page is unavailable. - * This is intended for speculative data generators, where the data can - * be regenerated if the page couldn't be grabbed. This routine should - * be safe to call while holding the lock for another page. - * - * Clear __GFP_FS when allocating the page to avoid recursion into the fs - * and deadlock against the caller's locked page. - */ -struct page * -grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) -{ - struct page *page = find_get_page(mapping, index); - - if (page) { - if (trylock_page(page)) - return page; - page_cache_release(page); - return NULL; - } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); - if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) { - page_cache_release(page); - page = NULL; - } - return page; -} -EXPORT_SYMBOL(grab_cache_page_nowait); - /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: @@ -1069,8 +1440,8 @@ static void shrink_readahead_size_eio(struct file *filp, * do_generic_file_read - generic file read routine * @filp: the file to read * @ppos: current file position - * @desc: read_descriptor - * @actor: read method + * @iter: data destination + * @written: already copied * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. @@ -1078,8 +1449,8 @@ static void shrink_readahead_size_eio(struct file *filp, * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. */ -static void do_generic_file_read(struct file *filp, loff_t *ppos, - read_descriptor_t *desc, read_actor_t actor) +static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, + struct iov_iter *iter, ssize_t written) { struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; @@ -1089,12 +1460,12 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos, pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; - int error; + int error = 0; index = *ppos >> PAGE_CACHE_SHIFT; prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT; prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1); - last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; + last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; offset = *ppos & ~PAGE_CACHE_MASK; for (;;) { @@ -1129,7 +1500,7 @@ find_page: if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, - desc, offset)) + offset, iter->count)) goto page_not_up_to_date_locked; unlock_page(page); } @@ -1179,23 +1550,23 @@ page_ok: /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... - * - * The actor routine returns how many bytes were actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). */ - ret = actor(desc, page, offset, nr); + + ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; prev_offset = offset; page_cache_release(page); - if (ret == nr && desc->count) - continue; - goto out; + written += ret; + if (!iov_iter_count(iter)) + goto out; + if (ret < nr) { + error = -EFAULT; + goto out; + } + continue; page_not_up_to_date: /* Get exclusive access to the page ... */ @@ -1230,6 +1601,7 @@ readpage: if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { page_cache_release(page); + error = 0; goto find_page; } goto readpage_error; @@ -1260,7 +1632,6 @@ readpage: readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ - desc->error = error; page_cache_release(page); goto out; @@ -1271,16 +1642,17 @@ no_cached_page: */ page = page_cache_alloc_cold(mapping); if (!page) { - desc->error = -ENOMEM; + error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); if (error) { page_cache_release(page); - if (error == -EEXIST) + if (error == -EEXIST) { + error = 0; goto find_page; - desc->error = error; + } goto out; } goto readpage; @@ -1293,185 +1665,66 @@ out: *ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset; file_accessed(filp); + return written ? written : error; } -int file_read_actor(read_descriptor_t *desc, struct page *page, - unsigned long offset, unsigned long size) -{ - char *kaddr; - unsigned long left, count = desc->count; - - if (size > count) - size = count; - - /* - * Faults on the destination of a read are common, so do it before - * taking the kmap. - */ - if (!fault_in_pages_writeable(desc->arg.buf, size)) { - kaddr = kmap_atomic(page); - left = __copy_to_user_inatomic(desc->arg.buf, - kaddr + offset, size); - kunmap_atomic(kaddr); - if (left == 0) - goto success; - } - - /* Do it the slow way */ - kaddr = kmap(page); - left = __copy_to_user(desc->arg.buf, kaddr + offset, size); - kunmap(page); - - if (left) { - size -= left; - desc->error = -EFAULT; - } -success: - desc->count = count - size; - desc->written += size; - desc->arg.buf += size; - return size; -} - -/* - * Performs necessary checks before doing a write - * @iov: io vector request - * @nr_segs: number of segments in the iovec - * @count: number of bytes to write - * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE - * - * Adjust number of segments and amount of bytes to write (nr_segs should be - * properly initialized first). Returns appropriate error code that caller - * should return or zero in case that write should be allowed. - */ -int generic_segment_checks(const struct iovec *iov, - unsigned long *nr_segs, size_t *count, int access_flags) -{ - unsigned long seg; - size_t cnt = 0; - for (seg = 0; seg < *nr_segs; seg++) { - const struct iovec *iv = &iov[seg]; - - /* - * If any segment has a negative length, or the cumulative - * length ever wraps negative then return -EINVAL. - */ - cnt += iv->iov_len; - if (unlikely((ssize_t)(cnt|iv->iov_len) < 0)) - return -EINVAL; - if (access_ok(access_flags, iv->iov_base, iv->iov_len)) - continue; - if (seg == 0) - return -EFAULT; - *nr_segs = seg; - cnt -= iv->iov_len; /* This segment is no good */ - break; - } - *count = cnt; - return 0; -} -EXPORT_SYMBOL(generic_segment_checks); - /** - * generic_file_aio_read - generic filesystem read routine + * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block - * @iov: io vector request - * @nr_segs: number of segments in the iovec - * @pos: current file position + * @iter: destination for the data read * - * This is the "read()" routine for all filesystems + * This is the "read_iter()" 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 pos) +generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct file *filp = iocb->ki_filp; - ssize_t retval; - unsigned long seg = 0; - size_t count; + struct file *file = iocb->ki_filp; + ssize_t retval = 0; loff_t *ppos = &iocb->ki_pos; - - count = 0; - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; + loff_t pos = *ppos; /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ - if (filp->f_flags & O_DIRECT) { + if (file->f_flags & O_DIRECT) { + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); loff_t size; - struct address_space *mapping; - struct inode *inode; - mapping = filp->f_mapping; - inode = mapping->host; if (!count) goto out; /* skip atime */ size = i_size_read(inode); - if (pos < size) { - retval = filemap_write_and_wait_range(mapping, pos, - pos + iov_length(iov, nr_segs) - 1); - if (!retval) { - retval = mapping->a_ops->direct_IO(READ, iocb, - iov, pos, nr_segs); - } - if (retval > 0) { - *ppos = pos + retval; - count -= retval; - } - - /* - * Btrfs can have a short DIO read if we encounter - * compressed extents, so if there was an error, or if - * we've already read everything we wanted to, or if - * there was a short read because we hit EOF, go ahead - * and return. Otherwise fallthrough to buffered io for - * the rest of the read. - */ - if (retval < 0 || !count || *ppos >= size) { - file_accessed(filp); - goto out; - } + retval = filemap_write_and_wait_range(mapping, pos, + pos + count - 1); + if (!retval) { + struct iov_iter data = *iter; + retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos); } - } - count = retval; - for (seg = 0; seg < nr_segs; seg++) { - read_descriptor_t desc; - loff_t offset = 0; + if (retval > 0) { + *ppos = pos + retval; + iov_iter_advance(iter, retval); + } /* - * If we did a short DIO read we need to skip the section of the - * iov that we've already read data into. + * Btrfs can have a short DIO read if we encounter + * compressed extents, so if there was an error, or if + * we've already read everything we wanted to, or if + * there was a short read because we hit EOF, go ahead + * and return. Otherwise fallthrough to buffered io for + * the rest of the read. */ - if (count) { - if (count > iov[seg].iov_len) { - count -= iov[seg].iov_len; - continue; - } - offset = count; - count = 0; - } - - desc.written = 0; - desc.arg.buf = iov[seg].iov_base + offset; - desc.count = iov[seg].iov_len - offset; - if (desc.count == 0) - continue; - desc.error = 0; - do_generic_file_read(filp, ppos, &desc, file_read_actor); - retval += desc.written; - if (desc.error) { - retval = retval ?: desc.error; - break; + if (retval < 0 || !iov_iter_count(iter) || *ppos >= size) { + file_accessed(file); + goto out; } - if (desc.count > 0) - break; } + + retval = do_generic_file_read(file, ppos, iter, retval); out: return retval; } -EXPORT_SYMBOL(generic_file_aio_read); +EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU /** @@ -1521,12 +1774,12 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma, struct address_space *mapping = file->f_mapping; /* If we don't want any read-ahead, don't bother */ - if (VM_RandomReadHint(vma)) + if (vma->vm_flags & VM_RAND_READ) return; if (!ra->ra_pages) return; - if (VM_SequentialReadHint(vma)) { + if (vma->vm_flags & VM_SEQ_READ) { page_cache_sync_readahead(mapping, ra, file, offset, ra->ra_pages); return; @@ -1566,7 +1819,7 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma, struct address_space *mapping = file->f_mapping; /* If we don't want any read-ahead, don't bother */ - if (VM_RandomReadHint(vma)) + if (vma->vm_flags & VM_RAND_READ) return; if (ra->mmap_miss > 0) ra->mmap_miss--; @@ -1596,11 +1849,11 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; struct page *page; - pgoff_t size; + loff_t size; int ret = 0; - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (offset >= size) + size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); + if (offset >= size >> PAGE_CACHE_SHIFT) return VM_FAULT_SIGBUS; /* @@ -1636,7 +1889,7 @@ retry_find: put_page(page); goto retry_find; } - VM_BUG_ON(page->index != offset); + VM_BUG_ON_PAGE(page->index != offset, page); /* * We have a locked page in the page cache, now we need to check @@ -1649,8 +1902,8 @@ retry_find: * Found the page and have a reference on it. * We must recheck i_size under page lock. */ - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (unlikely(offset >= size)) { + size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); + if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) { unlock_page(page); page_cache_release(page); return VM_FAULT_SIGBUS; @@ -1708,10 +1961,82 @@ page_not_uptodate: } EXPORT_SYMBOL(filemap_fault); +void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct radix_tree_iter iter; + void **slot; + struct file *file = vma->vm_file; + struct address_space *mapping = file->f_mapping; + loff_t size; + struct page *page; + unsigned long address = (unsigned long) vmf->virtual_address; + unsigned long addr; + pte_t *pte; + + rcu_read_lock(); + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) { + if (iter.index > vmf->max_pgoff) + break; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + goto next; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + break; + else + goto next; + } + + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } + + if (!PageUptodate(page) || + PageReadahead(page) || + PageHWPoison(page)) + goto skip; + if (!trylock_page(page)) + goto skip; + + if (page->mapping != mapping || !PageUptodate(page)) + goto unlock; + + size = round_up(i_size_read(mapping->host), PAGE_CACHE_SIZE); + if (page->index >= size >> PAGE_CACHE_SHIFT) + goto unlock; + + pte = vmf->pte + page->index - vmf->pgoff; + if (!pte_none(*pte)) + goto unlock; + + if (file->f_ra.mmap_miss > 0) + file->f_ra.mmap_miss--; + addr = address + (page->index - vmf->pgoff) * PAGE_SIZE; + do_set_pte(vma, addr, page, pte, false, false); + unlock_page(page); + goto next; +unlock: + unlock_page(page); +skip: + page_cache_release(page); +next: + if (iter.index == vmf->max_pgoff) + break; + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(filemap_map_pages); + int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page = vmf->page; - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); int ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); @@ -1728,6 +2053,7 @@ int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) * see the dirty page and writeprotect it again. */ set_page_dirty(page); + wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return ret; @@ -1736,6 +2062,7 @@ EXPORT_SYMBOL(filemap_page_mkwrite); const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, .remap_pages = generic_file_remap_pages, }; @@ -1776,6 +2103,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + page_cache_release(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), @@ -1802,6 +2141,8 @@ repeat: if (err < 0) { page_cache_release(page); page = ERR_PTR(err); + } else { + page = wait_on_page_read(page); } } return page; @@ -1838,6 +2179,10 @@ retry: if (err < 0) { page_cache_release(page); return ERR_PTR(err); + } else { + page = wait_on_page_read(page); + if (IS_ERR(page)) + return page; } out: mark_page_accessed(page); @@ -1845,40 +2190,25 @@ out: } /** - * read_cache_page_async - read into page cache, fill it if needed + * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * - * Same as read_cache_page, but don't wait for page to become unlocked - * after submitting it to the filler. - * * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page but don't wait for it to become unlocked. + * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */ -struct page *read_cache_page_async(struct address_space *mapping, +struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } -EXPORT_SYMBOL(read_cache_page_async); - -static struct page *wait_on_page_read(struct page *page) -{ - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); - } - } - return page; -} +EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. @@ -1897,175 +2227,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping, { filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); + return do_read_cache_page(mapping, index, filler, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); -/** - * read_cache_page - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: first arg to filler(data, page) function, often left as NULL - * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page then wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. - */ -struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) -{ - return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); -} -EXPORT_SYMBOL(read_cache_page); - -static size_t __iovec_copy_from_user_inatomic(char *vaddr, - const struct iovec *iov, size_t base, size_t bytes) -{ - size_t copied = 0, left = 0; - - while (bytes) { - char __user *buf = iov->iov_base + base; - int copy = min(bytes, iov->iov_len - base); - - base = 0; - left = __copy_from_user_inatomic(vaddr, buf, copy); - copied += copy; - bytes -= copy; - vaddr += copy; - iov++; - - if (unlikely(left)) - break; - } - return copied - left; -} - -/* - * Copy as much as we can into the page and return the number of bytes which - * were successfully copied. If a fault is encountered then return the number of - * bytes which were copied. - */ -size_t iov_iter_copy_from_user_atomic(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - BUG_ON(!in_atomic()); - kaddr = kmap_atomic(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap_atomic(kaddr); - - return copied; -} -EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); - -/* - * This has the same sideeffects and return value as - * iov_iter_copy_from_user_atomic(). - * The difference is that it attempts to resolve faults. - * Page must not be locked. - */ -size_t iov_iter_copy_from_user(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - kaddr = kmap(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap(page); - return copied; -} -EXPORT_SYMBOL(iov_iter_copy_from_user); - -void iov_iter_advance(struct iov_iter *i, size_t bytes) -{ - BUG_ON(i->count < bytes); - - if (likely(i->nr_segs == 1)) { - i->iov_offset += bytes; - i->count -= bytes; - } else { - const struct iovec *iov = i->iov; - size_t base = i->iov_offset; - unsigned long nr_segs = i->nr_segs; - - /* - * The !iov->iov_len check ensures we skip over unlikely - * zero-length segments (without overruning the iovec). - */ - while (bytes || unlikely(i->count && !iov->iov_len)) { - int copy; - - copy = min(bytes, iov->iov_len - base); - BUG_ON(!i->count || i->count < copy); - i->count -= copy; - bytes -= copy; - base += copy; - if (iov->iov_len == base) { - iov++; - nr_segs--; - base = 0; - } - } - i->iov = iov; - i->iov_offset = base; - i->nr_segs = nr_segs; - } -} -EXPORT_SYMBOL(iov_iter_advance); - -/* - * Fault in the first iovec of the given iov_iter, to a maximum length - * of bytes. Returns 0 on success, or non-zero if the memory could not be - * accessed (ie. because it is an invalid address). - * - * writev-intensive code may want this to prefault several iovecs -- that - * would be possible (callers must not rely on the fact that _only_ the - * first iovec will be faulted with the current implementation). - */ -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) -{ - char __user *buf = i->iov->iov_base + i->iov_offset; - bytes = min(bytes, i->iov->iov_len - i->iov_offset); - return fault_in_pages_readable(buf, bytes); -} -EXPORT_SYMBOL(iov_iter_fault_in_readable); - -/* - * Return the count of just the current iov_iter segment. - */ -size_t iov_iter_single_seg_count(struct iov_iter *i) -{ - const struct iovec *iov = i->iov; - if (i->nr_segs == 1) - return i->count; - else - return min(i->count, iov->iov_len - i->iov_offset); -} -EXPORT_SYMBOL(iov_iter_single_seg_count); - /* * Performs necessary checks before doing a write * @@ -2165,15 +2330,12 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - mark_page_accessed(page); return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); ssize_t -generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long *nr_segs, loff_t pos, loff_t *ppos, - size_t count, size_t ocount) +generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -2181,11 +2343,9 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, ssize_t written; size_t write_len; pgoff_t end; + struct iov_iter data; - if (count != ocount) - *nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count); - - write_len = iov_length(iov, *nr_segs); + write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT; written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); @@ -2212,7 +2372,8 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, } } - written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs); + data = *from; + written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos); /* * Finally, try again to invalidate clean pages which might have been @@ -2229,11 +2390,12 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, if (written > 0) { pos += written; + iov_iter_advance(from, written); if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } - *ppos = pos; + iocb->ki_pos = pos; } out: return written; @@ -2247,39 +2409,23 @@ EXPORT_SYMBOL(generic_file_direct_write); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { - int status; - gfp_t gfp_mask; struct page *page; - gfp_t gfp_notmask = 0; + int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT; - gfp_mask = mapping_gfp_mask(mapping); - if (mapping_cap_account_dirty(mapping)) - gfp_mask |= __GFP_WRITE; if (flags & AOP_FLAG_NOFS) - gfp_notmask = __GFP_FS; -repeat: - page = find_lock_page(mapping, index); + fgp_flags |= FGP_NOFS; + + page = pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping), + GFP_KERNEL); if (page) - goto found; + wait_for_stable_page(page); - page = __page_cache_alloc(gfp_mask & ~gfp_notmask); - if (!page) - return NULL; - status = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & ~gfp_notmask); - if (unlikely(status)) { - page_cache_release(page); - if (status == -EEXIST) - goto repeat; - return NULL; - } -found: - wait_on_page_writeback(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); -static ssize_t generic_perform_write(struct file *file, +ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; @@ -2323,18 +2469,15 @@ again: status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); - if (unlikely(status)) + if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) @@ -2369,34 +2512,12 @@ again: return written ? written : status; } - -ssize_t -generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, loff_t *ppos, - size_t count, ssize_t written) -{ - struct file *file = iocb->ki_filp; - ssize_t status; - struct iov_iter i; - - iov_iter_init(&i, iov, nr_segs, count, written); - status = generic_perform_write(file, &i, pos); - - if (likely(status >= 0)) { - written += status; - *ppos = pos + status; - } - - return written ? written : status; -} -EXPORT_SYMBOL(generic_file_buffered_write); +EXPORT_SYMBOL(generic_perform_write); /** - * __generic_file_aio_write - write data to a file + * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) - * @iov: vector with data to write - * @nr_segs: number of segments in the vector - * @ppos: position where to write + * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates @@ -2410,30 +2531,19 @@ EXPORT_SYMBOL(generic_file_buffered_write); * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. */ -ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; - size_t ocount; /* original count */ - size_t count; /* after file limit checks */ struct inode *inode = mapping->host; - loff_t pos; - ssize_t written; + loff_t pos = iocb->ki_pos; + ssize_t written = 0; ssize_t err; - - ocount = 0; - err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); - if (err) - return err; - - count = ocount; - pos = *ppos; + ssize_t status; + size_t count = iov_iter_count(from); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; - written = 0; - err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) goto out; @@ -2441,6 +2551,8 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; + iov_iter_truncate(from, count); + err = file_remove_suid(file); if (err) goto out; @@ -2452,42 +2564,40 @@ ssize_t __generic_file_aio_write(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)) { loff_t endbyte; - ssize_t written_buffered; - written = generic_file_direct_write(iocb, iov, &nr_segs, pos, - ppos, count, ocount); + written = generic_file_direct_write(iocb, from, pos); if (written < 0 || written == count) goto out; + /* * direct-io write to a hole: fall through to buffered I/O * for completing the rest of the request. */ pos += written; count -= written; - written_buffered = generic_file_buffered_write(iocb, iov, - nr_segs, pos, ppos, count, - written); + + status = generic_perform_write(file, from, pos); /* - * If generic_file_buffered_write() retuned a synchronous error + * If generic_perform_write() returned 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; + if (unlikely(status < 0) && !written) { + err = status; goto out; } - + iocb->ki_pos = pos + status; /* * 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; + endbyte = pos + status - 1; err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte); if (err == 0) { - written = written_buffered; + written += status; invalidate_mapping_pages(mapping, pos >> PAGE_CACHE_SHIFT, endbyte >> PAGE_CACHE_SHIFT); @@ -2498,51 +2608,45 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, */ } } else { - written = generic_file_buffered_write(iocb, iov, nr_segs, - pos, ppos, count, written); + written = generic_perform_write(file, from, pos); + if (likely(written >= 0)) + iocb->ki_pos = pos + written; } out: current->backing_dev_info = NULL; return written ? written : err; } -EXPORT_SYMBOL(__generic_file_aio_write); +EXPORT_SYMBOL(__generic_file_write_iter); /** - * generic_file_aio_write - write data to a file + * generic_file_write_iter - write data to a file * @iocb: IO state structure - * @iov: vector with data to write - * @nr_segs: number of segments in the vector - * @pos: position in file where to write + * @from: iov_iter with data to write * - * This is a wrapper around __generic_file_aio_write() to be used by most + * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. */ -ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; - BUG_ON(iocb->ki_pos != pos); - - sb_start_write(inode->i_sb); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + ret = __generic_file_write_iter(iocb, from); mutex_unlock(&inode->i_mutex); - if (ret > 0 || ret == -EIOCBQUEUED) { + if (ret > 0) { ssize_t err; - err = generic_write_sync(file, pos, ret); - if (err < 0 && ret > 0) + err = generic_write_sync(file, iocb->ki_pos - ret, ret); + if (err < 0) ret = err; } - sb_end_write(inode->i_sb); return ret; } -EXPORT_SYMBOL(generic_file_aio_write); +EXPORT_SYMBOL(generic_file_write_iter); /** * try_to_release_page() - release old fs-specific metadata on a page diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index a912da6ddfd..d8d9fe3f685 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -26,7 +26,7 @@ * of ZERO_PAGE(), such as /dev/zero */ static DEFINE_MUTEX(xip_sparse_mutex); -static seqcount_t xip_sparse_seq = SEQCNT_ZERO; +static seqcount_t xip_sparse_seq = SEQCNT_ZERO(xip_sparse_seq); static struct page *__xip_sparse_page; /* called under xip_sparse_mutex */ @@ -404,8 +404,6 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len, loff_t pos; ssize_t ret; - sb_start_write(inode->i_sb); - mutex_lock(&inode->i_mutex); if (!access_ok(VERIFY_READ, buf, len)) { @@ -439,7 +437,6 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len, current->backing_dev_info = NULL; out_up: mutex_unlock(&inode->i_mutex); - sb_end_write(inode->i_sb); return ret; } EXPORT_SYMBOL_GPL(xip_file_write); diff --git a/mm/fremap.c b/mm/fremap.c index a0aaf0e5680..72b8fa36143 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -23,28 +23,44 @@ #include "internal.h" +static int mm_counter(struct page *page) +{ + return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES; +} + static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; + struct page *page; + swp_entry_t entry; if (pte_present(pte)) { - struct page *page; - flush_cache_page(vma, addr, pte_pfn(pte)); pte = ptep_clear_flush(vma, addr, ptep); page = vm_normal_page(vma, addr, pte); if (page) { if (pte_dirty(pte)) set_page_dirty(page); + update_hiwater_rss(mm); + dec_mm_counter(mm, mm_counter(page)); page_remove_rmap(page); page_cache_release(page); + } + } else { /* zap_pte() is not called when pte_none() */ + if (!pte_file(pte)) { update_hiwater_rss(mm); - dec_mm_counter(mm, MM_FILEPAGES); + entry = pte_to_swp_entry(pte); + if (non_swap_entry(entry)) { + if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + dec_mm_counter(mm, mm_counter(page)); + } + } else { + free_swap_and_cache(entry); + dec_mm_counter(mm, MM_SWAPENTS); + } } - } else { - if (!pte_file(pte)) - free_swap_and_cache(pte_to_swp_entry(pte)); pte_clear_not_present_full(mm, addr, ptep, 0); } } @@ -57,17 +73,19 @@ static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot) { int err = -ENOMEM; - pte_t *pte; + pte_t *pte, ptfile; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) goto out; + ptfile = pgoff_to_pte(pgoff); + if (!pte_none(*pte)) zap_pte(mm, vma, addr, pte); - set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff)); + set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile)); /* * 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 @@ -129,6 +147,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, struct vm_area_struct *vma; int err = -EINVAL; int has_write_lock = 0; + vm_flags_t vm_flags = 0; + + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " + "See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); if (prot) return err; @@ -160,15 +183,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, /* * Make sure the vma is shared, that it supports prefaulting, * and that the remapped range is valid and fully within - * the single existing vma. vm_private_data is used as a - * swapout cursor in a VM_NONLINEAR vma. + * the single existing vma. */ if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; - if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR)) - goto out; - if (!vma->vm_ops || !vma->vm_ops->remap_pages) goto out; @@ -177,6 +196,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, /* Must set VM_NONLINEAR before any pages are populated. */ if (!(vma->vm_flags & VM_NONLINEAR)) { + /* + * vm_private_data is used as a swapout cursor + * in a VM_NONLINEAR vma. + */ + if (vma->vm_private_data) + goto out; + /* Don't need a nonlinear mapping, exit success */ if (pgoff == linear_page_index(vma, start)) { err = 0; @@ -184,6 +210,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, } if (!has_write_lock) { +get_write_lock: up_read(&mm->mmap_sem); down_write(&mm->mmap_sem); has_write_lock = 1; @@ -198,10 +225,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (mapping_cap_account_dirty(mapping)) { unsigned long addr; struct file *file = get_file(vma->vm_file); + /* mmap_region may free vma; grab the info now */ + vm_flags = vma->vm_flags; - flags &= MAP_NONBLOCK; - addr = mmap_region(file, start, size, - flags, vma->vm_flags, pgoff); + addr = mmap_region(file, start, size, vm_flags, pgoff); fput(file); if (IS_ERR_VALUE(addr)) { err = addr; @@ -209,7 +236,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, BUG_ON(addr != start); err = 0; } - goto out; + goto out_freed; } mutex_lock(&mapping->i_mmap_mutex); flush_dcache_mmap_lock(mapping); @@ -224,28 +251,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, /* * drop PG_Mlocked flag for over-mapped range */ - vm_flags_t saved_flags = vma->vm_flags; + if (!has_write_lock) + goto get_write_lock; + vm_flags = vma->vm_flags; munlock_vma_pages_range(vma, start, start + size); - vma->vm_flags = saved_flags; + vma->vm_flags = vm_flags; } mmu_notifier_invalidate_range_start(mm, start, start + size); err = vma->vm_ops->remap_pages(vma, start, size, pgoff); mmu_notifier_invalidate_range_end(mm, start, start + size); - if (!err && !(flags & MAP_NONBLOCK)) { - if (vma->vm_flags & VM_LOCKED) { - /* - * might be mapping previously unmapped range of file - */ - mlock_vma_pages_range(vma, start, start + size); - } else { - if (unlikely(has_write_lock)) { - downgrade_write(&mm->mmap_sem); - has_write_lock = 0; - } - make_pages_present(start, start+size); - } - } /* * We can't clear VM_NONLINEAR because we'd have to do @@ -254,10 +269,15 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, */ out: + if (vma) + vm_flags = vma->vm_flags; +out_freed: if (likely(!has_write_lock)) up_read(&mm->mmap_sem); else up_write(&mm->mmap_sem); + if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK))) + mm_populate(start, size); return err; } diff --git a/mm/frontswap.c b/mm/frontswap.c index 2890e67d602..c30eec536f0 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -24,15 +24,7 @@ * frontswap_ops is set by frontswap_register_ops to contain the pointers * to the frontswap "backend" implementation functions. */ -static struct frontswap_ops frontswap_ops __read_mostly; - -/* - * This global enablement flag reduces overhead on systems where frontswap_ops - * has not been registered, so is preferred to the slower alternative: a - * function call that checks a non-global. - */ -bool frontswap_enabled __read_mostly; -EXPORT_SYMBOL(frontswap_enabled); +static struct frontswap_ops *frontswap_ops __read_mostly; /* * If enabled, frontswap_store will return failure even on success. As @@ -80,16 +72,70 @@ static inline void inc_frontswap_succ_stores(void) { } static inline void inc_frontswap_failed_stores(void) { } static inline void inc_frontswap_invalidates(void) { } #endif + +/* + * Due to the asynchronous nature of the backends loading potentially + * _after_ the swap system has been activated, we have chokepoints + * on all frontswap functions to not call the backend until the backend + * has registered. + * + * Specifically when no backend is registered (nobody called + * frontswap_register_ops) all calls to frontswap_init (which is done via + * swapon -> enable_swap_info -> frontswap_init) are registered and remembered + * (via the setting of need_init bitmap) but fail to create tmem_pools. When a + * backend registers with frontswap at some later point the previous + * calls to frontswap_init are executed (by iterating over the need_init + * bitmap) to create tmem_pools and set the respective poolids. All of that is + * guarded by us using atomic bit operations on the 'need_init' bitmap. + * + * This would not guards us against the user deciding to call swapoff right as + * we are calling the backend to initialize (so swapon is in action). + * Fortunatly for us, the swapon_mutex has been taked by the callee so we are + * OK. The other scenario where calls to frontswap_store (called via + * swap_writepage) is racing with frontswap_invalidate_area (called via + * swapoff) is again guarded by the swap subsystem. + * + * While no backend is registered all calls to frontswap_[store|load| + * invalidate_area|invalidate_page] are ignored or fail. + * + * The time between the backend being registered and the swap file system + * calling the backend (via the frontswap_* functions) is indeterminate as + * frontswap_ops is not atomic_t (or a value guarded by a spinlock). + * That is OK as we are comfortable missing some of these calls to the newly + * registered backend. + * + * Obviously the opposite (unloading the backend) must be done after all + * the frontswap_[store|load|invalidate_area|invalidate_page] start + * ignorning or failing the requests - at which point frontswap_ops + * would have to be made in some fashion atomic. + */ +static DECLARE_BITMAP(need_init, MAX_SWAPFILES); + /* * Register operations for frontswap, returning previous thus allowing * detection of multiple backends and possible nesting. */ -struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops) +struct frontswap_ops *frontswap_register_ops(struct frontswap_ops *ops) { - struct frontswap_ops old = frontswap_ops; - - frontswap_ops = *ops; - frontswap_enabled = true; + struct frontswap_ops *old = frontswap_ops; + int i; + + for (i = 0; i < MAX_SWAPFILES; i++) { + if (test_and_clear_bit(i, need_init)) { + struct swap_info_struct *sis = swap_info[i]; + /* __frontswap_init _should_ have set it! */ + if (!sis->frontswap_map) + return ERR_PTR(-EINVAL); + ops->init(i); + } + } + /* + * We MUST have frontswap_ops set _after_ the frontswap_init's + * have been called. Otherwise __frontswap_store might fail. Hence + * the barrier to make sure compiler does not re-order us. + */ + barrier(); + frontswap_ops = ops; return old; } EXPORT_SYMBOL(frontswap_register_ops); @@ -115,20 +161,48 @@ EXPORT_SYMBOL(frontswap_tmem_exclusive_gets); /* * Called when a swap device is swapon'd. */ -void __frontswap_init(unsigned type) +void __frontswap_init(unsigned type, unsigned long *map) { struct swap_info_struct *sis = swap_info[type]; BUG_ON(sis == NULL); - if (sis->frontswap_map == NULL) + + /* + * p->frontswap is a bitmap that we MUST have to figure out which page + * has gone in frontswap. Without it there is no point of continuing. + */ + if (WARN_ON(!map)) return; - frontswap_ops.init(type); + /* + * Irregardless of whether the frontswap backend has been loaded + * before this function or it will be later, we _MUST_ have the + * p->frontswap set to something valid to work properly. + */ + frontswap_map_set(sis, map); + if (frontswap_ops) + frontswap_ops->init(type); + else { + BUG_ON(type > MAX_SWAPFILES); + set_bit(type, need_init); + } } EXPORT_SYMBOL(__frontswap_init); -static inline void __frontswap_clear(struct swap_info_struct *sis, pgoff_t offset) +bool __frontswap_test(struct swap_info_struct *sis, + pgoff_t offset) +{ + bool ret = false; + + if (frontswap_ops && sis->frontswap_map) + ret = test_bit(offset, sis->frontswap_map); + return ret; +} +EXPORT_SYMBOL(__frontswap_test); + +static inline void __frontswap_clear(struct swap_info_struct *sis, + pgoff_t offset) { - frontswap_clear(sis, offset); + clear_bit(offset, sis->frontswap_map); atomic_dec(&sis->frontswap_pages); } @@ -147,13 +221,20 @@ int __frontswap_store(struct page *page) struct swap_info_struct *sis = swap_info[type]; pgoff_t offset = swp_offset(entry); + /* + * Return if no backend registed. + * Don't need to inc frontswap_failed_stores here. + */ + if (!frontswap_ops) + return ret; + BUG_ON(!PageLocked(page)); BUG_ON(sis == NULL); - if (frontswap_test(sis, offset)) + if (__frontswap_test(sis, offset)) dup = 1; - ret = frontswap_ops.store(type, offset, page); + ret = frontswap_ops->store(type, offset, page); if (ret == 0) { - frontswap_set(sis, offset); + set_bit(offset, sis->frontswap_map); inc_frontswap_succ_stores(); if (!dup) atomic_inc(&sis->frontswap_pages); @@ -188,13 +269,16 @@ int __frontswap_load(struct page *page) BUG_ON(!PageLocked(page)); BUG_ON(sis == NULL); - if (frontswap_test(sis, offset)) - ret = frontswap_ops.load(type, offset, page); + /* + * __frontswap_test() will check whether there is backend registered + */ + if (__frontswap_test(sis, offset)) + ret = frontswap_ops->load(type, offset, page); if (ret == 0) { inc_frontswap_loads(); if (frontswap_tmem_exclusive_gets_enabled) { SetPageDirty(page); - frontswap_clear(sis, offset); + __frontswap_clear(sis, offset); } } return ret; @@ -210,8 +294,11 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset) struct swap_info_struct *sis = swap_info[type]; BUG_ON(sis == NULL); - if (frontswap_test(sis, offset)) { - frontswap_ops.invalidate_page(type, offset); + /* + * __frontswap_test() will check whether there is backend registered + */ + if (__frontswap_test(sis, offset)) { + frontswap_ops->invalidate_page(type, offset); __frontswap_clear(sis, offset); inc_frontswap_invalidates(); } @@ -226,26 +313,26 @@ void __frontswap_invalidate_area(unsigned type) { struct swap_info_struct *sis = swap_info[type]; - BUG_ON(sis == NULL); - if (sis->frontswap_map == NULL) - return; - frontswap_ops.invalidate_area(type); - atomic_set(&sis->frontswap_pages, 0); - memset(sis->frontswap_map, 0, sis->max / sizeof(long)); + if (frontswap_ops) { + BUG_ON(sis == NULL); + if (sis->frontswap_map == NULL) + return; + frontswap_ops->invalidate_area(type); + atomic_set(&sis->frontswap_pages, 0); + bitmap_zero(sis->frontswap_map, sis->max); + } + clear_bit(type, need_init); } EXPORT_SYMBOL(__frontswap_invalidate_area); static unsigned long __frontswap_curr_pages(void) { - int type; unsigned long totalpages = 0; struct swap_info_struct *si = NULL; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + plist_for_each_entry(si, &swap_active_head, list) totalpages += atomic_read(&si->frontswap_pages); - } return totalpages; } @@ -257,11 +344,9 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, int si_frontswap_pages; unsigned long total_pages_to_unuse = total; unsigned long pages = 0, pages_to_unuse = 0; - int type; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + plist_for_each_entry(si, &swap_active_head, list) { si_frontswap_pages = atomic_read(&si->frontswap_pages); if (total_pages_to_unuse < si_frontswap_pages) { pages = pages_to_unuse = total_pages_to_unuse; @@ -276,7 +361,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, } vm_unacct_memory(pages); *unused = pages_to_unuse; - *swapid = type; + *swapid = si->type; ret = 0; break; } @@ -323,7 +408,7 @@ void frontswap_shrink(unsigned long target_pages) /* * we don't want to hold swap_lock while doing a very * lengthy try_to_unuse, but swap_list may change - * so restart scan from swap_list.head each time + * so restart scan from swap_active_head each time */ spin_lock(&swap_lock); ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); diff --git a/mm/gup.c b/mm/gup.c new file mode 100644 index 00000000000..cc5a9e7adea --- /dev/null +++ b/mm/gup.c @@ -0,0 +1,662 @@ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/spinlock.h> + +#include <linux/hugetlb.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/rmap.h> +#include <linux/swap.h> +#include <linux/swapops.h> + +#include "internal.h" + +static struct page *no_page_table(struct vm_area_struct *vma, + unsigned int flags) +{ + /* + * When core dumping an enormous anonymous area that nobody + * has touched so far, we don't want to allocate unnecessary pages or + * page tables. Return error instead of NULL to skip handle_mm_fault, + * then get_dump_page() will return NULL to leave a hole in the dump. + * But we can only make this optimization where a hole would surely + * be zero-filled if handle_mm_fault() actually did handle it. + */ + if ((flags & FOLL_DUMP) && (!vma->vm_ops || !vma->vm_ops->fault)) + return ERR_PTR(-EFAULT); + return NULL; +} + +static struct page *follow_page_pte(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, unsigned int flags) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page; + spinlock_t *ptl; + pte_t *ptep, pte; + +retry: + if (unlikely(pmd_bad(*pmd))) + return no_page_table(vma, flags); + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + pte = *ptep; + if (!pte_present(pte)) { + swp_entry_t entry; + /* + * KSM's break_ksm() relies upon recognizing a ksm page + * even while it is being migrated, so for that case we + * need migration_entry_wait(). + */ + if (likely(!(flags & FOLL_MIGRATION))) + goto no_page; + if (pte_none(pte) || pte_file(pte)) + goto no_page; + entry = pte_to_swp_entry(pte); + if (!is_migration_entry(entry)) + goto no_page; + pte_unmap_unlock(ptep, ptl); + migration_entry_wait(mm, pmd, address); + goto retry; + } + if ((flags & FOLL_NUMA) && pte_numa(pte)) + goto no_page; + if ((flags & FOLL_WRITE) && !pte_write(pte)) { + pte_unmap_unlock(ptep, ptl); + return NULL; + } + + page = vm_normal_page(vma, address, pte); + if (unlikely(!page)) { + if ((flags & FOLL_DUMP) || + !is_zero_pfn(pte_pfn(pte))) + goto bad_page; + page = pte_page(pte); + } + + if (flags & FOLL_GET) + get_page_foll(page); + if (flags & FOLL_TOUCH) { + if ((flags & FOLL_WRITE) && + !pte_dirty(pte) && !PageDirty(page)) + set_page_dirty(page); + /* + * pte_mkyoung() would be more correct here, but atomic care + * is needed to avoid losing the dirty bit: it is easier to use + * mark_page_accessed(). + */ + mark_page_accessed(page); + } + if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { + /* + * The preliminary mapping check is mainly to avoid the + * pointless overhead of lock_page on the ZERO_PAGE + * which might bounce very badly if there is contention. + * + * If the page is already locked, we don't need to + * handle it now - vmscan will handle it later if and + * when it attempts to reclaim the page. + */ + if (page->mapping && trylock_page(page)) { + lru_add_drain(); /* push cached pages to LRU */ + /* + * Because we lock page here, and migration is + * blocked by the pte's page reference, and we + * know the page is still mapped, we don't even + * need to check for file-cache page truncation. + */ + mlock_vma_page(page); + unlock_page(page); + } + } + pte_unmap_unlock(ptep, ptl); + return page; +bad_page: + pte_unmap_unlock(ptep, ptl); + return ERR_PTR(-EFAULT); + +no_page: + pte_unmap_unlock(ptep, ptl); + if (!pte_none(pte)) + return NULL; + return no_page_table(vma, flags); +} + +/** + * follow_page_mask - look up a page descriptor from a user-virtual address + * @vma: vm_area_struct mapping @address + * @address: virtual address to look up + * @flags: flags modifying lookup behaviour + * @page_mask: on output, *page_mask is set according to the size of the page + * + * @flags can have FOLL_ flags set, defined in <linux/mm.h> + * + * Returns the mapped (struct page *), %NULL if no mapping exists, or + * an error pointer if there is a mapping to something not represented + * by a page descriptor (see also vm_normal_page()). + */ +struct page *follow_page_mask(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned int *page_mask) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + spinlock_t *ptl; + struct page *page; + struct mm_struct *mm = vma->vm_mm; + + *page_mask = 0; + + page = follow_huge_addr(mm, address, flags & FOLL_WRITE); + if (!IS_ERR(page)) { + BUG_ON(flags & FOLL_GET); + return page; + } + + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + return no_page_table(vma, flags); + + pud = pud_offset(pgd, address); + if (pud_none(*pud)) + return no_page_table(vma, flags); + if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { + if (flags & FOLL_GET) + return NULL; + page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); + return page; + } + if (unlikely(pud_bad(*pud))) + return no_page_table(vma, flags); + + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd)) + return no_page_table(vma, flags); + if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { + page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); + if (flags & FOLL_GET) { + /* + * Refcount on tail pages are not well-defined and + * shouldn't be taken. The caller should handle a NULL + * return when trying to follow tail pages. + */ + if (PageHead(page)) + get_page(page); + else + page = NULL; + } + return page; + } + if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + return no_page_table(vma, flags); + if (pmd_trans_huge(*pmd)) { + if (flags & FOLL_SPLIT) { + split_huge_page_pmd(vma, address, pmd); + return follow_page_pte(vma, address, pmd, flags); + } + ptl = pmd_lock(mm, pmd); + if (likely(pmd_trans_huge(*pmd))) { + if (unlikely(pmd_trans_splitting(*pmd))) { + spin_unlock(ptl); + wait_split_huge_page(vma->anon_vma, pmd); + } else { + page = follow_trans_huge_pmd(vma, address, + pmd, flags); + spin_unlock(ptl); + *page_mask = HPAGE_PMD_NR - 1; + return page; + } + } else + spin_unlock(ptl); + } + return follow_page_pte(vma, address, pmd, flags); +} + +static int get_gate_page(struct mm_struct *mm, unsigned long address, + unsigned int gup_flags, struct vm_area_struct **vma, + struct page **page) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int ret = -EFAULT; + + /* user gate pages are read-only */ + if (gup_flags & FOLL_WRITE) + return -EFAULT; + if (address > TASK_SIZE) + pgd = pgd_offset_k(address); + else + pgd = pgd_offset_gate(mm, address); + BUG_ON(pgd_none(*pgd)); + pud = pud_offset(pgd, address); + BUG_ON(pud_none(*pud)); + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd)) + return -EFAULT; + VM_BUG_ON(pmd_trans_huge(*pmd)); + pte = pte_offset_map(pmd, address); + if (pte_none(*pte)) + goto unmap; + *vma = get_gate_vma(mm); + if (!page) + goto out; + *page = vm_normal_page(*vma, address, *pte); + if (!*page) { + if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte))) + goto unmap; + *page = pte_page(*pte); + } + get_page(*page); +out: + ret = 0; +unmap: + pte_unmap(pte); + return ret; +} + +static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, + unsigned long address, unsigned int *flags, int *nonblocking) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned int fault_flags = 0; + int ret; + + /* For mlock, just skip the stack guard page. */ + if ((*flags & FOLL_MLOCK) && + (stack_guard_page_start(vma, address) || + stack_guard_page_end(vma, address + PAGE_SIZE))) + return -ENOENT; + if (*flags & FOLL_WRITE) + fault_flags |= FAULT_FLAG_WRITE; + if (nonblocking) + fault_flags |= FAULT_FLAG_ALLOW_RETRY; + if (*flags & FOLL_NOWAIT) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; + + ret = handle_mm_fault(mm, vma, address, fault_flags); + if (ret & VM_FAULT_ERROR) { + if (ret & VM_FAULT_OOM) + return -ENOMEM; + if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) + return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT; + if (ret & VM_FAULT_SIGBUS) + return -EFAULT; + BUG(); + } + + if (tsk) { + if (ret & VM_FAULT_MAJOR) + tsk->maj_flt++; + else + tsk->min_flt++; + } + + if (ret & VM_FAULT_RETRY) { + if (nonblocking) + *nonblocking = 0; + return -EBUSY; + } + + /* + * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when + * necessary, even if maybe_mkwrite decided not to set pte_write. We + * can thus safely do subsequent page lookups as if they were reads. + * But only do so when looping for pte_write is futile: in some cases + * userspace may also be wanting to write to the gotten user page, + * which a read fault here might prevent (a readonly page might get + * reCOWed by userspace write). + */ + if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) + *flags &= ~FOLL_WRITE; + return 0; +} + +static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) +{ + vm_flags_t vm_flags = vma->vm_flags; + + if (vm_flags & (VM_IO | VM_PFNMAP)) + return -EFAULT; + + if (gup_flags & FOLL_WRITE) { + if (!(vm_flags & VM_WRITE)) { + if (!(gup_flags & FOLL_FORCE)) + return -EFAULT; + /* + * We used to let the write,force case do COW in a + * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could + * set a breakpoint in a read-only mapping of an + * executable, without corrupting the file (yet only + * when that file had been opened for writing!). + * Anon pages in shared mappings are surprising: now + * just reject it. + */ + if (!is_cow_mapping(vm_flags)) { + WARN_ON_ONCE(vm_flags & VM_MAYWRITE); + return -EFAULT; + } + } + } else if (!(vm_flags & VM_READ)) { + if (!(gup_flags & FOLL_FORCE)) + return -EFAULT; + /* + * Is there actually any vma we can reach here which does not + * have VM_MAYREAD set? + */ + if (!(vm_flags & VM_MAYREAD)) + return -EFAULT; + } + return 0; +} + +/** + * __get_user_pages() - pin user pages in memory + * @tsk: task_struct of target task + * @mm: mm_struct of target mm + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying pin behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * @nonblocking: whether waiting for disk IO or mmap_sem contention + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. vmas will only + * remain valid while mmap_sem is held. + * + * Must be called with mmap_sem held for read or write. + * + * __get_user_pages walks a process's page tables and takes a reference to + * each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * __get_user_pages returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If + * the page is written to, set_page_dirty (or set_page_dirty_lock, as + * appropriate) must be called after the page is finished with, and + * before put_page is called. + * + * If @nonblocking != NULL, __get_user_pages will not wait for disk IO + * or mmap_sem contention, and if waiting is needed to pin all pages, + * *@nonblocking will be set to 0. + * + * In most cases, get_user_pages or get_user_pages_fast should be used + * instead of __get_user_pages. __get_user_pages should be used only if + * you need some special @gup_flags. + */ +long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *nonblocking) +{ + long i = 0; + unsigned int page_mask; + struct vm_area_struct *vma = NULL; + + if (!nr_pages) + return 0; + + VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); + + /* + * If FOLL_FORCE is set then do not force a full fault as the hinting + * fault information is unrelated to the reference behaviour of a task + * using the address space + */ + if (!(gup_flags & FOLL_FORCE)) + gup_flags |= FOLL_NUMA; + + do { + struct page *page; + unsigned int foll_flags = gup_flags; + unsigned int page_increm; + + /* first iteration or cross vma bound */ + if (!vma || start >= vma->vm_end) { + vma = find_extend_vma(mm, start); + if (!vma && in_gate_area(mm, start)) { + int ret; + ret = get_gate_page(mm, start & PAGE_MASK, + gup_flags, &vma, + pages ? &pages[i] : NULL); + if (ret) + return i ? : ret; + page_mask = 0; + goto next_page; + } + + if (!vma || check_vma_flags(vma, gup_flags)) + return i ? : -EFAULT; + if (is_vm_hugetlb_page(vma)) { + i = follow_hugetlb_page(mm, vma, pages, vmas, + &start, &nr_pages, i, + gup_flags); + continue; + } + } +retry: + /* + * If we have a pending SIGKILL, don't keep faulting pages and + * potentially allocating memory. + */ + if (unlikely(fatal_signal_pending(current))) + return i ? i : -ERESTARTSYS; + cond_resched(); + page = follow_page_mask(vma, start, foll_flags, &page_mask); + if (!page) { + int ret; + ret = faultin_page(tsk, vma, start, &foll_flags, + nonblocking); + switch (ret) { + case 0: + goto retry; + case -EFAULT: + case -ENOMEM: + case -EHWPOISON: + return i ? i : ret; + case -EBUSY: + return i; + case -ENOENT: + goto next_page; + } + BUG(); + } + if (IS_ERR(page)) + return i ? i : PTR_ERR(page); + if (pages) { + pages[i] = page; + flush_anon_page(vma, page, start); + flush_dcache_page(page); + page_mask = 0; + } +next_page: + if (vmas) { + vmas[i] = vma; + page_mask = 0; + } + page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask); + if (page_increm > nr_pages) + page_increm = nr_pages; + i += page_increm; + start += page_increm * PAGE_SIZE; + nr_pages -= page_increm; + } while (nr_pages); + return i; +} +EXPORT_SYMBOL(__get_user_pages); + +/* + * fixup_user_fault() - manually resolve a user page fault + * @tsk: the task_struct to use for page fault accounting, or + * NULL if faults are not to be recorded. + * @mm: mm_struct of target mm + * @address: user address + * @fault_flags:flags to pass down to handle_mm_fault() + * + * This is meant to be called in the specific scenario where for locking reasons + * we try to access user memory in atomic context (within a pagefault_disable() + * section), this returns -EFAULT, and we want to resolve the user fault before + * trying again. + * + * Typically this is meant to be used by the futex code. + * + * The main difference with get_user_pages() is that this function will + * unconditionally call handle_mm_fault() which will in turn perform all the + * necessary SW fixup of the dirty and young bits in the PTE, while + * handle_mm_fault() only guarantees to update these in the struct page. + * + * This is important for some architectures where those bits also gate the + * access permission to the page because they are maintained in software. On + * such architectures, gup() will not be enough to make a subsequent access + * succeed. + * + * This should be called with the mm_sem held for read. + */ +int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, + unsigned long address, unsigned int fault_flags) +{ + struct vm_area_struct *vma; + vm_flags_t vm_flags; + int ret; + + vma = find_extend_vma(mm, address); + if (!vma || address < vma->vm_start) + return -EFAULT; + + vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ; + if (!(vm_flags & vma->vm_flags)) + return -EFAULT; + + ret = handle_mm_fault(mm, vma, address, fault_flags); + if (ret & VM_FAULT_ERROR) { + if (ret & VM_FAULT_OOM) + return -ENOMEM; + if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) + return -EHWPOISON; + if (ret & VM_FAULT_SIGBUS) + return -EFAULT; + BUG(); + } + if (tsk) { + if (ret & VM_FAULT_MAJOR) + tsk->maj_flt++; + else + tsk->min_flt++; + } + return 0; +} + +/* + * get_user_pages() - pin user pages in memory + * @tsk: the task_struct to use for page fault accounting, or + * NULL if faults are not to be recorded. + * @mm: mm_struct of target mm + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @write: whether pages will be written to by the caller + * @force: whether to force access even when user mapping is currently + * protected (but never forces write access to shared mapping). + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. vmas will only + * remain valid while mmap_sem is held. + * + * Must be called with mmap_sem held for read or write. + * + * get_user_pages walks a process's page tables and takes a reference to + * each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * get_user_pages returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If write=0, the page must not be written to. If the page is written to, + * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called + * after the page is finished with, and before put_page is called. + * + * get_user_pages is typically used for fewer-copy IO operations, to get a + * handle on the memory by some means other than accesses via the user virtual + * addresses. The pages may be submitted for DMA to devices or accessed via + * their kernel linear mapping (via the kmap APIs). Care should be taken to + * use the correct cache flushing APIs. + * + * See also get_user_pages_fast, for performance critical applications. + */ +long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, int write, + int force, struct page **pages, struct vm_area_struct **vmas) +{ + int flags = FOLL_TOUCH; + + if (pages) + flags |= FOLL_GET; + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, + NULL); +} +EXPORT_SYMBOL(get_user_pages); + +/** + * get_dump_page() - pin user page in memory while writing it to core dump + * @addr: user address + * + * Returns struct page pointer of user page pinned for dump, + * to be freed afterwards by page_cache_release() or put_page(). + * + * Returns NULL on any kind of failure - a hole must then be inserted into + * the corefile, to preserve alignment with its headers; and also returns + * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - + * allowing a hole to be left in the corefile to save diskspace. + * + * Called without mmap_sem, but after all other threads have been killed. + */ +#ifdef CONFIG_ELF_CORE +struct page *get_dump_page(unsigned long addr) +{ + struct vm_area_struct *vma; + struct page *page; + + if (__get_user_pages(current, current->mm, addr, 1, + FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, + NULL) < 1) + return NULL; + flush_cache_page(vma, addr, page_to_pfn(page)); + return page; +} +#endif /* CONFIG_ELF_CORE */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6001ee6347a..33514d88fef 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -5,6 +5,8 @@ * the COPYING file in the top-level directory. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/sched.h> #include <linux/highmem.h> @@ -20,17 +22,19 @@ #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/migrate.h> +#include <linux/hashtable.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" /* - * By default transparent hugepage support is enabled for all mappings - * and khugepaged scans all mappings. Defrag is only invoked by - * khugepaged hugepage allocations and by page faults inside - * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived - * allocations. + * By default transparent hugepage support is disabled in order that avoid + * to risk increase the memory footprint of applications without a guaranteed + * benefit. When transparent hugepage support is enabled, is for all mappings, + * and khugepaged scans all mappings. + * Defrag is invoked by khugepaged hugepage allocations and by page faults + * for all hugepage allocations. */ unsigned long transparent_hugepage_flags __read_mostly = #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS @@ -62,12 +66,11 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1; static int khugepaged(void *none); -static int mm_slots_hash_init(void); static int khugepaged_slab_init(void); -static void khugepaged_slab_free(void); -#define MM_SLOTS_HASH_HEADS 1024 -static struct hlist_head *mm_slots_hash __read_mostly; +#define MM_SLOTS_HASH_BITS 10 +static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); + static struct kmem_cache *mm_slot_cache __read_mostly; /** @@ -105,7 +108,6 @@ static int set_recommended_min_free_kbytes(void) struct zone *zone; int nr_zones = 0; unsigned long recommended_min; - extern int min_free_kbytes; if (!khugepaged_enabled()) return 0; @@ -130,8 +132,14 @@ static int set_recommended_min_free_kbytes(void) (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); - if (recommended_min > min_free_kbytes) + if (recommended_min > min_free_kbytes) { + if (user_min_free_kbytes >= 0) + pr_info("raising min_free_kbytes from %d to %lu " + "to help transparent hugepage allocations\n", + min_free_kbytes, recommended_min); + min_free_kbytes = recommended_min; + } setup_per_zone_wmarks(); return 0; } @@ -145,8 +153,7 @@ static int start_khugepaged(void) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (unlikely(IS_ERR(khugepaged_thread))) { - printk(KERN_ERR - "khugepaged: kthread_run(khugepaged) failed\n"); + pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; } @@ -164,35 +171,34 @@ static int start_khugepaged(void) } static atomic_t huge_zero_refcount; -static unsigned long huge_zero_pfn __read_mostly; +static struct page *huge_zero_page __read_mostly; -static inline bool is_huge_zero_pfn(unsigned long pfn) +static inline bool is_huge_zero_page(struct page *page) { - unsigned long zero_pfn = ACCESS_ONCE(huge_zero_pfn); - return zero_pfn && pfn == zero_pfn; + return ACCESS_ONCE(huge_zero_page) == page; } static inline bool is_huge_zero_pmd(pmd_t pmd) { - return is_huge_zero_pfn(pmd_pfn(pmd)); + return is_huge_zero_page(pmd_page(pmd)); } -static unsigned long get_huge_zero_page(void) +static struct page *get_huge_zero_page(void) { struct page *zero_page; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) - return ACCESS_ONCE(huge_zero_pfn); + return ACCESS_ONCE(huge_zero_page); zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); if (!zero_page) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); - return 0; + return NULL; } count_vm_event(THP_ZERO_PAGE_ALLOC); preempt_disable(); - if (cmpxchg(&huge_zero_pfn, 0, page_to_pfn(zero_page))) { + if (cmpxchg(&huge_zero_page, NULL, zero_page)) { preempt_enable(); __free_page(zero_page); goto retry; @@ -201,7 +207,7 @@ retry: /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); preempt_enable(); - return ACCESS_ONCE(huge_zero_pfn); + return ACCESS_ONCE(huge_zero_page); } static void put_huge_zero_page(void) @@ -213,24 +219,29 @@ static void put_huge_zero_page(void) BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } -static int shrink_huge_zero_page(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, + struct shrink_control *sc) { - if (!sc->nr_to_scan) - /* we can free zero page only if last reference remains */ - return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; + /* we can free zero page only if last reference remains */ + return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; +} +static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { - unsigned long zero_pfn = xchg(&huge_zero_pfn, 0); - BUG_ON(zero_pfn == 0); - __free_page(__pfn_to_page(zero_pfn)); + struct page *zero_page = xchg(&huge_zero_page, NULL); + BUG_ON(zero_page == NULL); + __free_page(zero_page); + return HPAGE_PMD_NR; } return 0; } static struct shrinker huge_zero_page_shrinker = { - .shrink = shrink_huge_zero_page, + .count_objects = shrink_huge_zero_page_count, + .scan_objects = shrink_huge_zero_page_scan, .seeks = DEFAULT_SEEKS, }; @@ -419,7 +430,7 @@ static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, unsigned long msecs; int err; - err = strict_strtoul(buf, 10, &msecs); + err = kstrtoul(buf, 10, &msecs); if (err || msecs > UINT_MAX) return -EINVAL; @@ -446,7 +457,7 @@ static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, unsigned long msecs; int err; - err = strict_strtoul(buf, 10, &msecs); + err = kstrtoul(buf, 10, &msecs); if (err || msecs > UINT_MAX) return -EINVAL; @@ -472,7 +483,7 @@ static ssize_t pages_to_scan_store(struct kobject *kobj, int err; unsigned long pages; - err = strict_strtoul(buf, 10, &pages); + err = kstrtoul(buf, 10, &pages); if (err || !pages || pages > UINT_MAX) return -EINVAL; @@ -540,7 +551,7 @@ static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, int err; unsigned long max_ptes_none; - err = strict_strtoul(buf, 10, &max_ptes_none); + err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR-1) return -EINVAL; @@ -574,19 +585,19 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) *hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); if (unlikely(!*hugepage_kobj)) { - printk(KERN_ERR "hugepage: failed to create transparent hugepage kobject\n"); + pr_err("failed to create transparent hugepage kobject\n"); return -ENOMEM; } err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group); if (err) { - printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n"); + pr_err("failed to register transparent hugepage group\n"); goto delete_obj; } err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group); if (err) { - printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n"); + pr_err("failed to register transparent hugepage group\n"); goto remove_hp_group; } @@ -634,12 +645,6 @@ static int __init hugepage_init(void) if (err) goto out; - err = mm_slots_hash_init(); - if (err) { - khugepaged_slab_free(); - goto out; - } - register_shrinker(&huge_zero_page_shrinker); /* @@ -657,7 +662,7 @@ out: hugepage_exit_sysfs(hugepage_kobj); return err; } -module_init(hugepage_init) +subsys_initcall(hugepage_init); static int __init setup_transparent_hugepage(char *str) { @@ -685,8 +690,7 @@ static int __init setup_transparent_hugepage(char *str) } out: if (!ret) - printk(KERN_WARNING - "transparent_hugepage= cannot parse, ignored\n"); + pr_warn("transparent_hugepage= cannot parse, ignored\n"); return ret; } __setup("transparent_hugepage=", setup_transparent_hugepage); @@ -698,11 +702,10 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) return pmd; } -static inline pmd_t mk_huge_pmd(struct page *page, struct vm_area_struct *vma) +static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot) { pmd_t entry; - entry = mk_pmd(page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + entry = mk_pmd(page, prot); entry = pmd_mkhuge(entry); return entry; } @@ -713,36 +716,37 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, struct page *page) { pgtable_t pgtable; + spinlock_t *ptl; - VM_BUG_ON(!PageCompound(page)); + VM_BUG_ON_PAGE(!PageCompound(page), page); pgtable = pte_alloc_one(mm, haddr); if (unlikely(!pgtable)) return VM_FAULT_OOM; clear_huge_page(page, haddr, HPAGE_PMD_NR); + /* + * The memory barrier inside __SetPageUptodate makes sure that + * clear_huge_page writes become visible before the set_pmd_at() + * write. + */ __SetPageUptodate(page); - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_none(*pmd))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mem_cgroup_uncharge_page(page); put_page(page); pte_free(mm, pgtable); } else { pmd_t entry; - entry = mk_huge_pmd(page, vma); - /* - * The spinlocking to take the lru_lock inside - * page_add_new_anon_rmap() acts as a full memory - * barrier to be sure clear_huge_page writes become - * visible after the set_pmd_at() write. - */ + entry = mk_huge_pmd(page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr); + pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); - pgtable_trans_huge_deposit(mm, pgtable); add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); - mm->nr_ptes++; - spin_unlock(&mm->page_table_lock); + atomic_long_inc(&mm->nr_ptes); + spin_unlock(ptl); } return 0; @@ -762,27 +766,20 @@ static inline struct page *alloc_hugepage_vma(int defrag, HPAGE_PMD_ORDER, vma, haddr, nd); } -#ifndef CONFIG_NUMA -static inline struct page *alloc_hugepage(int defrag) -{ - return alloc_pages(alloc_hugepage_gfpmask(defrag, 0), - HPAGE_PMD_ORDER); -} -#endif - +/* Caller must hold page table lock. */ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, - unsigned long zero_pfn) + struct page *zero_page) { pmd_t entry; if (!pmd_none(*pmd)) return false; - entry = pfn_pmd(zero_pfn, vma->vm_page_prot); + entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_wrprotect(entry); entry = pmd_mkhuge(entry); + pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); - pgtable_trans_huge_deposit(mm, pgtable); - mm->nr_ptes++; + atomic_long_inc(&mm->nr_ptes); return true; } @@ -792,83 +789,65 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct page *page; unsigned long haddr = address & HPAGE_PMD_MASK; - pte_t *pte; - if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) { - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; - if (unlikely(khugepaged_enter(vma))) + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return VM_FAULT_FALLBACK; + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + if (unlikely(khugepaged_enter(vma))) + return VM_FAULT_OOM; + if (!(flags & FAULT_FLAG_WRITE) && + transparent_hugepage_use_zero_page()) { + spinlock_t *ptl; + pgtable_t pgtable; + struct page *zero_page; + bool set; + pgtable = pte_alloc_one(mm, haddr); + if (unlikely(!pgtable)) return VM_FAULT_OOM; - if (!(flags & FAULT_FLAG_WRITE) && - transparent_hugepage_use_zero_page()) { - pgtable_t pgtable; - unsigned long zero_pfn; - bool set; - pgtable = pte_alloc_one(mm, haddr); - if (unlikely(!pgtable)) - return VM_FAULT_OOM; - zero_pfn = get_huge_zero_page(); - if (unlikely(!zero_pfn)) { - pte_free(mm, pgtable); - count_vm_event(THP_FAULT_FALLBACK); - goto out; - } - spin_lock(&mm->page_table_lock); - set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd, - zero_pfn); - spin_unlock(&mm->page_table_lock); - if (!set) { - pte_free(mm, pgtable); - put_huge_zero_page(); - } - return 0; - } - page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); - if (unlikely(!page)) { + zero_page = get_huge_zero_page(); + if (unlikely(!zero_page)) { + pte_free(mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); - goto out; + return VM_FAULT_FALLBACK; } - count_vm_event(THP_FAULT_ALLOC); - if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { - put_page(page); - goto out; - } - if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, - page))) { - mem_cgroup_uncharge_page(page); - put_page(page); - goto out; + ptl = pmd_lock(mm, pmd); + set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd, + zero_page); + spin_unlock(ptl); + if (!set) { + pte_free(mm, pgtable); + put_huge_zero_page(); } - return 0; } -out: - /* - * Use __pte_alloc instead of pte_alloc_map, because we can't - * run pte_offset_map on the pmd, if an huge pmd could - * materialize from under us from a different thread. - */ - if (unlikely(pmd_none(*pmd)) && - unlikely(__pte_alloc(mm, vma, pmd, address))) - return VM_FAULT_OOM; - /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd))) - return 0; - /* - * A regular pmd is established and it can't morph into a huge pmd - * from under us anymore at this point because we hold the mmap_sem - * read mode and khugepaged takes it in write mode. So now it's - * safe to run pte_offset_map(). - */ - pte = pte_offset_map(pmd, address); - return handle_pte_fault(mm, vma, address, pte, pmd, flags); + page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), + vma, haddr, numa_node_id(), 0); + if (unlikely(!page)) { + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + if (unlikely(mem_cgroup_charge_anon(page, mm, GFP_KERNEL))) { + put_page(page); + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) { + mem_cgroup_uncharge_page(page); + put_page(page); + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + + count_vm_event(THP_FAULT_ALLOC); + return 0; } int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma) { + spinlock_t *dst_ptl, *src_ptl; struct page *src_page; pmd_t pmd; pgtable_t pgtable; @@ -879,8 +858,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (unlikely(!pgtable)) goto out; - spin_lock(&dst_mm->page_table_lock); - spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING); + dst_ptl = pmd_lock(dst_mm, dst_pmd); + src_ptl = pmd_lockptr(src_mm, src_pmd); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); ret = -EAGAIN; pmd = *src_pmd; @@ -889,50 +869,51 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } /* - * mm->page_table_lock is enough to be sure that huge zero pmd is not + * When page table lock is held, the huge zero pmd should not be * under splitting since we don't split the page itself, only pmd to * a page table. */ if (is_huge_zero_pmd(pmd)) { - unsigned long zero_pfn; + struct page *zero_page; bool set; /* * get_huge_zero_page() will never allocate a new page here, * since we already have a zero page to copy. It just takes a * reference. */ - zero_pfn = get_huge_zero_page(); + zero_page = get_huge_zero_page(); set = set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd, - zero_pfn); + zero_page); BUG_ON(!set); /* unexpected !pmd_none(dst_pmd) */ ret = 0; goto out_unlock; } + if (unlikely(pmd_trans_splitting(pmd))) { /* split huge page running from under us */ - spin_unlock(&src_mm->page_table_lock); - spin_unlock(&dst_mm->page_table_lock); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); pte_free(dst_mm, pgtable); wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */ goto out; } src_page = pmd_page(pmd); - VM_BUG_ON(!PageHead(src_page)); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); get_page(src_page); page_dup_rmap(src_page); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); pmdp_set_wrprotect(src_mm, addr, src_pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); set_pmd_at(dst_mm, addr, dst_pmd, pmd); - pgtable_trans_huge_deposit(dst_mm, pgtable); - dst_mm->nr_ptes++; + atomic_long_inc(&dst_mm->nr_ptes); ret = 0; out_unlock: - spin_unlock(&src_mm->page_table_lock); - spin_unlock(&dst_mm->page_table_lock); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); out: return ret; } @@ -943,10 +924,11 @@ void huge_pmd_set_accessed(struct mm_struct *mm, pmd_t *pmd, pmd_t orig_pmd, int dirty) { + spinlock_t *ptl; pmd_t entry; unsigned long haddr; - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, orig_pmd))) goto unlock; @@ -956,81 +938,38 @@ void huge_pmd_set_accessed(struct mm_struct *mm, update_mmu_cache_pmd(vma, address, pmd); unlock: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); } -static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd, pmd_t orig_pmd, unsigned long haddr) +/* + * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages + * during copy_user_huge_page()'s copy_page_rep(): in the case when + * the source page gets split and a tail freed before copy completes. + * Called under pmd_lock of checked pmd, so safe from splitting itself. + */ +static void get_user_huge_page(struct page *page) { - pgtable_t pgtable; - pmd_t _pmd; - struct page *page; - int i, ret = 0; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - - page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (!page) { - ret |= VM_FAULT_OOM; - goto out; - } + if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) { + struct page *endpage = page + HPAGE_PMD_NR; - if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) { - put_page(page); - ret |= VM_FAULT_OOM; - goto out; + atomic_add(HPAGE_PMD_NR, &page->_count); + while (++page < endpage) + get_huge_page_tail(page); + } else { + get_page(page); } +} - clear_user_highpage(page, address); - __SetPageUptodate(page); - - mmun_start = haddr; - mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(*pmd, orig_pmd))) - goto out_free_page; - - pmdp_clear_flush(vma, haddr, pmd); - /* leave pmd empty until pte is filled */ - - pgtable = pgtable_trans_huge_withdraw(mm); - pmd_populate(mm, &_pmd, pgtable); +static void put_user_huge_page(struct page *page) +{ + if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) { + struct page *endpage = page + HPAGE_PMD_NR; - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { - pte_t *pte, entry; - if (haddr == (address & PAGE_MASK)) { - entry = mk_pte(page, vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr); - } else { - entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); - entry = pte_mkspecial(entry); - } - pte = pte_offset_map(&_pmd, haddr); - VM_BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); - pte_unmap(pte); + while (page < endpage) + put_page(page++); + } else { + put_page(page); } - smp_wmb(); /* make pte visible before pmd */ - pmd_populate(mm, pmd, pgtable); - spin_unlock(&mm->page_table_lock); - put_huge_zero_page(); - inc_mm_counter(mm, MM_ANONPAGES); - - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - - ret |= VM_FAULT_WRITE; -out: - return ret; -out_free_page: - spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - mem_cgroup_uncharge_page(page); - put_page(page); - goto out; } static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, @@ -1040,6 +979,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, struct page *page, unsigned long haddr) { + spinlock_t *ptl; pgtable_t pgtable; pmd_t _pmd; int ret = 0, i; @@ -1059,7 +999,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, __GFP_OTHER_NODE, vma, address, page_to_nid(page)); if (unlikely(!pages[i] || - mem_cgroup_newpage_charge(pages[i], mm, + mem_cgroup_charge_anon(pages[i], mm, GFP_KERNEL))) { if (pages[i]) put_page(pages[i]); @@ -1086,15 +1026,15 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, mmun_end = haddr + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, orig_pmd))) goto out_free_pages; - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); pmdp_clear_flush(vma, haddr, pmd); /* leave pmd empty until pte is filled */ - pgtable = pgtable_trans_huge_withdraw(mm); + pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { @@ -1112,7 +1052,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); page_remove_rmap(page); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); @@ -1123,7 +1063,7 @@ out: return ret; out_free_pages: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); mem_cgroup_uncharge_start(); for (i = 0; i < HPAGE_PMD_NR; i++) { @@ -1138,22 +1078,24 @@ out_free_pages: int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, pmd_t orig_pmd) { + spinlock_t *ptl; int ret = 0; struct page *page = NULL, *new_page; unsigned long haddr; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ + ptl = pmd_lockptr(mm, pmd); VM_BUG_ON(!vma->anon_vma); haddr = address & HPAGE_PMD_MASK; if (is_huge_zero_pmd(orig_pmd)) goto alloc; - spin_lock(&mm->page_table_lock); + spin_lock(ptl); if (unlikely(!pmd_same(*pmd, orig_pmd))) goto out_unlock; page = pmd_page(orig_pmd); - VM_BUG_ON(!PageCompound(page) || !PageHead(page)); + VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page); if (page_mapcount(page) == 1) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); @@ -1163,8 +1105,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, ret |= VM_FAULT_WRITE; goto out_unlock; } - get_page(page); - spin_unlock(&mm->page_table_lock); + get_user_huge_page(page); + spin_unlock(ptl); alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) @@ -1174,32 +1116,37 @@ alloc: new_page = NULL; if (unlikely(!new_page)) { - count_vm_event(THP_FAULT_FALLBACK); - if (is_huge_zero_pmd(orig_pmd)) { - ret = do_huge_pmd_wp_zero_page_fallback(mm, vma, - address, pmd, orig_pmd, haddr); + if (!page) { + split_huge_page_pmd(vma, address, pmd); + ret |= VM_FAULT_FALLBACK; } else { ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); - if (ret & VM_FAULT_OOM) + if (ret & VM_FAULT_OOM) { split_huge_page(page); - put_page(page); + ret |= VM_FAULT_FALLBACK; + } + put_user_huge_page(page); } + count_vm_event(THP_FAULT_FALLBACK); goto out; } - count_vm_event(THP_FAULT_ALLOC); - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { + if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) { put_page(new_page); if (page) { split_huge_page(page); - put_page(page); - } - ret |= VM_FAULT_OOM; + put_user_huge_page(page); + } else + split_huge_page_pmd(vma, address, pmd); + ret |= VM_FAULT_FALLBACK; + count_vm_event(THP_FAULT_FALLBACK); goto out; } - if (is_huge_zero_pmd(orig_pmd)) + count_vm_event(THP_FAULT_ALLOC); + + if (!page) clear_huge_page(new_page, haddr, HPAGE_PMD_NR); else copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR); @@ -1209,38 +1156,39 @@ alloc: mmun_end = haddr + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); + spin_lock(ptl); if (page) - put_page(page); + put_user_huge_page(page); if (unlikely(!pmd_same(*pmd, orig_pmd))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mem_cgroup_uncharge_page(new_page); put_page(new_page); goto out_mn; } else { pmd_t entry; - entry = mk_huge_pmd(new_page, vma); + entry = mk_huge_pmd(new_page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); pmdp_clear_flush(vma, haddr, pmd); page_add_new_anon_rmap(new_page, vma, haddr); set_pmd_at(mm, haddr, pmd, entry); update_mmu_cache_pmd(vma, address, pmd); - if (is_huge_zero_pmd(orig_pmd)) { + if (!page) { add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); put_huge_zero_page(); } else { - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); page_remove_rmap(page); put_page(page); } ret |= VM_FAULT_WRITE; } - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); out_mn: mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); out: return ret; out_unlock: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); return ret; } @@ -1252,13 +1200,21 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; struct page *page = NULL; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmd)); if (flags & FOLL_WRITE && !pmd_write(*pmd)) goto out; + /* Avoid dumping huge zero page */ + if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) + return ERR_PTR(-EFAULT); + + /* Full NUMA hinting faults to serialise migration in fault paths */ + if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + goto out; + page = pmd_page(*pmd); - VM_BUG_ON(!PageHead(page)); + VM_BUG_ON_PAGE(!PageHead(page), page); if (flags & FOLL_TOUCH) { pmd_t _pmd; /* @@ -1270,7 +1226,9 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, * young bit, instead of the current set_pmd_at. */ _pmd = pmd_mkyoung(pmd_mkdirty(*pmd)); - set_pmd_at(mm, addr & HPAGE_PMD_MASK, pmd, _pmd); + if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, + pmd, _pmd, 1)) + update_mmu_cache_pmd(vma, addr, pmd); } if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { if (page->mapping && trylock_page(page)) { @@ -1281,7 +1239,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, } } page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; - VM_BUG_ON(!PageCompound(page)); + VM_BUG_ON_PAGE(!PageCompound(page), page); if (flags & FOLL_GET) get_page_foll(page); @@ -1293,101 +1251,157 @@ out: int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp) { + spinlock_t *ptl; + struct anon_vma *anon_vma = NULL; struct page *page; unsigned long haddr = addr & HPAGE_PMD_MASK; - int target_nid; - int current_nid = -1; - bool migrated; - bool page_locked = false; + int page_nid = -1, this_nid = numa_node_id(); + int target_nid, last_cpupid = -1; + bool page_locked; + bool migrated = false; + int flags = 0; - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmdp); if (unlikely(!pmd_same(pmd, *pmdp))) goto out_unlock; + /* + * If there are potential migrations, wait for completion and retry + * without disrupting NUMA hinting information. Do not relock and + * check_same as the page may no longer be mapped. + */ + if (unlikely(pmd_trans_migrating(*pmdp))) { + spin_unlock(ptl); + wait_migrate_huge_page(vma->anon_vma, pmdp); + goto out; + } + page = pmd_page(pmd); - get_page(page); - current_nid = page_to_nid(page); + BUG_ON(is_huge_zero_page(page)); + page_nid = page_to_nid(page); + last_cpupid = page_cpupid_last(page); count_vm_numa_event(NUMA_HINT_FAULTS); - if (current_nid == numa_node_id()) + if (page_nid == this_nid) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + flags |= TNF_FAULT_LOCAL; + } + /* + * Avoid grouping on DSO/COW pages in specific and RO pages + * in general, RO pages shouldn't hurt as much anyway since + * they can be in shared cache state. + */ + if (!pmd_write(pmd)) + flags |= TNF_NO_GROUP; + + /* + * Acquire the page lock to serialise THP migrations but avoid dropping + * page_table_lock if at all possible + */ + page_locked = trylock_page(page); target_nid = mpol_misplaced(page, vma, haddr); if (target_nid == -1) { - put_page(page); - goto clear_pmdnuma; + /* If the page was locked, there are no parallel migrations */ + if (page_locked) + goto clear_pmdnuma; } - /* Acquire the page lock to serialise THP migrations */ - spin_unlock(&mm->page_table_lock); - lock_page(page); - page_locked = true; + /* Migration could have started since the pmd_trans_migrating check */ + if (!page_locked) { + spin_unlock(ptl); + wait_on_page_locked(page); + page_nid = -1; + goto out; + } + + /* + * Page is misplaced. Page lock serialises migrations. Acquire anon_vma + * to serialises splits + */ + get_page(page); + spin_unlock(ptl); + anon_vma = page_lock_anon_vma_read(page); - /* Confirm the PTE did not while locked */ - spin_lock(&mm->page_table_lock); + /* Confirm the PMD did not change while page_table_lock was released */ + spin_lock(ptl); if (unlikely(!pmd_same(pmd, *pmdp))) { unlock_page(page); put_page(page); + page_nid = -1; goto out_unlock; } - spin_unlock(&mm->page_table_lock); - /* Migrate the THP to the requested node */ - migrated = migrate_misplaced_transhuge_page(mm, vma, - pmdp, pmd, addr, - page, target_nid); - if (migrated) - current_nid = target_nid; - else { - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(pmd, *pmdp))) { - unlock_page(page); - goto out_unlock; - } + /* Bail if we fail to protect against THP splits for any reason */ + if (unlikely(!anon_vma)) { + put_page(page); + page_nid = -1; goto clear_pmdnuma; } - task_numa_fault(current_nid, HPAGE_PMD_NR, migrated); - return 0; + /* + * Migrate the THP to the requested node, returns with page unlocked + * and pmd_numa cleared. + */ + spin_unlock(ptl); + migrated = migrate_misplaced_transhuge_page(mm, vma, + pmdp, pmd, addr, page, target_nid); + if (migrated) { + flags |= TNF_MIGRATED; + page_nid = target_nid; + } + goto out; clear_pmdnuma: + BUG_ON(!PageLocked(page)); pmd = pmd_mknonnuma(pmd); set_pmd_at(mm, haddr, pmdp, pmd); VM_BUG_ON(pmd_numa(*pmdp)); update_mmu_cache_pmd(vma, addr, pmdp); - if (page_locked) - unlock_page(page); - + unlock_page(page); out_unlock: - spin_unlock(&mm->page_table_lock); - if (current_nid != -1) - task_numa_fault(current_nid, HPAGE_PMD_NR, migrated); + spin_unlock(ptl); + +out: + if (anon_vma) + page_unlock_anon_vma_read(anon_vma); + + if (page_nid != -1) + task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); + return 0; } int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr) { + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { struct page *page; pgtable_t pgtable; pmd_t orig_pmd; - pgtable = pgtable_trans_huge_withdraw(tlb->mm); + /* + * For architectures like ppc64 we look at deposited pgtable + * when calling pmdp_get_and_clear. So do the + * pgtable_trans_huge_withdraw after finishing pmdp related + * operations. + */ orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); if (is_huge_zero_pmd(orig_pmd)) { - tlb->mm->nr_ptes--; - spin_unlock(&tlb->mm->page_table_lock); + atomic_long_dec(&tlb->mm->nr_ptes); + spin_unlock(ptl); put_huge_zero_page(); } else { page = pmd_page(orig_pmd); page_remove_rmap(page); - VM_BUG_ON(page_mapcount(page) < 0); + VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); - VM_BUG_ON(!PageHead(page)); - tlb->mm->nr_ptes--; - spin_unlock(&tlb->mm->page_table_lock); + VM_BUG_ON_PAGE(!PageHead(page), page); + atomic_long_dec(&tlb->mm->nr_ptes); + spin_unlock(ptl); tlb_remove_page(tlb, page); } pte_free(tlb->mm, pgtable); @@ -1400,14 +1414,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec) { + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { /* * All logical pages in the range are present * if backed by a huge page. */ - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); memset(vec, 1, (end - addr) >> PAGE_SHIFT); ret = 1; } @@ -1420,6 +1435,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd) { + spinlock_t *old_ptl, *new_ptl; int ret = 0; pmd_t pmd; @@ -1440,41 +1456,72 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, goto out; } - ret = __pmd_trans_huge_lock(old_pmd, vma); + /* + * We don't have to worry about the ordering of src and dst + * ptlocks because exclusive mmap_sem prevents deadlock. + */ + ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl); if (ret == 1) { + new_ptl = pmd_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); VM_BUG_ON(!pmd_none(*new_pmd)); - set_pmd_at(mm, new_addr, new_pmd, pmd); - spin_unlock(&mm->page_table_lock); + + if (pmd_move_must_withdraw(new_ptl, old_ptl)) { + pgtable_t pgtable; + pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); + pgtable_trans_huge_deposit(mm, new_pmd, pgtable); + } + set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd)); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); } out: return ret; } +/* + * Returns + * - 0 if PMD could not be locked + * - 1 if PMD was locked but protections unchange and TLB flush unnecessary + * - HPAGE_PMD_NR is protections changed and TLB flush necessary + */ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; - entry = pmdp_get_and_clear(mm, addr, pmd); + ret = 1; if (!prot_numa) { + entry = pmdp_get_and_clear(mm, addr, pmd); + if (pmd_numa(entry)) + entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); + ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); - /* only check non-shared pages */ - if (page_mapcount(page) == 1 && + /* + * Do not trap faults against the zero page. The + * read-only data is likely to be read-cached on the + * local CPU cache and it is less useful to know about + * local vs remote hits on the zero page. + */ + if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = pmd_mknuma(entry); + pmdp_set_numa(mm, addr, pmd); + ret = HPAGE_PMD_NR; } } - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(&vma->vm_mm->page_table_lock); - ret = 1; + spin_unlock(ptl); } return ret; @@ -1487,12 +1534,13 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * Note that if it returns 1, this routine returns without unlocking page * table locks. So callers must unlock them. */ -int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) +int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, + spinlock_t **ptl) { - spin_lock(&vma->vm_mm->page_table_lock); + *ptl = pmd_lock(vma->vm_mm, pmd); if (likely(pmd_trans_huge(*pmd))) { if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(*ptl); wait_split_huge_page(vma->anon_vma, pmd); return -1; } else { @@ -1501,27 +1549,44 @@ int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) return 1; } } - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(*ptl); return 0; } +/* + * This function returns whether a given @page is mapped onto the @address + * in the virtual space of @mm. + * + * When it's true, this function returns *pmd with holding the page table lock + * and passing it back to the caller via @ptl. + * If it's false, returns NULL without holding the page table lock. + */ pmd_t *page_check_address_pmd(struct page *page, struct mm_struct *mm, unsigned long address, - enum page_check_address_pmd_flag flag) + enum page_check_address_pmd_flag flag, + spinlock_t **ptl) { - pmd_t *pmd, *ret = NULL; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; if (address & ~HPAGE_PMD_MASK) - goto out; + return NULL; - pmd = mm_find_pmd(mm, address); - if (!pmd) - goto out; - if (pmd_none(*pmd)) - goto out; + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + return NULL; + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return NULL; + pmd = pmd_offset(pud, address); + + *ptl = pmd_lock(mm, pmd); + if (!pmd_present(*pmd)) + goto unlock; if (pmd_page(*pmd) != page) - goto out; + goto unlock; /* * split_vma() may create temporary aliased mappings. There is * no risk as long as all huge pmd are found and have their @@ -1531,14 +1596,15 @@ pmd_t *page_check_address_pmd(struct page *page, */ if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG && pmd_trans_splitting(*pmd)) - goto out; + goto unlock; if (pmd_trans_huge(*pmd)) { VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG && !pmd_trans_splitting(*pmd)); - ret = pmd; + return pmd; } -out: - return ret; +unlock: + spin_unlock(*ptl); + return NULL; } static int __split_huge_page_splitting(struct page *page, @@ -1546,6 +1612,7 @@ static int __split_huge_page_splitting(struct page *page, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; pmd_t *pmd; int ret = 0; /* For mmu_notifiers */ @@ -1553,9 +1620,8 @@ static int __split_huge_page_splitting(struct page *page, const unsigned long mmun_end = address + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG); + PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl); if (pmd) { /* * We can't temporarily set the pmd to null in order @@ -1566,14 +1632,15 @@ static int __split_huge_page_splitting(struct page *page, */ pmdp_splitting_flush(vma, address, pmd); ret = 1; + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); return ret; } -static void __split_huge_page_refcount(struct page *page) +static void __split_huge_page_refcount(struct page *page, + struct list_head *list) { int i; struct zone *zone = page_zone(page); @@ -1626,7 +1693,9 @@ static void __split_huge_page_refcount(struct page *page) ((1L << PG_referenced) | (1L << PG_swapbacked) | (1L << PG_mlocked) | - (1L << PG_uptodate))); + (1L << PG_uptodate) | + (1L << PG_active) | + (1L << PG_unevictable))); page_tail->flags |= (1L << PG_dirty); /* clear PageTail before overwriting first_page */ @@ -1652,20 +1721,19 @@ static void __split_huge_page_refcount(struct page *page) page_tail->mapping = page->mapping; page_tail->index = page->index + i; - page_xchg_last_nid(page_tail, page_last_nid(page)); + page_cpupid_xchg_last(page_tail, page_cpupid_last(page)); BUG_ON(!PageAnon(page_tail)); BUG_ON(!PageUptodate(page_tail)); BUG_ON(!PageDirty(page_tail)); BUG_ON(!PageSwapBacked(page_tail)); - lru_add_page_tail(page, page_tail, lruvec); + lru_add_page_tail(page, page_tail, lruvec, list); } atomic_sub(tail_count, &page->_count); BUG_ON(atomic_read(&page->_count) <= 0); __mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1); - __mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR); ClearPageCompound(page); compound_unlock(page); @@ -1696,16 +1764,16 @@ static int __split_huge_page_map(struct page *page, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; pmd_t *pmd, _pmd; int ret = 0, i; pgtable_t pgtable; unsigned long haddr; - spin_lock(&mm->page_table_lock); pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG); + PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl); if (pmd) { - pgtable = pgtable_trans_huge_withdraw(mm); + pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); haddr = address; @@ -1758,15 +1826,16 @@ static int __split_huge_page_map(struct page *page, pmdp_invalidate(vma, address, pmd); pmd_populate(mm, pmd, pgtable); ret = 1; + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); return ret; } /* must be called with anon_vma->root->rwsem held */ static void __split_huge_page(struct page *page, - struct anon_vma *anon_vma) + struct anon_vma *anon_vma, + struct list_head *list) { int mapcount, mapcount2; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); @@ -1792,12 +1861,13 @@ static void __split_huge_page(struct page *page, * the newly established pmd of the child later during the * walk, to be able to set it as pmd_trans_splitting too. */ - if (mapcount != page_mapcount(page)) - printk(KERN_ERR "mapcount %d page_mapcount %d\n", - mapcount, page_mapcount(page)); - BUG_ON(mapcount != page_mapcount(page)); + if (mapcount != page_mapcount(page)) { + pr_err("mapcount %d page_mapcount %d\n", + mapcount, page_mapcount(page)); + BUG(); + } - __split_huge_page_refcount(page); + __split_huge_page_refcount(page, list); mapcount2 = 0; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { @@ -1806,18 +1876,26 @@ static void __split_huge_page(struct page *page, BUG_ON(is_vma_temporary_stack(vma)); mapcount2 += __split_huge_page_map(page, vma, addr); } - if (mapcount != mapcount2) - printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d\n", - mapcount, mapcount2, page_mapcount(page)); - BUG_ON(mapcount != mapcount2); + if (mapcount != mapcount2) { + pr_err("mapcount %d mapcount2 %d page_mapcount %d\n", + mapcount, mapcount2, page_mapcount(page)); + BUG(); + } } -int split_huge_page(struct page *page) +/* + * Split a hugepage into normal pages. This doesn't change the position of head + * page. If @list is null, tail pages will be added to LRU list, otherwise, to + * @list. Both head page and tail pages will inherit mapping, flags, and so on + * from the hugepage. + * Return 0 if the hugepage is split successfully otherwise return 1. + */ +int split_huge_page_to_list(struct page *page, struct list_head *list) { struct anon_vma *anon_vma; int ret = 1; - BUG_ON(is_huge_zero_pfn(page_to_pfn(page))); + BUG_ON(is_huge_zero_page(page)); BUG_ON(!PageAnon(page)); /* @@ -1837,33 +1915,38 @@ int split_huge_page(struct page *page) goto out_unlock; BUG_ON(!PageSwapBacked(page)); - __split_huge_page(page, anon_vma); + __split_huge_page(page, anon_vma, list); count_vm_event(THP_SPLIT); BUG_ON(PageCompound(page)); out_unlock: - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); put_anon_vma(anon_vma); out: return ret; } -#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE) +#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { - struct mm_struct *mm = vma->vm_mm; - switch (advice) { case MADV_HUGEPAGE: +#ifdef CONFIG_S390 + /* + * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 + * can't handle this properly after s390_enable_sie, so we simply + * ignore the madvise to prevent qemu from causing a SIGSEGV. + */ + if (mm_has_pgste(vma->vm_mm)) + return 0; +#endif /* * Be somewhat over-protective like KSM for now! */ if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP)) return -EINVAL; - if (mm->def_flags & VM_NOHUGEPAGE) - return -EINVAL; *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* @@ -1904,12 +1987,6 @@ static int __init khugepaged_slab_init(void) return 0; } -static void __init khugepaged_slab_free(void) -{ - kmem_cache_destroy(mm_slot_cache); - mm_slot_cache = NULL; -} - static inline struct mm_slot *alloc_mm_slot(void) { if (!mm_slot_cache) /* initialization failed */ @@ -1922,47 +1999,22 @@ static inline void free_mm_slot(struct mm_slot *mm_slot) kmem_cache_free(mm_slot_cache, mm_slot); } -static int __init mm_slots_hash_init(void) -{ - mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head), - GFP_KERNEL); - if (!mm_slots_hash) - return -ENOMEM; - return 0; -} - -#if 0 -static void __init mm_slots_hash_free(void) -{ - kfree(mm_slots_hash); - mm_slots_hash = NULL; -} -#endif - static struct mm_slot *get_mm_slot(struct mm_struct *mm) { struct mm_slot *mm_slot; - struct hlist_head *bucket; - struct hlist_node *node; - bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) - % MM_SLOTS_HASH_HEADS]; - hlist_for_each_entry(mm_slot, node, bucket, hash) { + hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) if (mm == mm_slot->mm) return mm_slot; - } + return NULL; } static void insert_to_mm_slots_hash(struct mm_struct *mm, struct mm_slot *mm_slot) { - struct hlist_head *bucket; - - bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) - % MM_SLOTS_HASH_HEADS]; mm_slot->mm = mm; - hlist_add_head(&mm_slot->hash, bucket); + hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); } static inline int khugepaged_test_exit(struct mm_struct *mm) @@ -2031,7 +2083,7 @@ void __khugepaged_exit(struct mm_struct *mm) spin_lock(&khugepaged_mm_lock); mm_slot = get_mm_slot(mm); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { - hlist_del(&mm_slot->hash); + hash_del(&mm_slot->hash); list_del(&mm_slot->mm_node); free = 1; } @@ -2094,9 +2146,9 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, if (unlikely(!page)) goto out; - VM_BUG_ON(PageCompound(page)); - BUG_ON(!PageAnon(page)); - VM_BUG_ON(!PageSwapBacked(page)); + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); /* cannot use mapcount: can't collapse if there's a gup pin */ if (page_count(page) != 1) @@ -2119,8 +2171,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, } /* 0 stands for page_is_file_cache(page) == false */ inc_zone_page_state(page, NR_ISOLATED_ANON + 0); - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageLRU(page), page); /* If there is no mapped pte young don't collapse the page */ if (pte_young(pteval) || PageReferenced(page) || @@ -2150,7 +2202,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, } else { src_page = pte_page(pteval); copy_user_highpage(page, src_page, address, vma); - VM_BUG_ON(page_mapcount(src_page) != 1); + VM_BUG_ON_PAGE(page_mapcount(src_page) != 1, src_page); release_pte_page(src_page); /* * ptl mostly unnecessary, but preempt has to @@ -2179,7 +2231,34 @@ static void khugepaged_alloc_sleep(void) msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); } +static int khugepaged_node_load[MAX_NUMNODES]; + #ifdef CONFIG_NUMA +static int khugepaged_find_target_node(void) +{ + static int last_khugepaged_target_node = NUMA_NO_NODE; + int nid, target_node = 0, max_value = 0; + + /* find first node with max normal pages hit */ + for (nid = 0; nid < MAX_NUMNODES; nid++) + if (khugepaged_node_load[nid] > max_value) { + max_value = khugepaged_node_load[nid]; + target_node = nid; + } + + /* do some balance if several nodes have the same hit record */ + if (target_node <= last_khugepaged_target_node) + for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; + nid++) + if (max_value == khugepaged_node_load[nid]) { + target_node = nid; + break; + } + + last_khugepaged_target_node = target_node; + return target_node; +} + static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { if (IS_ERR(*hpage)) { @@ -2202,7 +2281,7 @@ static struct page struct vm_area_struct *vma, unsigned long address, int node) { - VM_BUG_ON(*hpage); + VM_BUG_ON_PAGE(*hpage, *hpage); /* * Allocate the page while the vma is still valid and under * the mmap_sem read mode so there is no memory allocation @@ -2213,9 +2292,8 @@ static struct page * mmap_sem in read mode is good idea also to allow greater * scalability. */ - *hpage = alloc_hugepage_vma(khugepaged_defrag(), vma, address, - node, __GFP_OTHER_NODE); - + *hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask( + khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER); /* * After allocating the hugepage, release the mmap_sem read lock in * preparation for taking it in write mode. @@ -2231,6 +2309,17 @@ static struct page return *hpage; } #else +static int khugepaged_find_target_node(void) +{ + return 0; +} + +static inline struct page *alloc_hugepage(int defrag) +{ + return alloc_pages(alloc_hugepage_gfpmask(defrag, 0), + HPAGE_PMD_ORDER); +} + static struct page *khugepaged_alloc_hugepage(bool *wait) { struct page *hpage; @@ -2297,7 +2386,7 @@ static void collapse_huge_page(struct mm_struct *mm, pte_t *pte; pgtable_t pgtable; struct page *new_page; - spinlock_t *ptl; + spinlock_t *pmd_ptl, *pte_ptl; int isolated; unsigned long hstart, hend; unsigned long mmun_start; /* For mmu_notifiers */ @@ -2310,7 +2399,7 @@ static void collapse_huge_page(struct mm_struct *mm, if (!new_page) return; - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) + if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) return; /* @@ -2323,6 +2412,8 @@ static void collapse_huge_page(struct mm_struct *mm, goto out; vma = find_vma(mm, address); + if (!vma) + goto out; hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (address < hstart || address + HPAGE_PMD_SIZE > hend) @@ -2332,18 +2423,16 @@ static void collapse_huge_page(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; anon_vma_lock_write(vma->anon_vma); pte = pte_offset_map(pmd, address); - ptl = pte_lockptr(mm, pmd); + pte_ptl = pte_lockptr(mm, pmd); mmun_start = address; mmun_end = address + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); /* probably unnecessary */ + pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * After this gup_fast can't run anymore. This also removes * any huge TLB entry from the CPU so we won't allow @@ -2351,20 +2440,25 @@ static void collapse_huge_page(struct mm_struct *mm, * to avoid the risk of CPU bugs in that area. */ _pmd = pmdp_clear_flush(vma, address, pmd); - spin_unlock(&mm->page_table_lock); + spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - spin_lock(ptl); + spin_lock(pte_ptl); isolated = __collapse_huge_page_isolate(vma, address, pte); - spin_unlock(ptl); + spin_unlock(pte_ptl); if (unlikely(!isolated)) { pte_unmap(pte); - spin_lock(&mm->page_table_lock); + spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - set_pmd_at(mm, address, pmd, _pmd); - spin_unlock(&mm->page_table_lock); - anon_vma_unlock(vma->anon_vma); + /* + * We can only use set_pmd_at when establishing + * hugepmds and never for establishing regular pmds that + * points to regular pagetables. Use pmd_populate for that + */ + pmd_populate(mm, pmd, pmd_pgtable(_pmd)); + spin_unlock(pmd_ptl); + anon_vma_unlock_write(vma->anon_vma); goto out; } @@ -2372,14 +2466,15 @@ static void collapse_huge_page(struct mm_struct *mm, * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ - anon_vma_unlock(vma->anon_vma); + anon_vma_unlock_write(vma->anon_vma); - __collapse_huge_page_copy(pte, new_page, vma, address, ptl); + __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl); pte_unmap(pte); __SetPageUptodate(new_page); pgtable = pmd_pgtable(_pmd); - _pmd = mk_huge_pmd(new_page, vma); + _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); + _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); /* * spin_lock() below is not the equivalent of smp_wmb(), so @@ -2388,13 +2483,13 @@ static void collapse_huge_page(struct mm_struct *mm, */ smp_wmb(); - spin_lock(&mm->page_table_lock); + spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address); + pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); - pgtable_trans_huge_deposit(mm, pgtable); - spin_unlock(&mm->page_table_lock); + spin_unlock(pmd_ptl); *hpage = NULL; @@ -2419,16 +2514,15 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct page *page; unsigned long _address; spinlock_t *ptl; - int node = -1; + int node = NUMA_NO_NODE; VM_BUG_ON(address & ~HPAGE_PMD_MASK); pmd = mm_find_pmd(mm, address); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; + memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { @@ -2445,13 +2539,14 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, if (unlikely(!page)) goto out_unmap; /* - * Chose the node of the first page. This could - * be more sophisticated and look at more pages, - * but isn't for now. + * Record which node the original page is from and save this + * information to khugepaged_node_load[]. + * Khupaged will allocate hugepage from the node has the max + * hit record. */ - if (node == -1) - node = page_to_nid(page); - VM_BUG_ON(PageCompound(page)); + node = page_to_nid(page); + khugepaged_node_load[node]++; + VM_BUG_ON_PAGE(PageCompound(page), page); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) goto out_unmap; /* cannot use mapcount: can't collapse if there's a gup pin */ @@ -2465,9 +2560,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, ret = 1; out_unmap: pte_unmap_unlock(pte, ptl); - if (ret) + if (ret) { + node = khugepaged_find_target_node(); /* collapse_huge_page will return with the mmap_sem released */ collapse_huge_page(mm, address, hpage, vma, node); + } out: return ret; } @@ -2480,7 +2577,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot) if (khugepaged_test_exit(mm)) { /* free mm_slot */ - hlist_del(&mm_slot->hash); + hash_del(&mm_slot->hash); list_del(&mm_slot->mm_node); /* @@ -2672,7 +2769,7 @@ static int khugepaged(void *none) struct mm_slot *mm_slot; set_freezable(); - set_user_nice(current, 19); + set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(); @@ -2699,7 +2796,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, pmdp_clear_flush(vma, haddr, pmd); /* leave pmd empty until pte is filled */ - pgtable = pgtable_trans_huge_withdraw(mm); + pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { @@ -2719,6 +2816,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd) { + spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; unsigned long haddr = address & HPAGE_PMD_MASK; @@ -2729,29 +2827,37 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, mmun_start = haddr; mmun_end = haddr + HPAGE_PMD_SIZE; +again: mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_trans_huge(*pmd))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); return; } if (is_huge_zero_pmd(*pmd)) { __split_huge_zero_page_pmd(vma, haddr, pmd); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); return; } page = pmd_page(*pmd); - VM_BUG_ON(!page_count(page)); + VM_BUG_ON_PAGE(!page_count(page), page); get_page(page); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); split_huge_page(page); put_page(page); - BUG_ON(pmd_trans_huge(*pmd)); + + /* + * We don't always have down_write of mmap_sem here: a racing + * do_huge_pmd_wp_page() might have copied-on-write to another + * huge page before our split_huge_page() got the anon_vma lock. + */ + if (unlikely(pmd_trans_huge(*pmd))) + goto again; } void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, @@ -2767,12 +2873,22 @@ void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, static void split_huge_page_address(struct mm_struct *mm, unsigned long address) { + pgd_t *pgd; + pud_t *pud; pmd_t *pmd; VM_BUG_ON(!(address & ~HPAGE_PMD_MASK)); - pmd = mm_find_pmd(mm, address); - if (!pmd) + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + return; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return; + + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) return; /* * Caller holds the mmap_sem write mode, so a huge pmd cannot diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4f3ea0b1e57..7a0a73d2fcf 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -13,6 +13,7 @@ #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> +#include <linux/compiler.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/bootmem.h> @@ -21,6 +22,8 @@ #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/page-isolation.h> +#include <linux/jhash.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -33,7 +36,6 @@ #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; -static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; int hugetlb_max_hstate __read_mostly; @@ -48,10 +50,18 @@ static unsigned long __initdata default_hstate_max_huge_pages; static unsigned long __initdata default_hstate_size; /* - * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages + * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, + * free_huge_pages, and surplus_huge_pages. */ DEFINE_SPINLOCK(hugetlb_lock); +/* + * Serializes faults on the same logical page. This is used to + * prevent spurious OOMs when the hugepage pool is fully utilized. + */ +static int num_fault_mutexes; +static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp; + static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) { bool free = (spool->count == 0) && (spool->used_hpages == 0); @@ -127,22 +137,15 @@ static inline struct hugepage_subpool *subpool_inode(struct inode *inode) static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { - return subpool_inode(vma->vm_file->f_dentry->d_inode); + return subpool_inode(file_inode(vma->vm_file)); } /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * - * The region data structures are protected by a combination of the mmap_sem - * and the hugetlb_instantion_mutex. To access or modify a region the caller - * must either hold the mmap_sem for write, or the mmap_sem for read and - * the hugetlb_instantiation mutex: - * - * down_write(&mm->mmap_sem); - * or - * down_read(&mm->mmap_sem); - * mutex_lock(&hugetlb_instantiation_mutex); + * The region data structures are embedded into a resv_map and + * protected by a resv_map's lock */ struct file_region { struct list_head link; @@ -150,10 +153,12 @@ struct file_region { long to; }; -static long region_add(struct list_head *head, long f, long t) +static long region_add(struct resv_map *resv, long f, long t) { + struct list_head *head = &resv->regions; struct file_region *rg, *nrg, *trg; + spin_lock(&resv->lock); /* Locate the region we are either in or before. */ list_for_each_entry(rg, head, link) if (f <= rg->to) @@ -183,14 +188,18 @@ static long region_add(struct list_head *head, long f, long t) } nrg->from = f; nrg->to = t; + spin_unlock(&resv->lock); return 0; } -static long region_chg(struct list_head *head, long f, long t) +static long region_chg(struct resv_map *resv, long f, long t) { - struct file_region *rg, *nrg; + struct list_head *head = &resv->regions; + struct file_region *rg, *nrg = NULL; long chg = 0; +retry: + spin_lock(&resv->lock); /* Locate the region we are before or in. */ list_for_each_entry(rg, head, link) if (f <= rg->to) @@ -200,15 +209,21 @@ static long region_chg(struct list_head *head, long f, long t) * Subtle, allocate a new region at the position but make it zero * size such that we can guarantee to record the reservation. */ if (&rg->link == head || t < rg->from) { - nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); - if (!nrg) - return -ENOMEM; - nrg->from = f; - nrg->to = f; - INIT_LIST_HEAD(&nrg->link); - list_add(&nrg->link, rg->link.prev); + if (!nrg) { + spin_unlock(&resv->lock); + nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); + if (!nrg) + return -ENOMEM; + + nrg->from = f; + nrg->to = f; + INIT_LIST_HEAD(&nrg->link); + goto retry; + } - return t - f; + list_add(&nrg->link, rg->link.prev); + chg = t - f; + goto out_nrg; } /* Round our left edge to the current segment if it encloses us. */ @@ -221,7 +236,7 @@ static long region_chg(struct list_head *head, long f, long t) if (&rg->link == head) break; if (rg->from > t) - return chg; + goto out; /* We overlap with this area, if it extends further than * us then we must extend ourselves. Account for its @@ -232,20 +247,30 @@ static long region_chg(struct list_head *head, long f, long t) } chg -= rg->to - rg->from; } + +out: + spin_unlock(&resv->lock); + /* We already know we raced and no longer need the new region */ + kfree(nrg); + return chg; +out_nrg: + spin_unlock(&resv->lock); return chg; } -static long region_truncate(struct list_head *head, long end) +static long region_truncate(struct resv_map *resv, long end) { + struct list_head *head = &resv->regions; struct file_region *rg, *trg; long chg = 0; + spin_lock(&resv->lock); /* Locate the region we are either in or before. */ list_for_each_entry(rg, head, link) if (end <= rg->to) break; if (&rg->link == head) - return 0; + goto out; /* If we are in the middle of a region then adjust it. */ if (end > rg->from) { @@ -262,14 +287,19 @@ static long region_truncate(struct list_head *head, long end) list_del(&rg->link); kfree(rg); } + +out: + spin_unlock(&resv->lock); return chg; } -static long region_count(struct list_head *head, long f, long t) +static long region_count(struct resv_map *resv, long f, long t) { + struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; + spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; @@ -285,6 +315,7 @@ static long region_count(struct list_head *head, long f, long t) chg += seg_to - seg_from; } + spin_unlock(&resv->lock); return chg; } @@ -319,7 +350,7 @@ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) hstate = hstate_vma(vma); - return 1UL << (hstate->order + PAGE_SHIFT); + return 1UL << huge_page_shift(hstate); } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); @@ -375,39 +406,46 @@ static void set_vma_private_data(struct vm_area_struct *vma, vma->vm_private_data = (void *)value; } -struct resv_map { - struct kref refs; - struct list_head regions; -}; - -static struct resv_map *resv_map_alloc(void) +struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); if (!resv_map) return NULL; kref_init(&resv_map->refs); + spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); return resv_map; } -static void resv_map_release(struct kref *ref) +void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); /* Clear out any active regions before we release the map. */ - region_truncate(&resv_map->regions, 0); + region_truncate(resv_map, 0); kfree(resv_map); } +static inline struct resv_map *inode_resv_map(struct inode *inode) +{ + return inode->i_mapping->private_data; +} + static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - if (!(vma->vm_flags & VM_MAYSHARE)) + if (vma->vm_flags & VM_MAYSHARE) { + struct address_space *mapping = vma->vm_file->f_mapping; + struct inode *inode = mapping->host; + + return inode_resv_map(inode); + + } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); - return NULL; + } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) @@ -434,25 +472,6 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) return (get_vma_private_data(vma) & flag) != 0; } -/* Decrement the reserved pages in the hugepage pool by one */ -static void decrement_hugepage_resv_vma(struct hstate *h, - struct vm_area_struct *vma) -{ - if (vma->vm_flags & VM_NORESERVE) - return; - - if (vma->vm_flags & VM_MAYSHARE) { - /* Shared mappings always use reserves */ - h->resv_huge_pages--; - } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { - /* - * Only the process that called mmap() has reserves for - * private mappings. - */ - h->resv_huge_pages--; - } -} - /* Reset counters to 0 and clear all HPAGE_RESV_* flags */ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { @@ -462,47 +481,36 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) } /* Returns true if the VMA has associated reserve pages */ -static int vma_has_reserves(struct vm_area_struct *vma) +static int vma_has_reserves(struct vm_area_struct *vma, long chg) { + if (vma->vm_flags & VM_NORESERVE) { + /* + * This address is already reserved by other process(chg == 0), + * so, we should decrement reserved count. Without decrementing, + * reserve count remains after releasing inode, because this + * allocated page will go into page cache and is regarded as + * coming from reserved pool in releasing step. Currently, we + * don't have any other solution to deal with this situation + * properly, so add work-around here. + */ + if (vma->vm_flags & VM_MAYSHARE && chg == 0) + return 1; + else + return 0; + } + + /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) return 1; + + /* + * Only the process that called mmap() has reserves for + * private mappings. + */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return 1; - return 0; -} -static void copy_gigantic_page(struct page *dst, struct page *src) -{ - int i; - struct hstate *h = page_hstate(src); - struct page *dst_base = dst; - struct page *src_base = src; - - for (i = 0; i < pages_per_huge_page(h); ) { - cond_resched(); - copy_highpage(dst, src); - - i++; - dst = mem_map_next(dst, dst_base, i); - src = mem_map_next(src, src_base, i); - } -} - -void copy_huge_page(struct page *dst, struct page *src) -{ - int i; - struct hstate *h = page_hstate(src); - - if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) { - copy_gigantic_page(dst, src); - return; - } - - might_sleep(); - for (i = 0; i < pages_per_huge_page(h); i++) { - cond_resched(); - copy_highpage(dst + i, src + i); - } + return 0; } static void enqueue_huge_page(struct hstate *h, struct page *page) @@ -517,9 +525,15 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) { struct page *page; - if (list_empty(&h->hugepage_freelists[nid])) + list_for_each_entry(page, &h->hugepage_freelists[nid], lru) + if (!is_migrate_isolate_page(page)) + break; + /* + * if 'non-isolated free hugepage' not found on the list, + * the allocation fails. + */ + if (&h->hugepage_freelists[nid] == &page->lru) return NULL; - page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); h->free_huge_pages--; @@ -527,9 +541,19 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) return page; } +/* Movability of hugepages depends on migration support. */ +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + if (hugepages_treat_as_movable || hugepage_migration_supported(h)) + return GFP_HIGHUSER_MOVABLE; + else + return GFP_HIGHUSER; +} + static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, int avoid_reserve) + unsigned long address, int avoid_reserve, + long chg) { struct page *page = NULL; struct mempolicy *mpol; @@ -539,16 +563,12 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, struct zoneref *z; unsigned int cpuset_mems_cookie; -retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); - zonelist = huge_zonelist(vma, address, - htlb_alloc_mask, &mpol, &nodemask); /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ - if (!vma_has_reserves(vma) && + if (!vma_has_reserves(vma, chg) && h->free_huge_pages - h->resv_huge_pages == 0) goto err; @@ -556,47 +576,273 @@ retry_cpuset: if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) goto err; +retry_cpuset: + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist = huge_zonelist(vma, address, + htlb_alloc_mask(h), &mpol, &nodemask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { - if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) { + if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) { page = dequeue_huge_page_node(h, zone_to_nid(zone)); if (page) { - if (!avoid_reserve) - decrement_hugepage_resv_vma(h, vma); + if (avoid_reserve) + break; + if (!vma_has_reserves(vma, chg)) + break; + + SetPagePrivate(page); + h->resv_huge_pages--; break; } } } mpol_cond_put(mpol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; err: - mpol_cond_put(mpol); return NULL; } +/* + * common helper functions for hstate_next_node_to_{alloc|free}. + * We may have allocated or freed a huge page based on a different + * nodes_allowed previously, so h->next_node_to_{alloc|free} might + * be outside of *nodes_allowed. Ensure that we use an allowed + * node for alloc or free. + */ +static int next_node_allowed(int nid, nodemask_t *nodes_allowed) +{ + nid = next_node(nid, *nodes_allowed); + if (nid == MAX_NUMNODES) + nid = first_node(*nodes_allowed); + VM_BUG_ON(nid >= MAX_NUMNODES); + + return nid; +} + +static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) +{ + if (!node_isset(nid, *nodes_allowed)) + nid = next_node_allowed(nid, nodes_allowed); + return nid; +} + +/* + * returns the previously saved node ["this node"] from which to + * allocate a persistent huge page for the pool and advance the + * next node from which to allocate, handling wrap at end of node + * mask. + */ +static int hstate_next_node_to_alloc(struct hstate *h, + nodemask_t *nodes_allowed) +{ + int nid; + + VM_BUG_ON(!nodes_allowed); + + nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed); + h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed); + + return nid; +} + +/* + * helper for free_pool_huge_page() - return the previously saved + * node ["this node"] from which to free a huge page. Advance the + * next node id whether or not we find a free huge page to free so + * that the next attempt to free addresses the next node. + */ +static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) +{ + int nid; + + VM_BUG_ON(!nodes_allowed); + + nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); + h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); + + return nid; +} + +#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \ + nr_nodes--) + +#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_free(hs, mask)) || 1); \ + nr_nodes--) + +#if defined(CONFIG_CMA) && defined(CONFIG_X86_64) +static void destroy_compound_gigantic_page(struct page *page, + unsigned long order) +{ + int i; + int nr_pages = 1 << order; + struct page *p = page + 1; + + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + __ClearPageTail(p); + set_page_refcounted(p); + p->first_page = NULL; + } + + set_compound_order(page, 0); + __ClearPageHead(page); +} + +static void free_gigantic_page(struct page *page, unsigned order) +{ + free_contig_range(page_to_pfn(page), 1 << order); +} + +static int __alloc_gigantic_page(unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long end_pfn = start_pfn + nr_pages; + return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE); +} + +static bool pfn_range_valid_gigantic(unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long i, end_pfn = start_pfn + nr_pages; + struct page *page; + + for (i = start_pfn; i < end_pfn; i++) { + if (!pfn_valid(i)) + return false; + + page = pfn_to_page(i); + + if (PageReserved(page)) + return false; + + if (page_count(page) > 0) + return false; + + if (PageHuge(page)) + return false; + } + + return true; +} + +static bool zone_spans_last_pfn(const struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + unsigned long last_pfn = start_pfn + nr_pages - 1; + return zone_spans_pfn(zone, last_pfn); +} + +static struct page *alloc_gigantic_page(int nid, unsigned order) +{ + unsigned long nr_pages = 1 << order; + unsigned long ret, pfn, flags; + struct zone *z; + + z = NODE_DATA(nid)->node_zones; + for (; z - NODE_DATA(nid)->node_zones < MAX_NR_ZONES; z++) { + spin_lock_irqsave(&z->lock, flags); + + pfn = ALIGN(z->zone_start_pfn, nr_pages); + while (zone_spans_last_pfn(z, pfn, nr_pages)) { + if (pfn_range_valid_gigantic(pfn, nr_pages)) { + /* + * We release the zone lock here because + * alloc_contig_range() will also lock the zone + * at some point. If there's an allocation + * spinning on this lock, it may win the race + * and cause alloc_contig_range() to fail... + */ + spin_unlock_irqrestore(&z->lock, flags); + ret = __alloc_gigantic_page(pfn, nr_pages); + if (!ret) + return pfn_to_page(pfn); + spin_lock_irqsave(&z->lock, flags); + } + pfn += nr_pages; + } + + spin_unlock_irqrestore(&z->lock, flags); + } + + return NULL; +} + +static void prep_new_huge_page(struct hstate *h, struct page *page, int nid); +static void prep_compound_gigantic_page(struct page *page, unsigned long order); + +static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid) +{ + struct page *page; + + page = alloc_gigantic_page(nid, huge_page_order(h)); + if (page) { + prep_compound_gigantic_page(page, huge_page_order(h)); + prep_new_huge_page(h, page, nid); + } + + return page; +} + +static int alloc_fresh_gigantic_page(struct hstate *h, + nodemask_t *nodes_allowed) +{ + struct page *page = NULL; + int nr_nodes, node; + + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + page = alloc_fresh_gigantic_page_node(h, node); + if (page) + return 1; + } + + return 0; +} + +static inline bool gigantic_page_supported(void) { return true; } +#else +static inline bool gigantic_page_supported(void) { return false; } +static inline void free_gigantic_page(struct page *page, unsigned order) { } +static inline void destroy_compound_gigantic_page(struct page *page, + unsigned long order) { } +static inline int alloc_fresh_gigantic_page(struct hstate *h, + nodemask_t *nodes_allowed) { return 0; } +#endif + static void update_and_free_page(struct hstate *h, struct page *page) { int i; - VM_BUG_ON(h->order >= MAX_ORDER); + if (hstate_is_gigantic(h) && !gigantic_page_supported()) + return; h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; for (i = 0; i < pages_per_huge_page(h); i++) { page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | - 1 << PG_active | 1 << PG_reserved | - 1 << PG_private | 1 << PG_writeback); + 1 << PG_active | 1 << PG_private | + 1 << PG_writeback); } - VM_BUG_ON(hugetlb_cgroup_from_page(page)); + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); set_compound_page_dtor(page, NULL); set_page_refcounted(page); - arch_release_hugepage(page); - __free_pages(page, huge_page_order(h)); + if (hstate_is_gigantic(h)) { + destroy_compound_gigantic_page(page, huge_page_order(h)); + free_gigantic_page(page, huge_page_order(h)); + } else { + arch_release_hugepage(page); + __free_pages(page, huge_page_order(h)); + } } struct hstate *size_to_hstate(unsigned long size) @@ -610,7 +856,7 @@ struct hstate *size_to_hstate(unsigned long size) return NULL; } -static void free_huge_page(struct page *page) +void free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the @@ -620,16 +866,22 @@ static void free_huge_page(struct page *page) int nid = page_to_nid(page); struct hugepage_subpool *spool = (struct hugepage_subpool *)page_private(page); + bool restore_reserve; set_page_private(page, 0); page->mapping = NULL; BUG_ON(page_count(page)); BUG_ON(page_mapcount(page)); + restore_reserve = PagePrivate(page); + ClearPagePrivate(page); spin_lock(&hugetlb_lock); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); - if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) { + if (restore_reserve) + h->resv_huge_pages++; + + if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ list_del(&page->lru); update_and_free_page(h, page); @@ -664,8 +916,22 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); __SetPageHead(page); + __ClearPageReserved(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { __SetPageTail(p); + /* + * For gigantic hugepages allocated through bootmem at + * boot, it's safer to be consistent with the not-gigantic + * hugepages and clear the PG_reserved bit from all tail pages + * too. Otherwse drivers using get_user_pages() to access tail + * pages may get the reference counting wrong if they see + * PG_reserved set on a tail page (despite the head page not + * having PG_reserved set). Enforcing this consistency between + * head and tail pages allows drivers to optimize away a check + * on the head page when they need know if put_page() is needed + * after get_user_pages(). + */ + __ClearPageReserved(p); set_page_count(p, 0); p->first_page = page; } @@ -678,27 +944,49 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) */ int PageHuge(struct page *page) { - compound_page_dtor *dtor; - if (!PageCompound(page)) return 0; page = compound_head(page); - dtor = get_compound_page_dtor(page); - - return dtor == free_huge_page; + return get_compound_page_dtor(page) == free_huge_page; } EXPORT_SYMBOL_GPL(PageHuge); +/* + * PageHeadHuge() only returns true for hugetlbfs head page, but not for + * normal or transparent huge pages. + */ +int PageHeadHuge(struct page *page_head) +{ + if (!PageHead(page_head)) + return 0; + + return get_compound_page_dtor(page_head) == free_huge_page; +} + +pgoff_t __basepage_index(struct page *page) +{ + struct page *page_head = compound_head(page); + pgoff_t index = page_index(page_head); + unsigned long compound_idx; + + if (!PageHuge(page_head)) + return page_index(page); + + if (compound_order(page_head) >= MAX_ORDER) + compound_idx = page_to_pfn(page) - page_to_pfn(page_head); + else + compound_idx = page - page_head; + + return (index << compound_order(page_head)) + compound_idx; +} + static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; - if (h->order >= MAX_ORDER) - return NULL; - page = alloc_pages_exact_node(nid, - htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| + htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page) { @@ -712,67 +1000,19 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) return page; } -/* - * common helper functions for hstate_next_node_to_{alloc|free}. - * We may have allocated or freed a huge page based on a different - * nodes_allowed previously, so h->next_node_to_{alloc|free} might - * be outside of *nodes_allowed. Ensure that we use an allowed - * node for alloc or free. - */ -static int next_node_allowed(int nid, nodemask_t *nodes_allowed) -{ - nid = next_node(nid, *nodes_allowed); - if (nid == MAX_NUMNODES) - nid = first_node(*nodes_allowed); - VM_BUG_ON(nid >= MAX_NUMNODES); - - return nid; -} - -static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) -{ - if (!node_isset(nid, *nodes_allowed)) - nid = next_node_allowed(nid, nodes_allowed); - return nid; -} - -/* - * returns the previously saved node ["this node"] from which to - * allocate a persistent huge page for the pool and advance the - * next node from which to allocate, handling wrap at end of node - * mask. - */ -static int hstate_next_node_to_alloc(struct hstate *h, - nodemask_t *nodes_allowed) -{ - int nid; - - VM_BUG_ON(!nodes_allowed); - - nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed); - h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed); - - return nid; -} - static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed) { struct page *page; - int start_nid; - int next_nid; + int nr_nodes, node; int ret = 0; - start_nid = hstate_next_node_to_alloc(h, nodes_allowed); - next_nid = start_nid; - - do { - page = alloc_fresh_huge_page_node(h, next_nid); + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + page = alloc_fresh_huge_page_node(h, node); if (page) { ret = 1; break; } - next_nid = hstate_next_node_to_alloc(h, nodes_allowed); - } while (next_nid != start_nid); + } if (ret) count_vm_event(HTLB_BUDDY_PGALLOC); @@ -783,24 +1023,6 @@ static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed) } /* - * helper for free_pool_huge_page() - return the previously saved - * node ["this node"] from which to free a huge page. Advance the - * next node id whether or not we find a free huge page to free so - * that the next attempt to free addresses the next node. - */ -static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) -{ - int nid; - - VM_BUG_ON(!nodes_allowed); - - nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); - h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); - - return nid; -} - -/* * Free huge page from pool from next node to free. * Attempt to keep persistent huge pages more or less * balanced over allowed nodes. @@ -809,46 +1031,79 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { - int start_nid; - int next_nid; + int nr_nodes, node; int ret = 0; - start_nid = hstate_next_node_to_free(h, nodes_allowed); - next_nid = start_nid; - - do { + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ - if ((!acct_surplus || h->surplus_huge_pages_node[next_nid]) && - !list_empty(&h->hugepage_freelists[next_nid])) { + if ((!acct_surplus || h->surplus_huge_pages_node[node]) && + !list_empty(&h->hugepage_freelists[node])) { struct page *page = - list_entry(h->hugepage_freelists[next_nid].next, + list_entry(h->hugepage_freelists[node].next, struct page, lru); list_del(&page->lru); h->free_huge_pages--; - h->free_huge_pages_node[next_nid]--; + h->free_huge_pages_node[node]--; if (acct_surplus) { h->surplus_huge_pages--; - h->surplus_huge_pages_node[next_nid]--; + h->surplus_huge_pages_node[node]--; } update_and_free_page(h, page); ret = 1; break; } - next_nid = hstate_next_node_to_free(h, nodes_allowed); - } while (next_nid != start_nid); + } return ret; } +/* + * Dissolve a given free hugepage into free buddy pages. This function does + * nothing for in-use (including surplus) hugepages. + */ +static void dissolve_free_huge_page(struct page *page) +{ + spin_lock(&hugetlb_lock); + if (PageHuge(page) && !page_count(page)) { + struct hstate *h = page_hstate(page); + int nid = page_to_nid(page); + list_del(&page->lru); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + update_and_free_page(h, page); + } + spin_unlock(&hugetlb_lock); +} + +/* + * Dissolve free hugepages in a given pfn range. Used by memory hotplug to + * make specified memory blocks removable from the system. + * Note that start_pfn should aligned with (minimum) hugepage size. + */ +void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned int order = 8 * sizeof(void *); + unsigned long pfn; + struct hstate *h; + + /* Set scan step to minimum hugepage size */ + for_each_hstate(h) + if (order > huge_page_order(h)) + order = huge_page_order(h); + VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << order)); + for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) + dissolve_free_huge_page(pfn_to_page(pfn)); +} + static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) { struct page *page; unsigned int r_nid; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return NULL; /* @@ -885,12 +1140,12 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) spin_unlock(&hugetlb_lock); if (nid == NUMA_NO_NODE) - page = alloc_pages(htlb_alloc_mask|__GFP_COMP| + page = alloc_pages(htlb_alloc_mask(h)|__GFP_COMP| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); else page = alloc_pages_exact_node(nid, - htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| + htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page && arch_prepare_hugepage(page)) { @@ -927,10 +1182,11 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) */ struct page *alloc_huge_page_node(struct hstate *h, int nid) { - struct page *page; + struct page *page = NULL; spin_lock(&hugetlb_lock); - page = dequeue_huge_page_node(h, nid); + if (h->free_huge_pages - h->resv_huge_pages > 0) + page = dequeue_huge_page_node(h, nid); spin_unlock(&hugetlb_lock); if (!page) @@ -1011,18 +1267,15 @@ retry: * no users -- drop the buddy allocator's reference. */ put_page_testzero(page); - VM_BUG_ON(page_count(page)); + VM_BUG_ON_PAGE(page_count(page), page); enqueue_huge_page(h, page); } free: spin_unlock(&hugetlb_lock); /* Free unnecessary surplus pages to the buddy allocator */ - if (!list_empty(&surplus_list)) { - list_for_each_entry_safe(page, tmp, &surplus_list, lru) { - put_page(page); - } - } + list_for_each_entry_safe(page, tmp, &surplus_list, lru) + put_page(page); spin_lock(&hugetlb_lock); return ret; @@ -1043,7 +1296,7 @@ static void return_unused_surplus_pages(struct hstate *h, h->resv_huge_pages -= unused_resv_pages; /* Cannot return gigantic pages currently */ - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return; nr_pages = min(unused_resv_pages, h->surplus_huge_pages); @@ -1059,6 +1312,7 @@ static void return_unused_surplus_pages(struct hstate *h, while (nr_pages--) { if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) break; + cond_resched_lock(&hugetlb_lock); } } @@ -1075,45 +1329,34 @@ static void return_unused_surplus_pages(struct hstate *h, static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; - - if (vma->vm_flags & VM_MAYSHARE) { - pgoff_t idx = vma_hugecache_offset(h, vma, addr); - return region_chg(&inode->i_mapping->private_list, - idx, idx + 1); + struct resv_map *resv; + pgoff_t idx; + long chg; - } else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv = vma_resv_map(vma); + if (!resv) return 1; - } else { - long err; - pgoff_t idx = vma_hugecache_offset(h, vma, addr); - struct resv_map *reservations = vma_resv_map(vma); + idx = vma_hugecache_offset(h, vma, addr); + chg = region_chg(resv, idx, idx + 1); - err = region_chg(&reservations->regions, idx, idx + 1); - if (err < 0) - return err; - return 0; - } + if (vma->vm_flags & VM_MAYSHARE) + return chg; + else + return chg < 0 ? chg : 0; } static void vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; - - if (vma->vm_flags & VM_MAYSHARE) { - pgoff_t idx = vma_hugecache_offset(h, vma, addr); - region_add(&inode->i_mapping->private_list, idx, idx + 1); + struct resv_map *resv; + pgoff_t idx; - } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { - pgoff_t idx = vma_hugecache_offset(h, vma, addr); - struct resv_map *reservations = vma_resv_map(vma); + resv = vma_resv_map(vma); + if (!resv) + return; - /* Mark this page used in the map. */ - region_add(&reservations->regions, idx, idx + 1); - } + idx = vma_hugecache_offset(h, vma, addr); + region_add(resv, idx, idx + 1); } static struct page *alloc_huge_page(struct vm_area_struct *vma, @@ -1138,58 +1381,67 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, chg = vma_needs_reservation(h, vma, addr); if (chg < 0) return ERR_PTR(-ENOMEM); - if (chg) - if (hugepage_subpool_get_pages(spool, chg)) + if (chg || avoid_reserve) + if (hugepage_subpool_get_pages(spool, 1)) return ERR_PTR(-ENOSPC); ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); - if (ret) { - hugepage_subpool_put_pages(spool, chg); - return ERR_PTR(-ENOSPC); - } + if (ret) + goto out_subpool_put; + spin_lock(&hugetlb_lock); - page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); - if (page) { - /* update page cgroup details */ - hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), - h_cg, page); - spin_unlock(&hugetlb_lock); - } else { + page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg); + if (!page) { spin_unlock(&hugetlb_lock); page = alloc_buddy_huge_page(h, NUMA_NO_NODE); - if (!page) { - hugetlb_cgroup_uncharge_cgroup(idx, - pages_per_huge_page(h), - h_cg); - hugepage_subpool_put_pages(spool, chg); - return ERR_PTR(-ENOSPC); - } + if (!page) + goto out_uncharge_cgroup; + spin_lock(&hugetlb_lock); - hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), - h_cg, page); list_move(&page->lru, &h->hugepage_activelist); - spin_unlock(&hugetlb_lock); + /* Fall through */ } + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); + spin_unlock(&hugetlb_lock); set_page_private(page, (unsigned long)spool); vma_commit_reservation(h, vma, addr); return page; + +out_uncharge_cgroup: + hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); +out_subpool_put: + if (chg || avoid_reserve) + hugepage_subpool_put_pages(spool, 1); + return ERR_PTR(-ENOSPC); +} + +/* + * alloc_huge_page()'s wrapper which simply returns the page if allocation + * succeeds, otherwise NULL. This function is called from new_vma_page(), + * where no ERR_VALUE is expected to be returned. + */ +struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve) +{ + struct page *page = alloc_huge_page(vma, addr, avoid_reserve); + if (IS_ERR(page)) + page = NULL; + return page; } int __weak alloc_bootmem_huge_page(struct hstate *h) { struct huge_bootmem_page *m; - int nr_nodes = nodes_weight(node_states[N_MEMORY]); + int nr_nodes, node; - while (nr_nodes) { + for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { void *addr; - addr = __alloc_bootmem_node_nopanic( - NODE_DATA(hstate_next_node_to_alloc(h, - &node_states[N_MEMORY])), - huge_page_size(h), huge_page_size(h), 0); - + addr = memblock_virt_alloc_try_nid_nopanic( + huge_page_size(h), huge_page_size(h), + 0, BOOTMEM_ALLOC_ACCESSIBLE, node); if (addr) { /* * Use the beginning of the huge page to store the @@ -1199,7 +1451,6 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) m = addr; goto found; } - nr_nodes--; } return 0; @@ -1211,7 +1462,7 @@ found: return 1; } -static void prep_compound_huge_page(struct page *page, int order) +static void __init prep_compound_huge_page(struct page *page, int order) { if (unlikely(order > (MAX_ORDER - 1))) prep_compound_gigantic_page(page, order); @@ -1230,14 +1481,14 @@ static void __init gather_bootmem_prealloc(void) #ifdef CONFIG_HIGHMEM page = pfn_to_page(m->phys >> PAGE_SHIFT); - free_bootmem_late((unsigned long)m, - sizeof(struct huge_bootmem_page)); + memblock_free_late(__pa(m), + sizeof(struct huge_bootmem_page)); #else page = virt_to_page(m); #endif - __ClearPageReserved(page); WARN_ON(page_count(page) != 1); prep_compound_huge_page(page, h->order); + WARN_ON(PageReserved(page)); prep_new_huge_page(h, page, page_to_nid(page)); /* * If we had gigantic hugepages allocated at boot time, we need @@ -1245,8 +1496,8 @@ static void __init gather_bootmem_prealloc(void) * fix confusing memory reports from free(1) and another * side-effects, like CommitLimit going negative. */ - if (h->order > (MAX_ORDER - 1)) - totalram_pages += 1 << h->order; + if (hstate_is_gigantic(h)) + adjust_managed_page_count(page, 1 << h->order); } } @@ -1255,7 +1506,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { - if (h->order >= MAX_ORDER) { + if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h)) break; } else if (!alloc_fresh_huge_page(h, @@ -1271,7 +1522,7 @@ static void __init hugetlb_init_hstates(void) for_each_hstate(h) { /* oversize hugepages were init'ed in early boot */ - if (h->order < MAX_ORDER) + if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } } @@ -1293,8 +1544,7 @@ static void __init report_hugepages(void) for_each_hstate(h) { char buf[32]; - printk(KERN_INFO "HugeTLB registered %s page size, " - "pre-allocated %ld pages\n", + pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n", memfmt(buf, huge_page_size(h)), h->free_huge_pages); } @@ -1306,7 +1556,7 @@ static void try_to_free_low(struct hstate *h, unsigned long count, { int i; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return; for_each_node_mask(i, *nodes_allowed) { @@ -1339,48 +1589,28 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count, static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { - int start_nid, next_nid; - int ret = 0; + int nr_nodes, node; VM_BUG_ON(delta != -1 && delta != 1); - if (delta < 0) - start_nid = hstate_next_node_to_alloc(h, nodes_allowed); - else - start_nid = hstate_next_node_to_free(h, nodes_allowed); - next_nid = start_nid; - - do { - int nid = next_nid; - if (delta < 0) { - /* - * To shrink on this node, there must be a surplus page - */ - if (!h->surplus_huge_pages_node[nid]) { - next_nid = hstate_next_node_to_alloc(h, - nodes_allowed); - continue; - } + if (delta < 0) { + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + if (h->surplus_huge_pages_node[node]) + goto found; } - if (delta > 0) { - /* - * Surplus cannot exceed the total number of pages - */ - if (h->surplus_huge_pages_node[nid] >= - h->nr_huge_pages_node[nid]) { - next_nid = hstate_next_node_to_free(h, - nodes_allowed); - continue; - } + } else { + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { + if (h->surplus_huge_pages_node[node] < + h->nr_huge_pages_node[node]) + goto found; } + } + return 0; - h->surplus_huge_pages += delta; - h->surplus_huge_pages_node[nid] += delta; - ret = 1; - break; - } while (next_nid != start_nid); - - return ret; +found: + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[node] += delta; + return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) @@ -1389,7 +1619,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, { unsigned long min_count, ret; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h) && !gigantic_page_supported()) return h->max_huge_pages; /* @@ -1416,7 +1646,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, * and reducing the surplus. */ spin_unlock(&hugetlb_lock); - ret = alloc_fresh_huge_page(h, nodes_allowed); + if (hstate_is_gigantic(h)) + ret = alloc_fresh_gigantic_page(h, nodes_allowed); + else + ret = alloc_fresh_huge_page(h, nodes_allowed); spin_lock(&hugetlb_lock); if (!ret) goto out; @@ -1447,6 +1680,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, while (min_count < persistent_huge_pages(h)) { if (!free_pool_huge_page(h, nodes_allowed, 0)) break; + cond_resched_lock(&hugetlb_lock); } while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) @@ -1510,12 +1744,12 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h; NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY); - err = strict_strtoul(buf, 10, &count); + err = kstrtoul(buf, 10, &count); if (err) goto out; h = kobj_to_hstate(kobj, &nid); - if (h->order >= MAX_ORDER) { + if (hstate_is_gigantic(h) && !gigantic_page_supported()) { err = -EINVAL; goto out; } @@ -1598,10 +1832,10 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return -EINVAL; - err = strict_strtoul(buf, 10, &input); + err = kstrtoul(buf, 10, &input); if (err) return err; @@ -1702,8 +1936,7 @@ static void __init hugetlb_sysfs_init(void) err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) - printk(KERN_ERR "Hugetlb: Unable to add hstate %s", - h->name); + pr_err("Hugetlb: Unable to add hstate %s", h->name); } } @@ -1763,7 +1996,7 @@ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ -void hugetlb_unregister_node(struct node *node) +static void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; @@ -1807,7 +2040,7 @@ static void hugetlb_unregister_all_nodes(void) * Register hstate attributes for a single node device. * No-op if attributes already registered. */ -void hugetlb_register_node(struct node *node) +static void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; @@ -1826,9 +2059,8 @@ void hugetlb_register_node(struct node *node) nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { - printk(KERN_ERR "Hugetlb: Unable to add hstate %s" - " for node %d\n", - h->name, node->dev.id); + pr_err("Hugetlb: Unable to add hstate %s for node %d\n", + h->name, node->dev.id); hugetlb_unregister_node(node); break; } @@ -1884,16 +2116,15 @@ static void __exit hugetlb_exit(void) } kobject_put(hugepages_kobj); + kfree(htlb_fault_mutex_table); } module_exit(hugetlb_exit); static int __init hugetlb_init(void) { - /* Some platform decide whether they support huge pages at boot - * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when - * there is no such support - */ - if (HPAGE_SHIFT == 0) + int i; + + if (!hugepages_supported()) return 0; if (!size_to_hstate(default_hstate_size)) { @@ -1913,6 +2144,17 @@ static int __init hugetlb_init(void) hugetlb_register_all_nodes(); hugetlb_cgroup_file_init(); +#ifdef CONFIG_SMP + num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); +#else + num_fault_mutexes = 1; +#endif + htlb_fault_mutex_table = + kmalloc(sizeof(struct mutex) * num_fault_mutexes, GFP_KERNEL); + BUG_ON(!htlb_fault_mutex_table); + + for (i = 0; i < num_fault_mutexes; i++) + mutex_init(&htlb_fault_mutex_table[i]); return 0; } module_init(hugetlb_init); @@ -1924,7 +2166,7 @@ void __init hugetlb_add_hstate(unsigned order) unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { - printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); + pr_warning("hugepagesz= specified twice, ignoring\n"); return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); @@ -1960,8 +2202,8 @@ static int __init hugetlb_nrpages_setup(char *s) mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { - printk(KERN_WARNING "hugepages= specified twice without " - "interleaving hugepagesz=, ignoring\n"); + pr_warning("hugepages= specified twice without " + "interleaving hugepagesz=, ignoring\n"); return 1; } @@ -2009,9 +2251,12 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->max_huge_pages; - if (write && h->order >= MAX_ORDER) + if (write && hstate_is_gigantic(h) && !gigantic_page_supported()) return -EINVAL; table->data = &tmp; @@ -2054,18 +2299,6 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, } #endif /* CONFIG_NUMA */ -int hugetlb_treat_movable_handler(struct ctl_table *table, int write, - void __user *buffer, - size_t *length, loff_t *ppos) -{ - proc_dointvec(table, write, buffer, length, ppos); - if (hugepages_treat_as_movable) - htlb_alloc_mask = GFP_HIGHUSER_MOVABLE; - else - htlb_alloc_mask = GFP_HIGHUSER; - return 0; -} - int hugetlb_overcommit_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) @@ -2074,9 +2307,12 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->nr_overcommit_huge_pages; - if (write && h->order >= MAX_ORDER) + if (write && hstate_is_gigantic(h)) return -EINVAL; table->data = &tmp; @@ -2099,6 +2335,8 @@ out: void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return; seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" @@ -2115,6 +2353,8 @@ void hugetlb_report_meminfo(struct seq_file *m) int hugetlb_report_node_meminfo(int nid, char *buf) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return 0; return sprintf(buf, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" @@ -2124,11 +2364,33 @@ int hugetlb_report_node_meminfo(int nid, char *buf) nid, h->surplus_huge_pages_node[nid]); } +void hugetlb_show_meminfo(void) +{ + struct hstate *h; + int nid; + + if (!hugepages_supported()) + return; + + for_each_node_state(nid, N_MEMORY) + for_each_hstate(h) + pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", + nid, + h->nr_huge_pages_node[nid], + h->free_huge_pages_node[nid], + h->surplus_huge_pages_node[nid], + 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); +} + /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { - struct hstate *h = &default_hstate; - return h->nr_huge_pages * pages_per_huge_page(h); + struct hstate *h; + unsigned long nr_total_pages = 0; + + for_each_hstate(h) + nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); + return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) @@ -2174,7 +2436,7 @@ out: static void hugetlb_vm_op_open(struct vm_area_struct *vma) { - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); /* * This new VMA should share its siblings reservation map if present. @@ -2184,41 +2446,30 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ - if (reservations) - kref_get(&reservations->refs); -} - -static void resv_map_put(struct vm_area_struct *vma) -{ - struct resv_map *reservations = vma_resv_map(vma); - - if (!reservations) - return; - kref_put(&reservations->refs, resv_map_release); + if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + kref_get(&resv->refs); } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); struct hugepage_subpool *spool = subpool_vma(vma); - unsigned long reserve; - unsigned long start; - unsigned long end; + unsigned long reserve, start, end; - if (reservations) { - start = vma_hugecache_offset(h, vma, vma->vm_start); - end = vma_hugecache_offset(h, vma, vma->vm_end); + if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + return; - reserve = (end - start) - - region_count(&reservations->regions, start, end); + start = vma_hugecache_offset(h, vma, vma->vm_start); + end = vma_hugecache_offset(h, vma, vma->vm_end); - resv_map_put(vma); + reserve = (end - start) - region_count(resv, start, end); - if (reserve) { - hugetlb_acct_memory(h, -reserve); - hugepage_subpool_put_pages(spool, reserve); - } + kref_put(&resv->refs, resv_map_release); + + if (reserve) { + hugetlb_acct_memory(h, -reserve); + hugepage_subpool_put_pages(spool, reserve); } } @@ -2246,10 +2497,11 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, pte_t entry; if (writable) { - entry = - pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot))); + entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, + vma->vm_page_prot))); } else { - entry = huge_pte_wrprotect(mk_pte(page, vma->vm_page_prot)); + entry = huge_pte_wrprotect(mk_huge_pte(page, + vma->vm_page_prot)); } entry = pte_mkyoung(entry); entry = pte_mkhuge(entry); @@ -2263,11 +2515,36 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma, { pte_t entry; - entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep))); + entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } +static int is_hugetlb_entry_migration(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return 0; + swp = pte_to_swp_entry(pte); + if (non_swap_entry(swp) && is_migration_entry(swp)) + return 1; + else + return 0; +} + +static int is_hugetlb_entry_hwpoisoned(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return 0; + swp = pte_to_swp_entry(pte); + if (non_swap_entry(swp) && is_hwpoison_entry(swp)) + return 1; + else + return 0; +} int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) @@ -2278,24 +2555,53 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, int cow; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); + unsigned long mmun_start; /* For mmu_notifiers */ + unsigned long mmun_end; /* For mmu_notifiers */ + int ret = 0; cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; + mmun_start = vma->vm_start; + mmun_end = vma->vm_end; + if (cow) + mmu_notifier_invalidate_range_start(src, mmun_start, mmun_end); + for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { + spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr); if (!src_pte) continue; dst_pte = huge_pte_alloc(dst, addr, sz); - if (!dst_pte) - goto nomem; + if (!dst_pte) { + ret = -ENOMEM; + break; + } /* If the pagetables are shared don't copy or take references */ if (dst_pte == src_pte) continue; - spin_lock(&dst->page_table_lock); - spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING); - if (!huge_pte_none(huge_ptep_get(src_pte))) { + dst_ptl = huge_pte_lock(h, dst, dst_pte); + src_ptl = huge_pte_lockptr(h, src, src_pte); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + entry = huge_ptep_get(src_pte); + if (huge_pte_none(entry)) { /* skip none entry */ + ; + } else if (unlikely(is_hugetlb_entry_migration(entry) || + is_hugetlb_entry_hwpoisoned(entry))) { + swp_entry_t swp_entry = pte_to_swp_entry(entry); + + if (is_write_migration_entry(swp_entry) && cow) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&swp_entry); + entry = swp_entry_to_pte(swp_entry); + set_huge_pte_at(src, addr, src_pte, entry); + } + set_huge_pte_at(dst, addr, dst_pte, entry); + } else { if (cow) huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_ptep_get(src_pte); @@ -2304,39 +2610,14 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, page_dup_rmap(ptepage); set_huge_pte_at(dst, addr, dst_pte, entry); } - spin_unlock(&src->page_table_lock); - spin_unlock(&dst->page_table_lock); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); } - return 0; - -nomem: - return -ENOMEM; -} - -static int is_hugetlb_entry_migration(pte_t pte) -{ - swp_entry_t swp; - - if (huge_pte_none(pte) || pte_present(pte)) - return 0; - swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_migration_entry(swp)) - return 1; - else - return 0; -} -static int is_hugetlb_entry_hwpoisoned(pte_t pte) -{ - swp_entry_t swp; + if (cow) + mmu_notifier_invalidate_range_end(src, mmun_start, mmun_end); - if (huge_pte_none(pte) || pte_present(pte)) - return 0; - swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_hwpoison_entry(swp)) - return 1; - else - return 0; + return ret; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, @@ -2348,6 +2629,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long address; pte_t *ptep; pte_t pte; + spinlock_t *ptl; struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); @@ -2361,25 +2643,25 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb_start_vma(tlb, vma); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); again: - spin_lock(&mm->page_table_lock); for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; + ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) - continue; + goto unlock; pte = huge_ptep_get(ptep); if (huge_pte_none(pte)) - continue; + goto unlock; /* * HWPoisoned hugepage is already unmapped and dropped reference */ if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { - pte_clear(mm, address, ptep); - continue; + huge_pte_clear(mm, address, ptep); + goto unlock; } page = pte_page(pte); @@ -2390,7 +2672,7 @@ again: */ if (ref_page) { if (page != ref_page) - continue; + goto unlock; /* * Mark the VMA as having unmapped its page so that @@ -2402,18 +2684,23 @@ again: pte = huge_ptep_get_and_clear(mm, address, ptep); tlb_remove_tlb_entry(tlb, ptep, address); - if (pte_dirty(pte)) + if (huge_pte_dirty(pte)) set_page_dirty(page); page_remove_rmap(page); force_flush = !__tlb_remove_page(tlb, page); - if (force_flush) + if (force_flush) { + spin_unlock(ptl); break; + } /* Bail out after unmapping reference page if supplied */ - if (ref_page) + if (ref_page) { + spin_unlock(ptl); break; + } +unlock: + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); /* * mmu_gather ran out of room to batch pages, we break out of * the PTE lock to avoid doing the potential expensive TLB invalidate @@ -2456,7 +2743,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, mm = vma->vm_mm; - tlb_gather_mmu(&tlb, mm, 0); + tlb_gather_mmu(&tlb, mm, start, end); __unmap_hugepage_range(&tlb, vma, start, end, ref_page); tlb_finish_mmu(&tlb, start, end); } @@ -2482,7 +2769,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - mapping = vma->vm_file->f_dentry->d_inode->i_mapping; + mapping = file_inode(vma->vm_file)->i_mapping; /* * Take the mapping lock for the duration of the table walk. As @@ -2519,11 +2806,10 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, */ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t pte, - struct page *pagecache_page) + struct page *pagecache_page, spinlock_t *ptl) { struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; - int avoidcopy; int outside_reserve = 0; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ @@ -2533,10 +2819,8 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ - avoidcopy = (page_mapcount(old_page) == 1); - if (avoidcopy) { - if (PageAnon(old_page)) - page_move_anon_rmap(old_page, vma, address); + if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { + page_move_anon_rmap(old_page, vma, address); set_huge_ptep_writable(vma, address, ptep); return 0; } @@ -2550,15 +2834,14 @@ retry_avoidcopy: * at the time of fork() could consume its reserves on COW instead * of the full address range. */ - if (!(vma->vm_flags & VM_MAYSHARE) && - is_vma_resv_set(vma, HPAGE_RESV_OWNER) && + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_page != pagecache_page) outside_reserve = 1; page_cache_get(old_page); - /* Drop page_table_lock as buddy allocator may be called */ - spin_unlock(&mm->page_table_lock); + /* Drop page table lock as buddy allocator may be called */ + spin_unlock(ptl); new_page = alloc_huge_page(vma, address, outside_reserve); if (IS_ERR(new_page)) { @@ -2576,13 +2859,14 @@ retry_avoidcopy: BUG_ON(huge_pte_none(pte)); if (unmap_ref_private(mm, vma, old_page, address)) { BUG_ON(huge_pte_none(pte)); - spin_lock(&mm->page_table_lock); + spin_lock(ptl); ptep = huge_pte_offset(mm, address & huge_page_mask(h)); - if (likely(pte_same(huge_ptep_get(ptep), pte))) + if (likely(ptep && + pte_same(huge_ptep_get(ptep), pte))) goto retry_avoidcopy; /* - * race occurs while re-acquiring page_table_lock, and - * our job is done. + * race occurs while re-acquiring page table + * lock, and our job is done. */ return 0; } @@ -2590,7 +2874,7 @@ retry_avoidcopy: } /* Caller expects lock to be held */ - spin_lock(&mm->page_table_lock); + spin_lock(ptl); if (err == -ENOMEM) return VM_FAULT_OOM; else @@ -2605,7 +2889,7 @@ retry_avoidcopy: page_cache_release(new_page); page_cache_release(old_page); /* Caller expects lock to be held */ - spin_lock(&mm->page_table_lock); + spin_lock(ptl); return VM_FAULT_OOM; } @@ -2617,12 +2901,14 @@ retry_avoidcopy: mmun_end = mmun_start + huge_page_size(h); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); /* - * Retake the page_table_lock to check for racing updates + * Retake the page table lock to check for racing updates * before the page tables are altered */ - spin_lock(&mm->page_table_lock); + spin_lock(ptl); ptep = huge_pte_offset(mm, address & huge_page_mask(h)); - if (likely(pte_same(huge_ptep_get(ptep), pte))) { + if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { + ClearPagePrivate(new_page); + /* Break COW */ huge_ptep_clear_flush(vma, address, ptep); set_huge_pte_at(mm, address, ptep, @@ -2632,12 +2918,13 @@ retry_avoidcopy: /* Make the old page be freed below */ new_page = old_page; } - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - /* Caller expects lock to be held */ - spin_lock(&mm->page_table_lock); page_cache_release(new_page); page_cache_release(old_page); + + /* Caller expects lock to be held */ + spin_lock(ptl); return 0; } @@ -2675,16 +2962,16 @@ static bool hugetlbfs_pagecache_present(struct hstate *h, } static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, unsigned int flags) + struct address_space *mapping, pgoff_t idx, + unsigned long address, pte_t *ptep, unsigned int flags) { struct hstate *h = hstate_vma(vma); int ret = VM_FAULT_SIGBUS; int anon_rmap = 0; - pgoff_t idx; unsigned long size; struct page *page; - struct address_space *mapping; pte_t new_pte; + spinlock_t *ptl; /* * Currently, we are forced to kill the process in the event the @@ -2692,15 +2979,11 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, * COW. Warn that such a situation has occurred as it may not be obvious */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { - printk(KERN_WARNING - "PID %d killed due to inadequate hugepage pool\n", - current->pid); + pr_warning("PID %d killed due to inadequate hugepage pool\n", + current->pid); return ret; } - mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, vma, address); - /* * Use page lock to guard against racing truncation * before we get page_table_lock. @@ -2734,6 +3017,7 @@ retry: goto retry; goto out; } + ClearPagePrivate(page); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); @@ -2771,7 +3055,8 @@ retry: goto backout_unlocked; } - spin_lock(&mm->page_table_lock); + ptl = huge_pte_lockptr(h, mm, ptep); + spin_lock(ptl); size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto backout; @@ -2780,9 +3065,10 @@ retry: if (!huge_pte_none(huge_ptep_get(ptep))) goto backout; - if (anon_rmap) + if (anon_rmap) { + ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, vma, address); - else + } else page_dup_rmap(page); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); @@ -2790,32 +3076,69 @@ retry: if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page); + ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl); } - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); unlock_page(page); out: return ret; backout: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); backout_unlocked: unlock_page(page); put_page(page); goto out; } +#ifdef CONFIG_SMP +static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, unsigned long address) +{ + unsigned long key[2]; + u32 hash; + + if (vma->vm_flags & VM_SHARED) { + key[0] = (unsigned long) mapping; + key[1] = idx; + } else { + key[0] = (unsigned long) mm; + key[1] = address >> huge_page_shift(h); + } + + hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0); + + return hash & (num_fault_mutexes - 1); +} +#else +/* + * For uniprocesor systems we always use a single mutex, so just + * return 0 and avoid the hashing overhead. + */ +static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, unsigned long address) +{ + return 0; +} +#endif + int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { - pte_t *ptep; - pte_t entry; + pte_t *ptep, entry; + spinlock_t *ptl; int ret; + u32 hash; + pgoff_t idx; struct page *page = NULL; struct page *pagecache_page = NULL; - static DEFINE_MUTEX(hugetlb_instantiation_mutex); struct hstate *h = hstate_vma(vma); + struct address_space *mapping; address &= huge_page_mask(h); @@ -2823,7 +3146,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (ptep) { entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait(mm, (pmd_t *)ptep, address); + migration_entry_wait_huge(vma, mm, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | @@ -2834,15 +3157,20 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (!ptep) return VM_FAULT_OOM; + mapping = vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, vma, address); + /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - mutex_lock(&hugetlb_instantiation_mutex); + hash = fault_mutex_hash(h, mm, vma, mapping, idx, address); + mutex_lock(&htlb_fault_mutex_table[hash]); + entry = huge_ptep_get(ptep); if (huge_pte_none(entry)) { - ret = hugetlb_no_page(mm, vma, address, ptep, flags); + ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); goto out_mutex; } @@ -2856,7 +3184,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * page now as it is used to determine if a reservation has been * consumed. */ - if ((flags & FAULT_FLAG_WRITE) && !pte_write(entry)) { + if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; @@ -2879,27 +3207,28 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (page != pagecache_page) lock_page(page); - spin_lock(&mm->page_table_lock); + ptl = huge_pte_lockptr(h, mm, ptep); + spin_lock(ptl); /* Check for a racing update before calling hugetlb_cow */ if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) - goto out_page_table_lock; + goto out_ptl; if (flags & FAULT_FLAG_WRITE) { - if (!pte_write(entry)) { + if (!huge_pte_write(entry)) { ret = hugetlb_cow(mm, vma, address, ptep, entry, - pagecache_page); - goto out_page_table_lock; + pagecache_page, ptl); + goto out_ptl; } - entry = pte_mkdirty(entry); + entry = huge_pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (huge_ptep_set_access_flags(vma, address, ptep, entry, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, address, ptep); -out_page_table_lock: - spin_unlock(&mm->page_table_lock); +out_ptl: + spin_unlock(ptl); if (pagecache_page) { unlock_page(pagecache_page); @@ -2910,33 +3239,23 @@ out_page_table_lock: put_page(page); out_mutex: - mutex_unlock(&hugetlb_instantiation_mutex); - + mutex_unlock(&htlb_fault_mutex_table[hash]); return ret; } -/* Can be overriden by architectures */ -__attribute__((weak)) struct page * -follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) -{ - BUG(); - return NULL; -} - -int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, - struct page **pages, struct vm_area_struct **vmas, - unsigned long *position, int *length, int i, - unsigned int flags) +long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, + struct page **pages, struct vm_area_struct **vmas, + unsigned long *position, unsigned long *nr_pages, + long i, unsigned int flags) { unsigned long pfn_offset; unsigned long vaddr = *position; - int remainder = *length; + unsigned long remainder = *nr_pages; struct hstate *h = hstate_vma(vma); - spin_lock(&mm->page_table_lock); while (vaddr < vma->vm_end && remainder) { pte_t *pte; + spinlock_t *ptl = NULL; int absent; struct page *page; @@ -2944,8 +3263,12 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * Some archs (sparc64, sh*) have multiple pte_ts to * each hugepage. We have to make sure we get the * first, for the page indexing below to work. + * + * Note that page table lock is not held when pte is null. */ pte = huge_pte_offset(mm, vaddr & huge_page_mask(h)); + if (pte) + ptl = huge_pte_lock(h, mm, pte); absent = !pte || huge_pte_none(huge_ptep_get(pte)); /* @@ -2957,18 +3280,31 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, */ if (absent && (flags & FOLL_DUMP) && !hugetlbfs_pagecache_present(h, vma, vaddr)) { + if (pte) + spin_unlock(ptl); remainder = 0; break; } - if (absent || - ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) { + /* + * We need call hugetlb_fault for both hugepages under migration + * (in which case hugetlb_fault waits for the migration,) and + * hwpoisoned hugepages (in which case we need to prevent the + * caller from accessing to them.) In order to do this, we use + * here is_swap_pte instead of is_hugetlb_entry_migration and + * is_hugetlb_entry_hwpoisoned. This is because it simply covers + * both cases, and because we can't follow correct pages + * directly from any kind of swap entries. + */ + if (absent || is_swap_pte(huge_ptep_get(pte)) || + ((flags & FOLL_WRITE) && + !huge_pte_write(huge_ptep_get(pte)))) { int ret; - spin_unlock(&mm->page_table_lock); + if (pte) + spin_unlock(ptl); ret = hugetlb_fault(mm, vma, vaddr, (flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0); - spin_lock(&mm->page_table_lock); if (!(ret & VM_FAULT_ERROR)) continue; @@ -2981,7 +3317,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); - get_page(pages[i]); + get_page_foll(pages[i]); } if (vmas) @@ -2999,9 +3335,9 @@ same_page: */ goto same_page; } + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); - *length = remainder; + *nr_pages = remainder; *position = vaddr; return i ? i : -EFAULT; @@ -3020,24 +3356,28 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, address, end); + mmu_notifier_invalidate_range_start(mm, start, end); mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); - spin_lock(&mm->page_table_lock); for (; address < end; address += huge_page_size(h)) { + spinlock_t *ptl; ptep = huge_pte_offset(mm, address); if (!ptep) continue; + ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) { pages++; + spin_unlock(ptl); continue; } if (!huge_pte_none(huge_ptep_get(ptep))) { pte = huge_ptep_get_and_clear(mm, address, ptep); - pte = pte_mkhuge(pte_modify(pte, newprot)); + pte = pte_mkhuge(huge_pte_modify(pte, newprot)); + pte = arch_make_huge_pte(pte, vma, NULL, 0); set_huge_pte_at(mm, address, ptep, pte); pages++; } + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); /* * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: @@ -3046,6 +3386,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, */ flush_tlb_range(vma, start, end); mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + mmu_notifier_invalidate_range_end(mm, start, end); return pages << h->order; } @@ -3058,6 +3399,7 @@ int hugetlb_reserve_pages(struct inode *inode, long ret, chg; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); + struct resv_map *resv_map; /* * Only apply hugepage reservation if asked. At fault time, an @@ -3073,10 +3415,13 @@ int hugetlb_reserve_pages(struct inode *inode, * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ - if (!vma || vma->vm_flags & VM_MAYSHARE) - chg = region_chg(&inode->i_mapping->private_list, from, to); - else { - struct resv_map *resv_map = resv_map_alloc(); + if (!vma || vma->vm_flags & VM_MAYSHARE) { + resv_map = inode_resv_map(inode); + + chg = region_chg(resv_map, from, to); + + } else { + resv_map = resv_map_alloc(); if (!resv_map) return -ENOMEM; @@ -3119,20 +3464,23 @@ int hugetlb_reserve_pages(struct inode *inode, * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) - region_add(&inode->i_mapping->private_list, from, to); + region_add(resv_map, from, to); return 0; out_err: - if (vma) - resv_map_put(vma); + if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + kref_put(&resv_map->refs, resv_map_release); return ret; } void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) { struct hstate *h = hstate_inode(inode); - long chg = region_truncate(&inode->i_mapping->private_list, offset); + struct resv_map *resv_map = inode_resv_map(inode); + long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); + if (resv_map) + chg = region_truncate(resv_map, offset); spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); @@ -3141,6 +3489,218 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) hugetlb_acct_memory(h, -(chg - freed)); } +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static unsigned long page_table_shareable(struct vm_area_struct *svma, + struct vm_area_struct *vma, + unsigned long addr, pgoff_t idx) +{ + unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + + svma->vm_start; + unsigned long sbase = saddr & PUD_MASK; + unsigned long s_end = sbase + PUD_SIZE; + + /* Allow segments to share if only one is marked locked */ + unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED; + unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED; + + /* + * match the virtual addresses, permission and the alignment of the + * page table page. + */ + if (pmd_index(addr) != pmd_index(saddr) || + vm_flags != svm_flags || + sbase < svma->vm_start || svma->vm_end < s_end) + return 0; + + return saddr; +} + +static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) +{ + unsigned long base = addr & PUD_MASK; + unsigned long end = base + PUD_SIZE; + + /* + * check on proper vm_flags and page table alignment + */ + if (vma->vm_flags & VM_MAYSHARE && + vma->vm_start <= base && end <= vma->vm_end) + return 1; + return 0; +} + +/* + * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() + * and returns the corresponding pte. While this is not necessary for the + * !shared pmd case because we can allocate the pmd later as well, it makes the + * code much cleaner. pmd allocation is essential for the shared case because + * pud has to be populated inside the same i_mmap_mutex section - otherwise + * racing tasks could either miss the sharing (see huge_pte_offset) or select a + * bad pmd for sharing. + */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + struct vm_area_struct *vma = find_vma(mm, addr); + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff; + struct vm_area_struct *svma; + unsigned long saddr; + pte_t *spte = NULL; + pte_t *pte; + spinlock_t *ptl; + + if (!vma_shareable(vma, addr)) + return (pte_t *)pmd_alloc(mm, pud, addr); + + mutex_lock(&mapping->i_mmap_mutex); + vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { + if (svma == vma) + continue; + + saddr = page_table_shareable(svma, vma, addr, idx); + if (saddr) { + spte = huge_pte_offset(svma->vm_mm, saddr); + if (spte) { + get_page(virt_to_page(spte)); + break; + } + } + } + + if (!spte) + goto out; + + ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte); + spin_lock(ptl); + if (pud_none(*pud)) + pud_populate(mm, pud, + (pmd_t *)((unsigned long)spte & PAGE_MASK)); + else + put_page(virt_to_page(spte)); + spin_unlock(ptl); +out: + pte = (pte_t *)pmd_alloc(mm, pud, addr); + mutex_unlock(&mapping->i_mmap_mutex); + return pte; +} + +/* + * unmap huge page backed by shared pte. + * + * Hugetlb pte page is ref counted at the time of mapping. If pte is shared + * indicated by page_count > 1, unmap is achieved by clearing pud and + * decrementing the ref count. If count == 1, the pte page is not shared. + * + * called with page table lock held. + * + * returns: 1 successfully unmapped a shared pte page + * 0 the underlying pte page is not shared, or it is the last user + */ +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + pgd_t *pgd = pgd_offset(mm, *addr); + pud_t *pud = pud_offset(pgd, *addr); + + BUG_ON(page_count(virt_to_page(ptep)) == 0); + if (page_count(virt_to_page(ptep)) == 1) + return 0; + + pud_clear(pud); + put_page(virt_to_page(ptep)); + *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; + return 1; +} +#define want_pmd_share() (1) +#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + return NULL; +} +#define want_pmd_share() (0) +#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ + +#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pte_t *pte = NULL; + + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (pud) { + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else { + BUG_ON(sz != PMD_SIZE); + if (want_pmd_share() && pud_none(*pud)) + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + } + } + BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); + + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd = NULL; + + pgd = pgd_offset(mm, addr); + if (pgd_present(*pgd)) { + pud = pud_offset(pgd, addr); + if (pud_present(*pud)) { + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); + } + } + return (pte_t *) pmd; +} + +struct page * +follow_huge_pmd(struct mm_struct *mm, unsigned long address, + pmd_t *pmd, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pmd); + if (page) + page += ((address & ~PMD_MASK) >> PAGE_SHIFT); + return page; +} + +struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pud); + if (page) + page += ((address & ~PUD_MASK) >> PAGE_SHIFT); + return page; +} + +#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */ + +/* Can be overriden by architectures */ +struct page * __weak +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + BUG(); + return NULL; +} + +#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ + #ifdef CONFIG_MEMORY_FAILURE /* Should be called in hugetlb_lock */ @@ -3185,3 +3745,45 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage) return ret; } #endif + +bool isolate_huge_page(struct page *page, struct list_head *list) +{ + VM_BUG_ON_PAGE(!PageHead(page), page); + if (!get_page_unless_zero(page)) + return false; + spin_lock(&hugetlb_lock); + list_move_tail(&page->lru, list); + spin_unlock(&hugetlb_lock); + return true; +} + +void putback_active_hugepage(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHead(page), page); + spin_lock(&hugetlb_lock); + list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); + spin_unlock(&hugetlb_lock); + put_page(page); +} + +bool is_hugepage_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHuge(page), page); + /* + * This function can be called for a tail page because the caller, + * scan_movable_pages, scans through a given pfn-range which typically + * covers one memory block. In systems using gigantic hugepage (1GB + * for x86_64,) a hugepage is larger than a memory block, and we don't + * support migrating such large hugepages for now, so return false + * when called for tail pages. + */ + if (PageTail(page)) + return false; + /* + * Refcount of a hwpoisoned hugepages is 1, but they are not active, + * so we should return false for them. + */ + if (unlikely(PageHWPoison(page))) + return false; + return page_count(page) > 0; +} diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 9cea7de22ff..493f758445e 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -30,27 +30,18 @@ struct hugetlb_cgroup { #define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) -struct cgroup_subsys hugetlb_subsys __read_mostly; static struct hugetlb_cgroup *root_h_cgroup __read_mostly; static inline struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) { - return container_of(s, struct hugetlb_cgroup, css); -} - -static inline -struct hugetlb_cgroup *hugetlb_cgroup_from_cgroup(struct cgroup *cgroup) -{ - return hugetlb_cgroup_from_css(cgroup_subsys_state(cgroup, - hugetlb_subsys_id)); + return s ? container_of(s, struct hugetlb_cgroup, css) : NULL; } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) { - return hugetlb_cgroup_from_css(task_subsys_state(task, - hugetlb_subsys_id)); + return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id)); } static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) @@ -58,17 +49,15 @@ static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) return (h_cg == root_h_cgroup); } -static inline struct hugetlb_cgroup *parent_hugetlb_cgroup(struct cgroup *cg) +static inline struct hugetlb_cgroup * +parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg) { - if (!cg->parent) - return NULL; - return hugetlb_cgroup_from_cgroup(cg->parent); + return hugetlb_cgroup_from_css(h_cg->css.parent); } -static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg) +static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) { int idx; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cg); for (idx = 0; idx < hugetlb_max_hstate; idx++) { if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0) @@ -77,19 +66,18 @@ static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg) return false; } -static struct cgroup_subsys_state *hugetlb_cgroup_css_alloc(struct cgroup *cgroup) +static struct cgroup_subsys_state * +hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { + struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); + struct hugetlb_cgroup *h_cgroup; int idx; - struct cgroup *parent_cgroup; - struct hugetlb_cgroup *h_cgroup, *parent_h_cgroup; h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); if (!h_cgroup) return ERR_PTR(-ENOMEM); - parent_cgroup = cgroup->parent; - if (parent_cgroup) { - parent_h_cgroup = hugetlb_cgroup_from_cgroup(parent_cgroup); + if (parent_h_cgroup) { for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) res_counter_init(&h_cgroup->hugepage[idx], &parent_h_cgroup->hugepage[idx]); @@ -101,11 +89,11 @@ static struct cgroup_subsys_state *hugetlb_cgroup_css_alloc(struct cgroup *cgrou return &h_cgroup->css; } -static void hugetlb_cgroup_css_free(struct cgroup *cgroup) +static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) { struct hugetlb_cgroup *h_cgroup; - h_cgroup = hugetlb_cgroup_from_cgroup(cgroup); + h_cgroup = hugetlb_cgroup_from_css(css); kfree(h_cgroup); } @@ -117,15 +105,14 @@ static void hugetlb_cgroup_css_free(struct cgroup *cgroup) * page reference and test for page active here. This function * cannot fail. */ -static void hugetlb_cgroup_move_parent(int idx, struct cgroup *cgroup, +static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, struct page *page) { int csize; struct res_counter *counter; struct res_counter *fail_res; struct hugetlb_cgroup *page_hcg; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); - struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(cgroup); + struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); page_hcg = hugetlb_cgroup_from_page(page); /* @@ -155,8 +142,9 @@ out: * Force the hugetlb cgroup to empty the hugetlb resources by moving them to * the parent cgroup. */ -static void hugetlb_cgroup_css_offline(struct cgroup *cgroup) +static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) { + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; struct page *page; int idx = 0; @@ -165,13 +153,13 @@ static void hugetlb_cgroup_css_offline(struct cgroup *cgroup) for_each_hstate(h) { spin_lock(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_activelist, lru) - hugetlb_cgroup_move_parent(idx, cgroup, page); + hugetlb_cgroup_move_parent(idx, h_cg, page); spin_unlock(&hugetlb_lock); idx++; } cond_resched(); - } while (hugetlb_cgroup_have_usage(cgroup)); + } while (hugetlb_cgroup_have_usage(h_cg)); } int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, @@ -193,7 +181,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); - if (!css_tryget(&h_cg->css)) { + if (!css_tryget_online(&h_cg->css)) { rcu_read_unlock(); goto again; } @@ -253,32 +241,28 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, return; } -static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft, - struct file *file, char __user *buf, - size_t nbytes, loff_t *ppos) +static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - u64 val; - char str[64]; - int idx, name, len; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + int idx, name; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); idx = MEMFILE_IDX(cft->private); name = MEMFILE_ATTR(cft->private); - val = res_counter_read_u64(&h_cg->hugepage[idx], name); - len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val); - return simple_read_from_buffer(buf, nbytes, ppos, str, len); + return res_counter_read_u64(&h_cg->hugepage[idx], name); } -static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft, - const char *buffer) +static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { int idx, name, ret; unsigned long long val; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); - idx = MEMFILE_IDX(cft->private); - name = MEMFILE_ATTR(cft->private); + buf = strstrip(buf); + idx = MEMFILE_IDX(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_LIMIT: @@ -288,7 +272,7 @@ static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft, break; } /* This function does all necessary parse...reuse it */ - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; ret = res_counter_set_limit(&h_cg->hugepage[idx], val); @@ -297,16 +281,17 @@ static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft, ret = -EINVAL; break; } - return ret; + return ret ?: nbytes; } -static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event) +static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { int idx, name, ret = 0; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); - idx = MEMFILE_IDX(event); - name = MEMFILE_ATTR(event); + idx = MEMFILE_IDX(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_MAX_USAGE: @@ -319,7 +304,7 @@ static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event) ret = -EINVAL; break; } - return ret; + return ret ?: nbytes; } static char *mem_fmt(char *buf, int size, unsigned long hsize) @@ -346,34 +331,34 @@ static void __init __hugetlb_cgroup_file_init(int idx) cft = &h->cgroup_files[0]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); - cft->read = hugetlb_cgroup_read; - cft->write_string = hugetlb_cgroup_write; + cft->read_u64 = hugetlb_cgroup_read_u64; + cft->write = hugetlb_cgroup_write; /* Add the usage file */ cft = &h->cgroup_files[1]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); - cft->read = hugetlb_cgroup_read; + cft->read_u64 = hugetlb_cgroup_read_u64; /* Add the MAX usage file */ cft = &h->cgroup_files[2]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); - cft->trigger = hugetlb_cgroup_reset; - cft->read = hugetlb_cgroup_read; + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; /* Add the failcntfile */ cft = &h->cgroup_files[3]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); - cft->trigger = hugetlb_cgroup_reset; - cft->read = hugetlb_cgroup_read; + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; /* NULL terminate the last cft */ cft = &h->cgroup_files[4]; memset(cft, 0, sizeof(*cft)); - WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files)); + WARN_ON(cgroup_add_cftypes(&hugetlb_cgrp_subsys, h->cgroup_files)); return; } @@ -405,7 +390,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) if (hugetlb_cgroup_disabled()) return; - VM_BUG_ON(!PageHuge(oldhpage)); + VM_BUG_ON_PAGE(!PageHuge(oldhpage), oldhpage); spin_lock(&hugetlb_lock); h_cg = hugetlb_cgroup_from_page(oldhpage); set_hugetlb_cgroup(oldhpage, NULL); @@ -417,10 +402,8 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) return; } -struct cgroup_subsys hugetlb_subsys = { - .name = "hugetlb", +struct cgroup_subsys hugetlb_cgrp_subsys = { .css_alloc = hugetlb_cgroup_css_alloc, .css_offline = hugetlb_cgroup_css_offline, .css_free = hugetlb_cgroup_css_free, - .subsys_id = hugetlb_subsys_id, }; diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index 3a61efc518d..95487c71cad 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -20,8 +20,6 @@ static int hwpoison_inject(void *data, u64 val) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!hwpoison_filter_enable) - goto inject; if (!pfn_valid(pfn)) return -ENXIO; @@ -33,6 +31,9 @@ static int hwpoison_inject(void *data, u64 val) if (!get_page_unless_zero(hpage)) return 0; + if (!hwpoison_filter_enable) + goto inject; + if (!PageLRU(p) && !PageHuge(p)) shake_page(p, 0); /* @@ -54,7 +55,7 @@ static int hwpoison_inject(void *data, u64 val) return 0; inject: - printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn); + pr_info("Injecting memory failure at pfn %#lx\n", pfn); return memory_failure(pfn, 18, MF_COUNT_INCREASED); } @@ -88,12 +89,12 @@ static int pfn_inject_init(void) * hardware status change, hence do not require hardware support. * They are mainly for testing hwpoison in software level. */ - dentry = debugfs_create_file("corrupt-pfn", 0600, hwpoison_dir, + dentry = debugfs_create_file("corrupt-pfn", 0200, hwpoison_dir, NULL, &hwpoison_fops); if (!dentry) goto fail; - dentry = debugfs_create_file("unpoison-pfn", 0600, hwpoison_dir, + dentry = debugfs_create_file("unpoison-pfn", 0200, hwpoison_dir, NULL, &unpoison_fops); if (!dentry) goto fail; diff --git a/mm/internal.h b/mm/internal.h index 9ba21100ebf..7f22a11fcc6 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -11,6 +11,7 @@ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H +#include <linux/fs.h> #include <linux/mm.h> void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, @@ -21,22 +22,31 @@ static inline void set_page_count(struct page *page, int v) atomic_set(&page->_count, v); } +extern int __do_page_cache_readahead(struct address_space *mapping, + struct file *filp, pgoff_t offset, unsigned long nr_to_read, + unsigned long lookahead_size); + +/* + * Submit IO for the read-ahead request in file_ra_state. + */ +static inline unsigned long ra_submit(struct file_ra_state *ra, + struct address_space *mapping, struct file *filp) +{ + return __do_page_cache_readahead(mapping, filp, + ra->start, ra->size, ra->async_size); +} + /* * Turn a non-refcounted page (->_count == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { - VM_BUG_ON(PageTail(page)); - VM_BUG_ON(atomic_read(&page->_count)); + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(atomic_read(&page->_count), page); set_page_count(page, 1); } -static inline void __put_page(struct page *page) -{ - atomic_dec(&page->_count); -} - static inline void __get_page_tail_foll(struct page *page, bool get_page_head) { @@ -51,12 +61,10 @@ static inline void __get_page_tail_foll(struct page *page, * speculative page access (like in * page_cache_get_speculative()) on tail pages. */ - VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0); - VM_BUG_ON(atomic_read(&page->_count) != 0); - VM_BUG_ON(page_mapcount(page) < 0); + VM_BUG_ON_PAGE(atomic_read(&page->first_page->_count) <= 0, page); if (get_page_head) atomic_inc(&page->first_page->_count); - atomic_inc(&page->_mapcount); + get_huge_page_tail(page); } /* @@ -78,7 +86,7 @@ static inline void get_page_foll(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_count. */ - VM_BUG_ON(atomic_read(&page->_count) <= 0); + VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); atomic_inc(&page->_count); } } @@ -90,6 +98,7 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); +extern bool zone_reclaimable(struct zone *zone); /* * in mm/rmap.c: @@ -104,6 +113,7 @@ extern void prep_compound_page(struct page *page, unsigned long order); #ifdef CONFIG_MEMORY_FAILURE extern bool is_free_buddy_page(struct page *page); #endif +extern int user_min_free_kbytes; #if defined CONFIG_COMPACTION || defined CONFIG_CMA @@ -124,7 +134,7 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ + enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool finished_update_free; /* True when the zone cached pfns are * no longer being updated @@ -134,7 +144,10 @@ struct compact_control { int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; - bool contended; /* True if a lock was contended */ + bool contended; /* True if a lock was contended, or + * need_resched() true during async + * compaction + */ }; unsigned long @@ -147,9 +160,11 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, #endif /* - * function for dealing with page's order in buddy system. - * zone->lock is already acquired when we use these. - * So, we don't need atomic page->flags operations here. + * This function returns the order of a free page in the buddy system. In + * general, page_zone(page)->lock must be held by the caller to prevent the + * page from being allocated in parallel and returning garbage as the order. + * If a caller does not hold page_zone(page)->lock, it must guarantee that the + * page cannot be allocated or merged in parallel. */ static inline unsigned long page_order(struct page *page) { @@ -157,13 +172,18 @@ static inline unsigned long page_order(struct page *page) return page_private(page); } +static inline bool is_cow_mapping(vm_flags_t flags) +{ + return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; +} + /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node *rb_parent); #ifdef CONFIG_MMU -extern long mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end); +extern long __mlock_vma_pages_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *nonblocking); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); static inline void munlock_vma_pages_all(struct vm_area_struct *vma) @@ -172,30 +192,10 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma) } /* - * Called only in fault path, to determine if a new page is being - * mapped into a LOCKED vma. If it is, mark page as mlocked. - */ -static inline int mlocked_vma_newpage(struct vm_area_struct *vma, - struct page *page) -{ - VM_BUG_ON(PageLRU(page)); - - if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) - return 0; - - if (!TestSetPageMlocked(page)) { - mod_zone_page_state(page_zone(page), NR_MLOCK, - hpage_nr_pages(page)); - count_vm_event(UNEVICTABLE_PGMLOCKED); - } - return 1; -} - -/* * must be called with vma's mmap_sem held for read or write, and page locked. */ extern void mlock_vma_page(struct page *page); -extern void munlock_vma_page(struct page *page); +extern unsigned int munlock_vma_page(struct page *page); /* * Clear the page's PageMlocked(). This can be useful in a situation where @@ -233,10 +233,6 @@ extern unsigned long vma_address(struct page *page, struct vm_area_struct *vma); #endif #else /* !CONFIG_MMU */ -static inline int mlocked_vma_newpage(struct vm_area_struct *v, struct page *p) -{ - return 0; -} static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void mlock_migrate_page(struct page *new, struct page *old) { } @@ -373,5 +369,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ +#define ALLOC_FAIR 0x100 /* fair zone allocation */ #endif /* __MM_INTERNAL_H */ diff --git a/mm/iov_iter.c b/mm/iov_iter.c new file mode 100644 index 00000000000..7b5dbd1517b --- /dev/null +++ b/mm/iov_iter.c @@ -0,0 +1,743 @@ +#include <linux/export.h> +#include <linux/uio.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, left, wanted; + const struct iovec *iov; + char __user *buf; + void *kaddr, *from; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + iov = i->iov; + skip = i->iov_offset; + buf = iov->iov_base + skip; + copy = min(bytes, iov->iov_len - skip); + + if (!fault_in_pages_writeable(buf, copy)) { + kaddr = kmap_atomic(page); + from = kaddr + offset; + + /* first chunk, usually the only one */ + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + if (likely(!bytes)) { + kunmap_atomic(kaddr); + goto done; + } + offset = from - kaddr; + buf += copy; + kunmap_atomic(kaddr); + copy = min(bytes, iov->iov_len - skip); + } + /* Too bad - revert to non-atomic kmap */ + kaddr = kmap(page); + from = kaddr + offset; + left = __copy_to_user(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + kunmap(page); +done: + if (skip == iov->iov_len) { + iov++; + skip = 0; + } + i->count -= wanted - bytes; + i->nr_segs -= iov - i->iov; + i->iov = iov; + i->iov_offset = skip; + return wanted - bytes; +} + +static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, left, wanted; + const struct iovec *iov; + char __user *buf; + void *kaddr, *to; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + iov = i->iov; + skip = i->iov_offset; + buf = iov->iov_base + skip; + copy = min(bytes, iov->iov_len - skip); + + if (!fault_in_pages_readable(buf, copy)) { + kaddr = kmap_atomic(page); + to = kaddr + offset; + + /* first chunk, usually the only one */ + left = __copy_from_user_inatomic(to, buf, copy); + copy -= left; + skip += copy; + to += copy; + bytes -= copy; + + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_from_user_inatomic(to, buf, copy); + copy -= left; + skip = copy; + to += copy; + bytes -= copy; + } + if (likely(!bytes)) { + kunmap_atomic(kaddr); + goto done; + } + offset = to - kaddr; + buf += copy; + kunmap_atomic(kaddr); + copy = min(bytes, iov->iov_len - skip); + } + /* Too bad - revert to non-atomic kmap */ + kaddr = kmap(page); + to = kaddr + offset; + left = __copy_from_user(to, buf, copy); + copy -= left; + skip += copy; + to += copy; + bytes -= copy; + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_from_user(to, buf, copy); + copy -= left; + skip = copy; + to += copy; + bytes -= copy; + } + kunmap(page); +done: + if (skip == iov->iov_len) { + iov++; + skip = 0; + } + i->count -= wanted - bytes; + i->nr_segs -= iov - i->iov; + i->iov = iov; + i->iov_offset = skip; + return wanted - bytes; +} + +static size_t __iovec_copy_from_user_inatomic(char *vaddr, + const struct iovec *iov, size_t base, size_t bytes) +{ + size_t copied = 0, left = 0; + + while (bytes) { + char __user *buf = iov->iov_base + base; + int copy = min(bytes, iov->iov_len - base); + + base = 0; + left = __copy_from_user_inatomic(vaddr, buf, copy); + copied += copy; + bytes -= copy; + vaddr += copy; + iov++; + + if (unlikely(left)) + break; + } + return copied - left; +} + +/* + * Copy as much as we can into the page and return the number of bytes which + * were successfully copied. If a fault is encountered then return the number of + * bytes which were copied. + */ +static size_t copy_from_user_atomic_iovec(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t copied; + + kaddr = kmap_atomic(page); + if (likely(i->nr_segs == 1)) { + int left; + char __user *buf = i->iov->iov_base + i->iov_offset; + left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); + copied = bytes - left; + } else { + copied = __iovec_copy_from_user_inatomic(kaddr + offset, + i->iov, i->iov_offset, bytes); + } + kunmap_atomic(kaddr); + + return copied; +} + +static void advance_iovec(struct iov_iter *i, size_t bytes) +{ + BUG_ON(i->count < bytes); + + if (likely(i->nr_segs == 1)) { + i->iov_offset += bytes; + i->count -= bytes; + } else { + const struct iovec *iov = i->iov; + size_t base = i->iov_offset; + unsigned long nr_segs = i->nr_segs; + + /* + * The !iov->iov_len check ensures we skip over unlikely + * zero-length segments (without overruning the iovec). + */ + while (bytes || unlikely(i->count && !iov->iov_len)) { + int copy; + + copy = min(bytes, iov->iov_len - base); + BUG_ON(!i->count || i->count < copy); + i->count -= copy; + bytes -= copy; + base += copy; + if (iov->iov_len == base) { + iov++; + nr_segs--; + base = 0; + } + } + i->iov = iov; + i->iov_offset = base; + i->nr_segs = nr_segs; + } +} + +/* + * Fault in the first iovec of the given iov_iter, to a maximum length + * of bytes. Returns 0 on success, or non-zero if the memory could not be + * accessed (ie. because it is an invalid address). + * + * writev-intensive code may want this to prefault several iovecs -- that + * would be possible (callers must not rely on the fact that _only_ the + * first iovec will be faulted with the current implementation). + */ +int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) +{ + if (!(i->type & ITER_BVEC)) { + char __user *buf = i->iov->iov_base + i->iov_offset; + bytes = min(bytes, i->iov->iov_len - i->iov_offset); + return fault_in_pages_readable(buf, bytes); + } + return 0; +} +EXPORT_SYMBOL(iov_iter_fault_in_readable); + +static unsigned long alignment_iovec(const struct iov_iter *i) +{ + const struct iovec *iov = i->iov; + unsigned long res; + size_t size = i->count; + size_t n; + + if (!size) + return 0; + + res = (unsigned long)iov->iov_base + i->iov_offset; + n = iov->iov_len - i->iov_offset; + if (n >= size) + return res | size; + size -= n; + res |= n; + while (size > (++iov)->iov_len) { + res |= (unsigned long)iov->iov_base | iov->iov_len; + size -= iov->iov_len; + } + res |= (unsigned long)iov->iov_base | size; + return res; +} + +void iov_iter_init(struct iov_iter *i, int direction, + const struct iovec *iov, unsigned long nr_segs, + size_t count) +{ + /* It will get better. Eventually... */ + if (segment_eq(get_fs(), KERNEL_DS)) + direction |= ITER_KVEC; + i->type = direction; + i->iov = iov; + i->nr_segs = nr_segs; + i->iov_offset = 0; + i->count = count; +} +EXPORT_SYMBOL(iov_iter_init); + +static ssize_t get_pages_iovec(struct iov_iter *i, + struct page **pages, size_t maxsize, + size_t *start) +{ + size_t offset = i->iov_offset; + const struct iovec *iov = i->iov; + size_t len; + unsigned long addr; + int n; + int res; + + len = iov->iov_len - offset; + if (len > i->count) + len = i->count; + if (len > maxsize) + len = maxsize; + addr = (unsigned long)iov->iov_base + offset; + len += *start = addr & (PAGE_SIZE - 1); + addr &= ~(PAGE_SIZE - 1); + n = (len + PAGE_SIZE - 1) / PAGE_SIZE; + res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); + if (unlikely(res < 0)) + return res; + return (res == n ? len : res * PAGE_SIZE) - *start; +} + +static ssize_t get_pages_alloc_iovec(struct iov_iter *i, + struct page ***pages, size_t maxsize, + size_t *start) +{ + size_t offset = i->iov_offset; + const struct iovec *iov = i->iov; + size_t len; + unsigned long addr; + void *p; + int n; + int res; + + len = iov->iov_len - offset; + if (len > i->count) + len = i->count; + if (len > maxsize) + len = maxsize; + addr = (unsigned long)iov->iov_base + offset; + len += *start = addr & (PAGE_SIZE - 1); + addr &= ~(PAGE_SIZE - 1); + n = (len + PAGE_SIZE - 1) / PAGE_SIZE; + + p = kmalloc(n * sizeof(struct page *), GFP_KERNEL); + if (!p) + p = vmalloc(n * sizeof(struct page *)); + if (!p) + return -ENOMEM; + + res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); + if (unlikely(res < 0)) { + kvfree(p); + return res; + } + *pages = p; + return (res == n ? len : res * PAGE_SIZE) - *start; +} + +static int iov_iter_npages_iovec(const struct iov_iter *i, int maxpages) +{ + size_t offset = i->iov_offset; + size_t size = i->count; + const struct iovec *iov = i->iov; + int npages = 0; + int n; + + for (n = 0; size && n < i->nr_segs; n++, iov++) { + unsigned long addr = (unsigned long)iov->iov_base + offset; + size_t len = iov->iov_len - offset; + offset = 0; + if (unlikely(!len)) /* empty segment */ + continue; + if (len > size) + len = size; + npages += (addr + len + PAGE_SIZE - 1) / PAGE_SIZE + - addr / PAGE_SIZE; + if (npages >= maxpages) /* don't bother going further */ + return maxpages; + size -= len; + offset = 0; + } + return min(npages, maxpages); +} + +static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) +{ + char *from = kmap_atomic(page); + memcpy(to, from + offset, len); + kunmap_atomic(from); +} + +static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t len) +{ + char *to = kmap_atomic(page); + memcpy(to + offset, from, len); + kunmap_atomic(to); +} + +static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, wanted; + const struct bio_vec *bvec; + void *kaddr, *from; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + bvec = i->bvec; + skip = i->iov_offset; + copy = min_t(size_t, bytes, bvec->bv_len - skip); + + kaddr = kmap_atomic(page); + from = kaddr + offset; + memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy); + skip += copy; + from += copy; + bytes -= copy; + while (bytes) { + bvec++; + copy = min(bytes, (size_t)bvec->bv_len); + memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, copy); + skip = copy; + from += copy; + bytes -= copy; + } + kunmap_atomic(kaddr); + if (skip == bvec->bv_len) { + bvec++; + skip = 0; + } + i->count -= wanted - bytes; + i->nr_segs -= bvec - i->bvec; + i->bvec = bvec; + i->iov_offset = skip; + return wanted - bytes; +} + +static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, wanted; + const struct bio_vec *bvec; + void *kaddr, *to; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + bvec = i->bvec; + skip = i->iov_offset; + + kaddr = kmap_atomic(page); + + to = kaddr + offset; + + copy = min(bytes, bvec->bv_len - skip); + + memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy); + + to += copy; + skip += copy; + bytes -= copy; + + while (bytes) { + bvec++; + copy = min(bytes, (size_t)bvec->bv_len); + memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, copy); + skip = copy; + to += copy; + bytes -= copy; + } + kunmap_atomic(kaddr); + if (skip == bvec->bv_len) { + bvec++; + skip = 0; + } + i->count -= wanted; + i->nr_segs -= bvec - i->bvec; + i->bvec = bvec; + i->iov_offset = skip; + return wanted; +} + +static size_t copy_from_user_bvec(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t left; + const struct bio_vec *bvec; + size_t base = i->iov_offset; + + kaddr = kmap_atomic(page); + for (left = bytes, bvec = i->bvec; left; bvec++, base = 0) { + size_t copy = min(left, bvec->bv_len - base); + if (!bvec->bv_len) + continue; + memcpy_from_page(kaddr + offset, bvec->bv_page, + bvec->bv_offset + base, copy); + offset += copy; + left -= copy; + } + kunmap_atomic(kaddr); + return bytes; +} + +static void advance_bvec(struct iov_iter *i, size_t bytes) +{ + BUG_ON(i->count < bytes); + + if (likely(i->nr_segs == 1)) { + i->iov_offset += bytes; + i->count -= bytes; + } else { + const struct bio_vec *bvec = i->bvec; + size_t base = i->iov_offset; + unsigned long nr_segs = i->nr_segs; + + /* + * The !iov->iov_len check ensures we skip over unlikely + * zero-length segments (without overruning the iovec). + */ + while (bytes || unlikely(i->count && !bvec->bv_len)) { + int copy; + + copy = min(bytes, bvec->bv_len - base); + BUG_ON(!i->count || i->count < copy); + i->count -= copy; + bytes -= copy; + base += copy; + if (bvec->bv_len == base) { + bvec++; + nr_segs--; + base = 0; + } + } + i->bvec = bvec; + i->iov_offset = base; + i->nr_segs = nr_segs; + } +} + +static unsigned long alignment_bvec(const struct iov_iter *i) +{ + const struct bio_vec *bvec = i->bvec; + unsigned long res; + size_t size = i->count; + size_t n; + + if (!size) + return 0; + + res = bvec->bv_offset + i->iov_offset; + n = bvec->bv_len - i->iov_offset; + if (n >= size) + return res | size; + size -= n; + res |= n; + while (size > (++bvec)->bv_len) { + res |= bvec->bv_offset | bvec->bv_len; + size -= bvec->bv_len; + } + res |= bvec->bv_offset | size; + return res; +} + +static ssize_t get_pages_bvec(struct iov_iter *i, + struct page **pages, size_t maxsize, + size_t *start) +{ + const struct bio_vec *bvec = i->bvec; + size_t len = bvec->bv_len - i->iov_offset; + if (len > i->count) + len = i->count; + if (len > maxsize) + len = maxsize; + *start = bvec->bv_offset + i->iov_offset; + + get_page(*pages = bvec->bv_page); + + return len; +} + +static ssize_t get_pages_alloc_bvec(struct iov_iter *i, + struct page ***pages, size_t maxsize, + size_t *start) +{ + const struct bio_vec *bvec = i->bvec; + size_t len = bvec->bv_len - i->iov_offset; + if (len > i->count) + len = i->count; + if (len > maxsize) + len = maxsize; + *start = bvec->bv_offset + i->iov_offset; + + *pages = kmalloc(sizeof(struct page *), GFP_KERNEL); + if (!*pages) + return -ENOMEM; + + get_page(**pages = bvec->bv_page); + + return len; +} + +static int iov_iter_npages_bvec(const struct iov_iter *i, int maxpages) +{ + size_t offset = i->iov_offset; + size_t size = i->count; + const struct bio_vec *bvec = i->bvec; + int npages = 0; + int n; + + for (n = 0; size && n < i->nr_segs; n++, bvec++) { + size_t len = bvec->bv_len - offset; + offset = 0; + if (unlikely(!len)) /* empty segment */ + continue; + if (len > size) + len = size; + npages++; + if (npages >= maxpages) /* don't bother going further */ + return maxpages; + size -= len; + offset = 0; + } + return min(npages, maxpages); +} + +size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + if (i->type & ITER_BVEC) + return copy_page_to_iter_bvec(page, offset, bytes, i); + else + return copy_page_to_iter_iovec(page, offset, bytes, i); +} +EXPORT_SYMBOL(copy_page_to_iter); + +size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + if (i->type & ITER_BVEC) + return copy_page_from_iter_bvec(page, offset, bytes, i); + else + return copy_page_from_iter_iovec(page, offset, bytes, i); +} +EXPORT_SYMBOL(copy_page_from_iter); + +size_t iov_iter_copy_from_user_atomic(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + if (i->type & ITER_BVEC) + return copy_from_user_bvec(page, i, offset, bytes); + else + return copy_from_user_atomic_iovec(page, i, offset, bytes); +} +EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); + +void iov_iter_advance(struct iov_iter *i, size_t size) +{ + if (i->type & ITER_BVEC) + advance_bvec(i, size); + else + advance_iovec(i, size); +} +EXPORT_SYMBOL(iov_iter_advance); + +/* + * Return the count of just the current iov_iter segment. + */ +size_t iov_iter_single_seg_count(const struct iov_iter *i) +{ + if (i->nr_segs == 1) + return i->count; + else if (i->type & ITER_BVEC) + return min(i->count, i->iov->iov_len - i->iov_offset); + else + return min(i->count, i->bvec->bv_len - i->iov_offset); +} +EXPORT_SYMBOL(iov_iter_single_seg_count); + +unsigned long iov_iter_alignment(const struct iov_iter *i) +{ + if (i->type & ITER_BVEC) + return alignment_bvec(i); + else + return alignment_iovec(i); +} +EXPORT_SYMBOL(iov_iter_alignment); + +ssize_t iov_iter_get_pages(struct iov_iter *i, + struct page **pages, size_t maxsize, + size_t *start) +{ + if (i->type & ITER_BVEC) + return get_pages_bvec(i, pages, maxsize, start); + else + return get_pages_iovec(i, pages, maxsize, start); +} +EXPORT_SYMBOL(iov_iter_get_pages); + +ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, + struct page ***pages, size_t maxsize, + size_t *start) +{ + if (i->type & ITER_BVEC) + return get_pages_alloc_bvec(i, pages, maxsize, start); + else + return get_pages_alloc_iovec(i, pages, maxsize, start); +} +EXPORT_SYMBOL(iov_iter_get_pages_alloc); + +int iov_iter_npages(const struct iov_iter *i, int maxpages) +{ + if (i->type & ITER_BVEC) + return iov_iter_npages_bvec(i, maxpages); + else + return iov_iter_npages_iovec(i, maxpages); +} +EXPORT_SYMBOL(iov_iter_npages); diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c index ff0d9779cec..dcdcadb6953 100644 --- a/mm/kmemleak-test.c +++ b/mm/kmemleak-test.c @@ -18,6 +18,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#define pr_fmt(fmt) "kmemleak: " fmt + #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> @@ -50,25 +52,25 @@ static int __init kmemleak_test_init(void) printk(KERN_INFO "Kmemleak testing\n"); /* make some orphan objects */ - pr_info("kmemleak: kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL)); - pr_info("kmemleak: kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL)); + pr_info("kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL)); + pr_info("kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL)); + pr_info("kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL)); + pr_info("kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL)); + pr_info("kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL)); + pr_info("kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL)); + pr_info("kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL)); + pr_info("kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL)); #ifndef CONFIG_MODULES - pr_info("kmemleak: kmem_cache_alloc(files_cachep) = %p\n", + pr_info("kmem_cache_alloc(files_cachep) = %p\n", kmem_cache_alloc(files_cachep, GFP_KERNEL)); - pr_info("kmemleak: kmem_cache_alloc(files_cachep) = %p\n", + pr_info("kmem_cache_alloc(files_cachep) = %p\n", kmem_cache_alloc(files_cachep, GFP_KERNEL)); #endif - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); - pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); + pr_info("vmalloc(64) = %p\n", vmalloc(64)); /* * Add elements to a list. They should only appear as orphan @@ -76,7 +78,7 @@ static int __init kmemleak_test_init(void) */ for (i = 0; i < 10; i++) { elem = kzalloc(sizeof(*elem), GFP_KERNEL); - pr_info("kmemleak: kzalloc(sizeof(*elem)) = %p\n", elem); + pr_info("kzalloc(sizeof(*elem)) = %p\n", elem); if (!elem) return -ENOMEM; INIT_LIST_HEAD(&elem->list); @@ -85,7 +87,7 @@ static int __init kmemleak_test_init(void) for_each_possible_cpu(i) { per_cpu(kmemleak_test_pointer, i) = kmalloc(129, GFP_KERNEL); - pr_info("kmemleak: kmalloc(129) = %p\n", + pr_info("kmalloc(129) = %p\n", per_cpu(kmemleak_test_pointer, i)); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 752a705c77c..3cda50c1e39 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -192,15 +192,15 @@ static struct kmem_cache *object_cache; static struct kmem_cache *scan_area_cache; /* set if tracing memory operations is enabled */ -static atomic_t kmemleak_enabled = ATOMIC_INIT(0); +static int kmemleak_enabled; /* set in the late_initcall if there were no errors */ -static atomic_t kmemleak_initialized = ATOMIC_INIT(0); +static int kmemleak_initialized; /* enables or disables early logging of the memory operations */ -static atomic_t kmemleak_early_log = ATOMIC_INIT(1); +static int kmemleak_early_log = 1; /* set if a kmemleak warning was issued */ -static atomic_t kmemleak_warning = ATOMIC_INIT(0); +static int kmemleak_warning; /* set if a fatal kmemleak error has occurred */ -static atomic_t kmemleak_error = ATOMIC_INIT(0); +static int kmemleak_error; /* minimum and maximum address that may be valid pointers */ static unsigned long min_addr = ULONG_MAX; @@ -218,7 +218,8 @@ static int kmemleak_stack_scan = 1; static DEFINE_MUTEX(scan_mutex); /* setting kmemleak=on, will set this var, skipping the disable */ static int kmemleak_skip_disable; - +/* If there are leaks that can be reported */ +static bool kmemleak_found_leaks; /* * Early object allocation/freeing logging. Kmemleak is initialized after the @@ -267,7 +268,7 @@ static void kmemleak_disable(void); #define kmemleak_warn(x...) do { \ pr_warning(x); \ dump_stack(); \ - atomic_set(&kmemleak_warning, 1); \ + kmemleak_warning = 1; \ } while (0) /* @@ -386,7 +387,7 @@ static void dump_object_info(struct kmemleak_object *object) pr_notice(" min_count = %d\n", object->min_count); pr_notice(" count = %d\n", object->count); pr_notice(" flags = 0x%lx\n", object->flags); - pr_notice(" checksum = %d\n", object->checksum); + pr_notice(" checksum = %u\n", object->checksum); pr_notice(" backtrace:\n"); print_stack_trace(&trace, 4); } @@ -436,7 +437,7 @@ static int get_object(struct kmemleak_object *object) */ static void free_object_rcu(struct rcu_head *rcu) { - struct hlist_node *elem, *tmp; + struct hlist_node *tmp; struct kmemleak_scan_area *area; struct kmemleak_object *object = container_of(rcu, struct kmemleak_object, rcu); @@ -445,8 +446,8 @@ static void free_object_rcu(struct rcu_head *rcu) * Once use_count is 0 (guaranteed by put_object), there is no other * code accessing this object, hence no need for locking. */ - hlist_for_each_entry_safe(area, elem, tmp, &object->area_list, node) { - hlist_del(elem); + hlist_for_each_entry_safe(area, tmp, &object->area_list, node) { + hlist_del(&area->node); kmem_cache_free(scan_area_cache, area); } kmem_cache_free(object_cache, object); @@ -753,7 +754,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) } spin_lock_irqsave(&object->lock, flags); - if (ptr + size > object->pointer + object->size) { + if (size == SIZE_MAX) { + size = object->pointer + object->size - ptr; + } else if (ptr + size > object->pointer + object->size) { kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr); dump_object_info(object); kmem_cache_free(scan_area_cache, area); @@ -803,7 +806,7 @@ static void __init log_early(int op_type, const void *ptr, size_t size, unsigned long flags; struct early_log *log; - if (atomic_read(&kmemleak_error)) { + if (kmemleak_error) { /* kmemleak stopped recording, just count the requests */ crt_early_log++; return; @@ -838,7 +841,7 @@ static void early_alloc(struct early_log *log) unsigned long flags; int i; - if (!atomic_read(&kmemleak_enabled) || !log->ptr || IS_ERR(log->ptr)) + if (!kmemleak_enabled || !log->ptr || IS_ERR(log->ptr)) return; /* @@ -891,9 +894,9 @@ void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count, { pr_debug("%s(0x%p, %zu, %d)\n", __func__, ptr, size, min_count); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) create_object((unsigned long)ptr, size, min_count, gfp); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_ALLOC, ptr, size, min_count); } EXPORT_SYMBOL_GPL(kmemleak_alloc); @@ -917,11 +920,11 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) * Percpu allocations are only scanned and not reported as leaks * (min_count is set to 0). */ - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) for_each_possible_cpu(cpu) create_object((unsigned long)per_cpu_ptr(ptr, cpu), size, 0, GFP_KERNEL); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_ALLOC_PERCPU, ptr, size, 0); } EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); @@ -937,9 +940,9 @@ void __ref kmemleak_free(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) delete_object_full((unsigned long)ptr); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_FREE, ptr, 0, 0); } EXPORT_SYMBOL_GPL(kmemleak_free); @@ -957,9 +960,9 @@ void __ref kmemleak_free_part(const void *ptr, size_t size) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) delete_object_part((unsigned long)ptr, size); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_FREE_PART, ptr, size, 0); } EXPORT_SYMBOL_GPL(kmemleak_free_part); @@ -977,16 +980,50 @@ void __ref kmemleak_free_percpu(const void __percpu *ptr) pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) for_each_possible_cpu(cpu) delete_object_full((unsigned long)per_cpu_ptr(ptr, cpu)); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_FREE_PERCPU, ptr, 0, 0); } EXPORT_SYMBOL_GPL(kmemleak_free_percpu); /** + * kmemleak_update_trace - update object allocation stack trace + * @ptr: pointer to beginning of the object + * + * Override the object allocation stack trace for cases where the actual + * allocation place is not always useful. + */ +void __ref kmemleak_update_trace(const void *ptr) +{ + struct kmemleak_object *object; + unsigned long flags; + + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (!kmemleak_enabled || IS_ERR_OR_NULL(ptr)) + return; + + object = find_and_get_object((unsigned long)ptr, 1); + if (!object) { +#ifdef DEBUG + kmemleak_warn("Updating stack trace for unknown object at %p\n", + ptr); +#endif + return; + } + + spin_lock_irqsave(&object->lock, flags); + object->trace_len = __save_stack_trace(object->trace); + spin_unlock_irqrestore(&object->lock, flags); + + put_object(object); +} +EXPORT_SYMBOL(kmemleak_update_trace); + +/** * kmemleak_not_leak - mark an allocated object as false positive * @ptr: pointer to beginning of the object * @@ -997,9 +1034,9 @@ void __ref kmemleak_not_leak(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) make_gray_object((unsigned long)ptr); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_NOT_LEAK, ptr, 0, 0); } EXPORT_SYMBOL(kmemleak_not_leak); @@ -1017,9 +1054,9 @@ void __ref kmemleak_ignore(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) make_black_object((unsigned long)ptr); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_IGNORE, ptr, 0, 0); } EXPORT_SYMBOL(kmemleak_ignore); @@ -1039,9 +1076,9 @@ void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && size && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && size && !IS_ERR(ptr)) add_scan_area((unsigned long)ptr, size, gfp); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_SCAN_AREA, ptr, size, 0); } EXPORT_SYMBOL(kmemleak_scan_area); @@ -1059,9 +1096,9 @@ void __ref kmemleak_no_scan(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); - if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) object_no_scan((unsigned long)ptr); - else if (atomic_read(&kmemleak_early_log)) + else if (kmemleak_early_log) log_early(KMEMLEAK_NO_SCAN, ptr, 0, 0); } EXPORT_SYMBOL(kmemleak_no_scan); @@ -1086,7 +1123,7 @@ static bool update_checksum(struct kmemleak_object *object) */ static int scan_should_stop(void) { - if (!atomic_read(&kmemleak_enabled)) + if (!kmemleak_enabled) return 1; /* @@ -1177,7 +1214,6 @@ static void scan_block(void *_start, void *_end, static void scan_object(struct kmemleak_object *object) { struct kmemleak_scan_area *area; - struct hlist_node *elem; unsigned long flags; /* @@ -1205,7 +1241,7 @@ static void scan_object(struct kmemleak_object *object) spin_lock_irqsave(&object->lock, flags); } } else - hlist_for_each_entry(area, elem, &object->area_list, node) + hlist_for_each_entry(area, &object->area_list, node) scan_block((void *)area->start, (void *)(area->start + area->size), object, 0); @@ -1298,11 +1334,10 @@ static void kmemleak_scan(void) /* * Struct page scanning for each node. */ - lock_memory_hotplug(); + get_online_mems(); for_each_online_node(i) { - pg_data_t *pgdat = NODE_DATA(i); - unsigned long start_pfn = pgdat->node_start_pfn; - unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; + unsigned long start_pfn = node_start_pfn(i); + unsigned long end_pfn = node_end_pfn(i); unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -1317,7 +1352,7 @@ static void kmemleak_scan(void) scan_block(page, page + 1, NULL, 1); } } - unlock_memory_hotplug(); + put_online_mems(); /* * Scanning the task stacks (may introduce false negatives). @@ -1382,9 +1417,12 @@ static void kmemleak_scan(void) } rcu_read_unlock(); - if (new_leaks) + if (new_leaks) { + kmemleak_found_leaks = true; + pr_info("%d new suspected memory leaks (see " "/sys/kernel/debug/kmemleak)\n", new_leaks); + } } @@ -1545,11 +1583,6 @@ static int kmemleak_open(struct inode *inode, struct file *file) return seq_open(file, &kmemleak_seq_ops); } -static int kmemleak_release(struct inode *inode, struct file *file) -{ - return seq_release(inode, file); -} - static int dump_str_object_info(const char *str) { unsigned long flags; @@ -1592,8 +1625,12 @@ static void kmemleak_clear(void) spin_unlock_irqrestore(&object->lock, flags); } rcu_read_unlock(); + + kmemleak_found_leaks = false; } +static void __kmemleak_do_cleanup(void); + /* * File write operation to configure kmemleak at run-time. The following * commands can be written to the /sys/kernel/debug/kmemleak file: @@ -1606,7 +1643,8 @@ static void kmemleak_clear(void) * disable it) * scan - trigger a memory scan * clear - mark all current reported unreferenced kmemleak objects as - * grey to ignore printing them + * grey to ignore printing them, or free all kmemleak objects + * if kmemleak has been disabled. * dump=... - dump information about the object found at the given address */ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, @@ -1616,9 +1654,6 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, int buf_size; int ret; - if (!atomic_read(&kmemleak_enabled)) - return -EBUSY; - buf_size = min(size, (sizeof(buf) - 1)); if (strncpy_from_user(buf, user_buf, buf_size) < 0) return -EFAULT; @@ -1628,6 +1663,19 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, if (ret < 0) return ret; + if (strncmp(buf, "clear", 5) == 0) { + if (kmemleak_enabled) + kmemleak_clear(); + else + __kmemleak_do_cleanup(); + goto out; + } + + if (!kmemleak_enabled) { + ret = -EBUSY; + goto out; + } + if (strncmp(buf, "off", 3) == 0) kmemleak_disable(); else if (strncmp(buf, "stack=on", 8) == 0) @@ -1641,7 +1689,7 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, else if (strncmp(buf, "scan=", 5) == 0) { unsigned long secs; - ret = strict_strtoul(buf + 5, 0, &secs); + ret = kstrtoul(buf + 5, 0, &secs); if (ret < 0) goto out; stop_scan_thread(); @@ -1651,8 +1699,6 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, } } else if (strncmp(buf, "scan", 4) == 0) kmemleak_scan(); - else if (strncmp(buf, "clear", 5) == 0) - kmemleak_clear(); else if (strncmp(buf, "dump=", 5) == 0) ret = dump_str_object_info(buf + 5); else @@ -1674,9 +1720,19 @@ static const struct file_operations kmemleak_fops = { .read = seq_read, .write = kmemleak_write, .llseek = seq_lseek, - .release = kmemleak_release, + .release = seq_release, }; +static void __kmemleak_do_cleanup(void) +{ + struct kmemleak_object *object; + + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) + delete_object_full(object->pointer); + rcu_read_unlock(); +} + /* * Stop the memory scanning thread and free the kmemleak internal objects if * no previous scan thread (otherwise, kmemleak may still have some useful @@ -1684,18 +1740,14 @@ static const struct file_operations kmemleak_fops = { */ static void kmemleak_do_cleanup(struct work_struct *work) { - struct kmemleak_object *object; - bool cleanup = scan_thread == NULL; - mutex_lock(&scan_mutex); stop_scan_thread(); - if (cleanup) { - rcu_read_lock(); - list_for_each_entry_rcu(object, &object_list, object_list) - delete_object_full(object->pointer); - rcu_read_unlock(); - } + if (!kmemleak_found_leaks) + __kmemleak_do_cleanup(); + else + pr_info("Kmemleak disabled without freeing internal data. " + "Reclaim the memory with \"echo clear > /sys/kernel/debug/kmemleak\"\n"); mutex_unlock(&scan_mutex); } @@ -1708,14 +1760,14 @@ static DECLARE_WORK(cleanup_work, kmemleak_do_cleanup); static void kmemleak_disable(void) { /* atomically check whether it was already invoked */ - if (atomic_cmpxchg(&kmemleak_error, 0, 1)) + if (cmpxchg(&kmemleak_error, 0, 1)) return; /* stop any memory operation tracing */ - atomic_set(&kmemleak_enabled, 0); + kmemleak_enabled = 0; /* check whether it is too early for a kernel thread */ - if (atomic_read(&kmemleak_initialized)) + if (kmemleak_initialized) schedule_work(&cleanup_work); pr_info("Kernel memory leak detector disabled\n"); @@ -1759,7 +1811,7 @@ void __init kmemleak_init(void) #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF if (!kmemleak_skip_disable) { - atomic_set(&kmemleak_early_log, 0); + kmemleak_early_log = 0; kmemleak_disable(); return; } @@ -1777,12 +1829,12 @@ void __init kmemleak_init(void) /* the kernel is still in UP mode, so disabling the IRQs is enough */ local_irq_save(flags); - atomic_set(&kmemleak_early_log, 0); - if (atomic_read(&kmemleak_error)) { + kmemleak_early_log = 0; + if (kmemleak_error) { local_irq_restore(flags); return; } else - atomic_set(&kmemleak_enabled, 1); + kmemleak_enabled = 1; local_irq_restore(flags); /* @@ -1826,9 +1878,9 @@ void __init kmemleak_init(void) log->op_type); } - if (atomic_read(&kmemleak_warning)) { + if (kmemleak_warning) { print_log_trace(log); - atomic_set(&kmemleak_warning, 0); + kmemleak_warning = 0; } } } @@ -1840,9 +1892,9 @@ static int __init kmemleak_late_init(void) { struct dentry *dentry; - atomic_set(&kmemleak_initialized, 1); + kmemleak_initialized = 1; - if (atomic_read(&kmemleak_error)) { + if (kmemleak_error) { /* * Some error occurred and kmemleak was disabled. There is a * small chance that kmemleak_disable() was called immediately @@ -33,13 +33,22 @@ #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/ksm.h> -#include <linux/hash.h> +#include <linux/hashtable.h> #include <linux/freezer.h> #include <linux/oom.h> +#include <linux/numa.h> #include <asm/tlbflush.h> #include "internal.h" +#ifdef CONFIG_NUMA +#define NUMA(x) (x) +#define DO_NUMA(x) do { (x); } while (0) +#else +#define NUMA(x) (0) +#define DO_NUMA(x) do { } while (0) +#endif + /* * A few notes about the KSM scanning process, * to make it easier to understand the data structures below: @@ -78,6 +87,9 @@ * take 10 attempts to find a page in the unstable tree, once it is found, * it is secured in the stable tree. (When we scan a new page, we first * compare it against the stable tree, and then against the unstable tree.) + * + * If the merge_across_nodes tunable is unset, then KSM maintains multiple + * stable trees and multiple unstable trees: one of each for each NUMA node. */ /** @@ -113,19 +125,32 @@ struct ksm_scan { /** * struct stable_node - node of the stable rbtree * @node: rb node of this ksm page in the stable tree + * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list + * @list: linked into migrate_nodes, pending placement in the proper node tree * @hlist: hlist head of rmap_items using this ksm page - * @kpfn: page frame number of this ksm page + * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid) + * @nid: NUMA node id of stable tree in which linked (may not match kpfn) */ struct stable_node { - struct rb_node node; + union { + struct rb_node node; /* when node of stable tree */ + struct { /* when listed for migration */ + struct list_head *head; + struct list_head list; + }; + }; struct hlist_head hlist; unsigned long kpfn; +#ifdef CONFIG_NUMA + int nid; +#endif }; /** * struct rmap_item - reverse mapping item for virtual addresses * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree + * @nid: NUMA node id of unstable tree in which linked (may not match page) * @mm: the memory structure this rmap_item is pointing into * @address: the virtual address this rmap_item tracks (+ flags in low bits) * @oldchecksum: previous checksum of the page at that virtual address @@ -135,7 +160,12 @@ struct stable_node { */ struct rmap_item { struct rmap_item *rmap_list; - struct anon_vma *anon_vma; /* when stable */ + union { + struct anon_vma *anon_vma; /* when stable */ +#ifdef CONFIG_NUMA + int nid; /* when node of unstable tree */ +#endif + }; struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ @@ -153,12 +183,16 @@ struct rmap_item { #define STABLE_FLAG 0x200 /* is listed from the stable tree */ /* The stable and unstable tree heads */ -static struct rb_root root_stable_tree = RB_ROOT; -static struct rb_root root_unstable_tree = RB_ROOT; +static struct rb_root one_stable_tree[1] = { RB_ROOT }; +static struct rb_root one_unstable_tree[1] = { RB_ROOT }; +static struct rb_root *root_stable_tree = one_stable_tree; +static struct rb_root *root_unstable_tree = one_unstable_tree; + +/* Recently migrated nodes of stable tree, pending proper placement */ +static LIST_HEAD(migrate_nodes); -#define MM_SLOTS_HASH_SHIFT 10 -#define MM_SLOTS_HASH_HEADS (1 << MM_SLOTS_HASH_SHIFT) -static struct hlist_head mm_slots_hash[MM_SLOTS_HASH_HEADS]; +#define MM_SLOTS_HASH_BITS 10 +static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct mm_slot ksm_mm_head = { .mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list), @@ -189,10 +223,21 @@ static unsigned int ksm_thread_pages_to_scan = 100; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; +#ifdef CONFIG_NUMA +/* Zeroed when merging across nodes is not allowed */ +static unsigned int ksm_merge_across_nodes = 1; +static int ksm_nr_node_ids = 1; +#else +#define ksm_merge_across_nodes 1U +#define ksm_nr_node_ids 1 +#endif + #define KSM_RUN_STOP 0 #define KSM_RUN_MERGE 1 #define KSM_RUN_UNMERGE 2 -static unsigned int ksm_run = KSM_RUN_STOP; +#define KSM_RUN_OFFLINE 4 +static unsigned long ksm_run = KSM_RUN_STOP; +static void wait_while_offlining(void); static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait); static DEFINE_MUTEX(ksm_thread_mutex); @@ -275,31 +320,20 @@ static inline void free_mm_slot(struct mm_slot *mm_slot) static struct mm_slot *get_mm_slot(struct mm_struct *mm) { - struct mm_slot *mm_slot; - struct hlist_head *bucket; - struct hlist_node *node; + struct mm_slot *slot; + + hash_for_each_possible(mm_slots_hash, slot, link, (unsigned long)mm) + if (slot->mm == mm) + return slot; - bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)]; - hlist_for_each_entry(mm_slot, node, bucket, link) { - if (mm == mm_slot->mm) - return mm_slot; - } return NULL; } static void insert_to_mm_slots_hash(struct mm_struct *mm, struct mm_slot *mm_slot) { - struct hlist_head *bucket; - - bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)]; mm_slot->mm = mm; - hlist_add_head(&mm_slot->link, bucket); -} - -static inline int in_stable_tree(struct rmap_item *rmap_item) -{ - return rmap_item->address & STABLE_FLAG; + hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm); } /* @@ -333,7 +367,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) do { cond_resched(); - page = follow_page(vma, addr, FOLL_GET); + page = follow_page(vma, addr, FOLL_GET | FOLL_MIGRATION); if (IS_ERR_OR_NULL(page)) break; if (PageKsm(page)) @@ -410,7 +444,7 @@ static void break_cow(struct rmap_item *rmap_item) static struct page *page_trans_compound_anon(struct page *page) { if (PageTransCompound(page)) { - struct page *head = compound_trans_head(page); + struct page *head = compound_head(page); /* * head may actually be splitted and freed from under * us but it's ok here. @@ -447,12 +481,22 @@ out: page = NULL; return page; } +/* + * This helper is used for getting right index into array of tree roots. + * When merge_across_nodes knob is set to 1, there are only two rb-trees for + * stable and unstable pages from all nodes with roots in index 0. Otherwise, + * every node has its own stable and unstable tree. + */ +static inline int get_kpfn_nid(unsigned long kpfn) +{ + return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn)); +} + static void remove_node_from_stable_tree(struct stable_node *stable_node) { struct rmap_item *rmap_item; - struct hlist_node *hlist; - hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { if (rmap_item->hlist.next) ksm_pages_sharing--; else @@ -462,7 +506,11 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) cond_resched(); } - rb_erase(&stable_node->node, &root_stable_tree); + if (stable_node->head == &migrate_nodes) + list_del(&stable_node->list); + else + rb_erase(&stable_node->node, + root_stable_tree + NUMA(stable_node->nid)); free_stable_node(stable_node); } @@ -472,6 +520,7 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) * In which case we can trust the content of the page, and it * returns the gotten page; but if the page has now been zapped, * remove the stale node from the stable tree and return NULL. + * But beware, the stable node's page might be being migrated. * * You would expect the stable_node to hold a reference to the ksm page. * But if it increments the page's count, swapping out has to wait for @@ -482,40 +531,77 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) * pointing back to this stable node. This relies on freeing a PageAnon * page to reset its page->mapping to NULL, and relies on no other use of * a page to put something that might look like our key in page->mapping. - * - * include/linux/pagemap.h page_cache_get_speculative() is a good reference, - * but this is different - made simpler by ksm_thread_mutex being held, but - * interesting for assuming that no other use of the struct page could ever - * put our expected_mapping into page->mapping (or a field of the union which - * coincides with page->mapping). The RCU calls are not for KSM at all, but - * to keep the page_count protocol described with page_cache_get_speculative. - * - * Note: it is possible that get_ksm_page() will return NULL one moment, - * then page the next, if the page is in between page_freeze_refs() and - * page_unfreeze_refs(): this shouldn't be a problem anywhere, the page * is on its way to being freed; but it is an anomaly to bear in mind. */ -static struct page *get_ksm_page(struct stable_node *stable_node) +static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it) { struct page *page; void *expected_mapping; + unsigned long kpfn; - page = pfn_to_page(stable_node->kpfn); expected_mapping = (void *)stable_node + (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); - rcu_read_lock(); - if (page->mapping != expected_mapping) - goto stale; - if (!get_page_unless_zero(page)) +again: + kpfn = ACCESS_ONCE(stable_node->kpfn); + page = pfn_to_page(kpfn); + + /* + * page is computed from kpfn, so on most architectures reading + * page->mapping is naturally ordered after reading node->kpfn, + * but on Alpha we need to be more careful. + */ + smp_read_barrier_depends(); + if (ACCESS_ONCE(page->mapping) != expected_mapping) goto stale; - if (page->mapping != expected_mapping) { + + /* + * We cannot do anything with the page while its refcount is 0. + * Usually 0 means free, or tail of a higher-order page: in which + * case this node is no longer referenced, and should be freed; + * however, it might mean that the page is under page_freeze_refs(). + * The __remove_mapping() case is easy, again the node is now stale; + * but if page is swapcache in migrate_page_move_mapping(), it might + * still be our page, in which case it's essential to keep the node. + */ + while (!get_page_unless_zero(page)) { + /* + * Another check for page->mapping != expected_mapping would + * work here too. We have chosen the !PageSwapCache test to + * optimize the common case, when the page is or is about to + * be freed: PageSwapCache is cleared (under spin_lock_irq) + * in the freeze_refs section of __remove_mapping(); but Anon + * page->mapping reset to NULL later, in free_pages_prepare(). + */ + if (!PageSwapCache(page)) + goto stale; + cpu_relax(); + } + + if (ACCESS_ONCE(page->mapping) != expected_mapping) { put_page(page); goto stale; } - rcu_read_unlock(); + + if (lock_it) { + lock_page(page); + if (ACCESS_ONCE(page->mapping) != expected_mapping) { + unlock_page(page); + put_page(page); + goto stale; + } + } return page; + stale: - rcu_read_unlock(); + /* + * We come here from above when page->mapping or !PageSwapCache + * suggests that the node is stale; but it might be under migration. + * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(), + * before checking whether node->kpfn has been changed. + */ + smp_rmb(); + if (ACCESS_ONCE(stable_node->kpfn) != kpfn) + goto again; remove_node_from_stable_tree(stable_node); return NULL; } @@ -531,11 +617,10 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) struct page *page; stable_node = rmap_item->head; - page = get_ksm_page(stable_node); + page = get_ksm_page(stable_node, true); if (!page) goto out; - lock_page(page); hlist_del(&rmap_item->hlist); unlock_page(page); put_page(page); @@ -560,8 +645,8 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) age = (unsigned char)(ksm_scan.seqnr - rmap_item->address); BUG_ON(age > 1); if (!age) - rb_erase(&rmap_item->node, &root_unstable_tree); - + rb_erase(&rmap_item->node, + root_unstable_tree + NUMA(rmap_item->nid)); ksm_pages_unshared--; rmap_item->address &= PAGE_MASK; } @@ -581,7 +666,7 @@ static void remove_trailing_rmap_items(struct mm_slot *mm_slot, } /* - * Though it's very tempting to unmerge in_stable_tree(rmap_item)s rather + * Though it's very tempting to unmerge rmap_items from stable tree rather * than check every pte of a given vma, the locking doesn't quite work for * that - an rmap_item is assigned to the stable tree after inserting ksm * page and upping mmap_sem. Nor does it fit with the way we skip dup'ing @@ -614,6 +699,71 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma, /* * Only called through the sysfs control interface: */ +static int remove_stable_node(struct stable_node *stable_node) +{ + struct page *page; + int err; + + page = get_ksm_page(stable_node, true); + if (!page) { + /* + * get_ksm_page did remove_node_from_stable_tree itself. + */ + return 0; + } + + if (WARN_ON_ONCE(page_mapped(page))) { + /* + * This should not happen: but if it does, just refuse to let + * merge_across_nodes be switched - there is no need to panic. + */ + err = -EBUSY; + } else { + /* + * The stable node did not yet appear stale to get_ksm_page(), + * since that allows for an unmapped ksm page to be recognized + * right up until it is freed; but the node is safe to remove. + * This page might be in a pagevec waiting to be freed, + * or it might be PageSwapCache (perhaps under writeback), + * or it might have been removed from swapcache a moment ago. + */ + set_page_stable_node(page, NULL); + remove_node_from_stable_tree(stable_node); + err = 0; + } + + unlock_page(page); + put_page(page); + return err; +} + +static int remove_all_stable_nodes(void) +{ + struct stable_node *stable_node; + struct list_head *this, *next; + int nid; + int err = 0; + + for (nid = 0; nid < ksm_nr_node_ids; nid++) { + while (root_stable_tree[nid].rb_node) { + stable_node = rb_entry(root_stable_tree[nid].rb_node, + struct stable_node, node); + if (remove_stable_node(stable_node)) { + err = -EBUSY; + break; /* proceed to next nid */ + } + cond_resched(); + } + } + list_for_each_safe(this, next, &migrate_nodes) { + stable_node = list_entry(this, struct stable_node, list); + if (remove_stable_node(stable_node)) + err = -EBUSY; + cond_resched(); + } + return err; +} + static int unmerge_and_remove_all_rmap_items(void) { struct mm_slot *mm_slot; @@ -647,7 +797,7 @@ static int unmerge_and_remove_all_rmap_items(void) ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next, struct mm_slot, mm_list); if (ksm_test_exit(mm)) { - hlist_del(&mm_slot->link); + hash_del(&mm_slot->link); list_del(&mm_slot->mm_list); spin_unlock(&ksm_mmlist_lock); @@ -661,6 +811,8 @@ static int unmerge_and_remove_all_rmap_items(void) } } + /* Clean up stable nodes, but don't worry if some are still busy */ + remove_all_stable_nodes(); ksm_scan.seqnr = 0; return 0; @@ -793,7 +945,6 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; - BUG_ON(pmd_trans_huge(*pmd)); mmun_start = addr; mmun_end = addr + PAGE_SIZE; @@ -946,6 +1097,9 @@ static int try_to_merge_with_ksm_page(struct rmap_item *rmap_item, if (err) goto out; + /* Unstable nid is in union with stable anon_vma: remove first */ + remove_rmap_item_from_tree(rmap_item); + /* Must get reference to anon_vma while still holding mmap_sem */ rmap_item->anon_vma = vma->anon_vma; get_anon_vma(vma->anon_vma); @@ -996,42 +1150,99 @@ static struct page *try_to_merge_two_pages(struct rmap_item *rmap_item, */ static struct page *stable_tree_search(struct page *page) { - struct rb_node *node = root_stable_tree.rb_node; + int nid; + struct rb_root *root; + struct rb_node **new; + struct rb_node *parent; struct stable_node *stable_node; + struct stable_node *page_node; - stable_node = page_stable_node(page); - if (stable_node) { /* ksm page forked */ + page_node = page_stable_node(page); + if (page_node && page_node->head != &migrate_nodes) { + /* ksm page forked */ get_page(page); return page; } - while (node) { + nid = get_kpfn_nid(page_to_pfn(page)); + root = root_stable_tree + nid; +again: + new = &root->rb_node; + parent = NULL; + + while (*new) { struct page *tree_page; int ret; cond_resched(); - stable_node = rb_entry(node, struct stable_node, node); - tree_page = get_ksm_page(stable_node); + stable_node = rb_entry(*new, struct stable_node, node); + tree_page = get_ksm_page(stable_node, false); if (!tree_page) return NULL; ret = memcmp_pages(page, tree_page); + put_page(tree_page); - if (ret < 0) { - put_page(tree_page); - node = node->rb_left; - } else if (ret > 0) { - put_page(tree_page); - node = node->rb_right; - } else - return tree_page; + parent = *new; + if (ret < 0) + new = &parent->rb_left; + else if (ret > 0) + new = &parent->rb_right; + else { + /* + * Lock and unlock the stable_node's page (which + * might already have been migrated) so that page + * migration is sure to notice its raised count. + * It would be more elegant to return stable_node + * than kpage, but that involves more changes. + */ + tree_page = get_ksm_page(stable_node, true); + if (tree_page) { + unlock_page(tree_page); + if (get_kpfn_nid(stable_node->kpfn) != + NUMA(stable_node->nid)) { + put_page(tree_page); + goto replace; + } + return tree_page; + } + /* + * There is now a place for page_node, but the tree may + * have been rebalanced, so re-evaluate parent and new. + */ + if (page_node) + goto again; + return NULL; + } } - return NULL; + if (!page_node) + return NULL; + + list_del(&page_node->list); + DO_NUMA(page_node->nid = nid); + rb_link_node(&page_node->node, parent, new); + rb_insert_color(&page_node->node, root); + get_page(page); + return page; + +replace: + if (page_node) { + list_del(&page_node->list); + DO_NUMA(page_node->nid = nid); + rb_replace_node(&stable_node->node, &page_node->node, root); + get_page(page); + } else { + rb_erase(&stable_node->node, root); + page = NULL; + } + stable_node->head = &migrate_nodes; + list_add(&stable_node->list, stable_node->head); + return page; } /* - * stable_tree_insert - insert rmap_item pointing to new ksm page + * stable_tree_insert - insert stable tree node pointing to new ksm page * into the stable tree. * * This function returns the stable tree node just allocated on success, @@ -1039,17 +1250,25 @@ static struct page *stable_tree_search(struct page *page) */ static struct stable_node *stable_tree_insert(struct page *kpage) { - struct rb_node **new = &root_stable_tree.rb_node; + int nid; + unsigned long kpfn; + struct rb_root *root; + struct rb_node **new; struct rb_node *parent = NULL; struct stable_node *stable_node; + kpfn = page_to_pfn(kpage); + nid = get_kpfn_nid(kpfn); + root = root_stable_tree + nid; + new = &root->rb_node; + while (*new) { struct page *tree_page; int ret; cond_resched(); stable_node = rb_entry(*new, struct stable_node, node); - tree_page = get_ksm_page(stable_node); + tree_page = get_ksm_page(stable_node, false); if (!tree_page) return NULL; @@ -1075,13 +1294,12 @@ static struct stable_node *stable_tree_insert(struct page *kpage) if (!stable_node) return NULL; - rb_link_node(&stable_node->node, parent, new); - rb_insert_color(&stable_node->node, &root_stable_tree); - INIT_HLIST_HEAD(&stable_node->hlist); - - stable_node->kpfn = page_to_pfn(kpage); + stable_node->kpfn = kpfn; set_page_stable_node(kpage, stable_node); + DO_NUMA(stable_node->nid = nid); + rb_link_node(&stable_node->node, parent, new); + rb_insert_color(&stable_node->node, root); return stable_node; } @@ -1104,10 +1322,15 @@ static struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, struct page *page, struct page **tree_pagep) - { - struct rb_node **new = &root_unstable_tree.rb_node; + struct rb_node **new; + struct rb_root *root; struct rb_node *parent = NULL; + int nid; + + nid = get_kpfn_nid(page_to_pfn(page)); + root = root_unstable_tree + nid; + new = &root->rb_node; while (*new) { struct rmap_item *tree_rmap_item; @@ -1137,6 +1360,15 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, } else if (ret > 0) { put_page(tree_page); new = &parent->rb_right; + } else if (!ksm_merge_across_nodes && + page_to_nid(tree_page) != nid) { + /* + * If tree_page has been migrated to another NUMA node, + * it will be flushed out and put in the right unstable + * tree next time: only merge with it when across_nodes. + */ + put_page(tree_page); + return NULL; } else { *tree_pagep = tree_page; return tree_rmap_item; @@ -1145,8 +1377,9 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, rmap_item->address |= UNSTABLE_FLAG; rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK); + DO_NUMA(rmap_item->nid = nid); rb_link_node(&rmap_item->node, parent, new); - rb_insert_color(&rmap_item->node, &root_unstable_tree); + rb_insert_color(&rmap_item->node, root); ksm_pages_unshared++; return NULL; @@ -1188,10 +1421,29 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) unsigned int checksum; int err; - remove_rmap_item_from_tree(rmap_item); + stable_node = page_stable_node(page); + if (stable_node) { + if (stable_node->head != &migrate_nodes && + get_kpfn_nid(stable_node->kpfn) != NUMA(stable_node->nid)) { + rb_erase(&stable_node->node, + root_stable_tree + NUMA(stable_node->nid)); + stable_node->head = &migrate_nodes; + list_add(&stable_node->list, stable_node->head); + } + if (stable_node->head != &migrate_nodes && + rmap_item->head == stable_node) + return; + } /* We first start with searching the page inside the stable tree */ kpage = stable_tree_search(page); + if (kpage == page && rmap_item->head == stable_node) { + put_page(kpage); + return; + } + + remove_rmap_item_from_tree(rmap_item); + if (kpage) { err = try_to_merge_with_ksm_page(rmap_item, page, kpage); if (!err) { @@ -1225,14 +1477,11 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) kpage = try_to_merge_two_pages(rmap_item, page, tree_rmap_item, tree_page); put_page(tree_page); - /* - * As soon as we merge this page, we want to remove the - * rmap_item of the page we have merged with from the unstable - * tree, and insert it instead as new node in the stable tree. - */ if (kpage) { - remove_rmap_item_from_tree(tree_rmap_item); - + /* + * The pages were successfully merged: insert new + * node in the stable tree and add both rmap_items. + */ lock_page(kpage); stable_node = stable_tree_insert(kpage); if (stable_node) { @@ -1289,6 +1538,7 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) struct mm_slot *slot; struct vm_area_struct *vma; struct rmap_item *rmap_item; + int nid; if (list_empty(&ksm_mm_head.mm_list)) return NULL; @@ -1307,7 +1557,29 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) */ lru_add_drain_all(); - root_unstable_tree = RB_ROOT; + /* + * Whereas stale stable_nodes on the stable_tree itself + * get pruned in the regular course of stable_tree_search(), + * those moved out to the migrate_nodes list can accumulate: + * so prune them once before each full scan. + */ + if (!ksm_merge_across_nodes) { + struct stable_node *stable_node; + struct list_head *this, *next; + struct page *page; + + list_for_each_safe(this, next, &migrate_nodes) { + stable_node = list_entry(this, + struct stable_node, list); + page = get_ksm_page(stable_node, false); + if (page) + put_page(page); + cond_resched(); + } + } + + for (nid = 0; nid < ksm_nr_node_ids; nid++) + root_unstable_tree[nid] = RB_ROOT; spin_lock(&ksm_mmlist_lock); slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list); @@ -1392,7 +1664,7 @@ next_mm: * or when all VM_MERGEABLE areas have been unmapped (and * mmap_sem then protects against race with MADV_MERGEABLE). */ - hlist_del(&slot->link); + hash_del(&slot->link); list_del(&slot->mm_list); spin_unlock(&ksm_mmlist_lock); @@ -1428,8 +1700,7 @@ static void ksm_do_scan(unsigned int scan_npages) rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) return; - if (!PageKsm(page) || !in_stable_tree(rmap_item)) - cmp_and_merge_page(page, rmap_item); + cmp_and_merge_page(page, rmap_item); put_page(page); } } @@ -1446,6 +1717,7 @@ static int ksm_scan_thread(void *nothing) while (!kthread_should_stop()) { mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); if (ksmd_should_run()) ksm_do_scan(ksm_thread_pages_to_scan); mutex_unlock(&ksm_thread_mutex); @@ -1525,11 +1797,19 @@ int __ksm_enter(struct mm_struct *mm) spin_lock(&ksm_mmlist_lock); insert_to_mm_slots_hash(mm, mm_slot); /* - * Insert just behind the scanning cursor, to let the area settle + * When KSM_RUN_MERGE (or KSM_RUN_STOP), + * insert just behind the scanning cursor, to let the area settle * down a little; when fork is followed by immediate exec, we don't * want ksmd to waste time setting up and tearing down an rmap_list. + * + * But when KSM_RUN_UNMERGE, it's important to insert ahead of its + * scanning cursor, otherwise KSM pages in newly forked mms will be + * missed: then we might as well insert at the end of the list. */ - list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list); + if (ksm_run & KSM_RUN_UNMERGE) + list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list); + else + list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list); spin_unlock(&ksm_mmlist_lock); set_bit(MMF_VM_MERGEABLE, &mm->flags); @@ -1559,7 +1839,7 @@ void __ksm_exit(struct mm_struct *mm) mm_slot = get_mm_slot(mm); if (mm_slot && ksm_scan.mm_slot != mm_slot) { if (!mm_slot->rmap_list) { - hlist_del(&mm_slot->link); + hash_del(&mm_slot->link); list_del(&mm_slot->mm_list); easy_to_free = 1; } else { @@ -1579,47 +1859,57 @@ void __ksm_exit(struct mm_struct *mm) } } -struct page *ksm_does_need_to_copy(struct page *page, +struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { + struct anon_vma *anon_vma = page_anon_vma(page); struct page *new_page; + if (PageKsm(page)) { + if (page_stable_node(page) && + !(ksm_run & KSM_RUN_UNMERGE)) + return page; /* no need to copy it */ + } else if (!anon_vma) { + return page; /* no need to copy it */ + } else if (anon_vma->root == vma->anon_vma->root && + page->index == linear_page_index(vma, address)) { + return page; /* still no need to copy it */ + } + if (!PageUptodate(page)) + return page; /* let do_swap_page report the error */ + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (new_page) { copy_user_highpage(new_page, page, address, vma); SetPageDirty(new_page); __SetPageUptodate(new_page); - SetPageSwapBacked(new_page); __set_page_locked(new_page); - - if (!mlocked_vma_newpage(vma, new_page)) - lru_cache_add_lru(new_page, LRU_ACTIVE_ANON); - else - add_page_to_unevictable_list(new_page); } return new_page; } -int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, - unsigned long *vm_flags) +int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) { struct stable_node *stable_node; struct rmap_item *rmap_item; - struct hlist_node *hlist; - unsigned int mapcount = page_mapcount(page); - int referenced = 0; + int ret = SWAP_AGAIN; int search_new_forks = 0; - VM_BUG_ON(!PageKsm(page)); - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageKsm(page), page); + + /* + * Rely on the page lock to protect against concurrent modifications + * to that page's node of the stable tree. + */ + VM_BUG_ON_PAGE(!PageLocked(page), page); stable_node = page_stable_node(page); if (!stable_node) - return 0; + return ret; again: - hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; struct anon_vma_chain *vmac; struct vm_area_struct *vma; @@ -1640,115 +1930,16 @@ again: if ((rmap_item->mm == vma->vm_mm) == search_new_forks) continue; - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - - referenced += page_referenced_one(page, vma, - rmap_item->address, &mapcount, vm_flags); - if (!search_new_forks || !mapcount) - break; - } - anon_vma_unlock_read(anon_vma); - if (!mapcount) - goto out; - } - if (!search_new_forks++) - goto again; -out: - return referenced; -} - -int try_to_unmap_ksm(struct page *page, enum ttu_flags flags) -{ - struct stable_node *stable_node; - struct hlist_node *hlist; - struct rmap_item *rmap_item; - int ret = SWAP_AGAIN; - int search_new_forks = 0; - - VM_BUG_ON(!PageKsm(page)); - VM_BUG_ON(!PageLocked(page)); - - stable_node = page_stable_node(page); - if (!stable_node) - return SWAP_FAIL; -again: - hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { - struct anon_vma *anon_vma = rmap_item->anon_vma; - struct anon_vma_chain *vmac; - struct vm_area_struct *vma; - - anon_vma_lock_read(anon_vma); - anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, - 0, ULONG_MAX) { - vma = vmac->vma; - if (rmap_item->address < vma->vm_start || - rmap_item->address >= vma->vm_end) - continue; - /* - * Initially we examine only the vma which covers this - * rmap_item; but later, if there is still work to do, - * we examine covering vmas in other mms: in case they - * were forked from the original since ksmd passed. - */ - if ((rmap_item->mm == vma->vm_mm) == search_new_forks) + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - ret = try_to_unmap_one(page, vma, - rmap_item->address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) { + ret = rwc->rmap_one(page, vma, + rmap_item->address, rwc->arg); + if (ret != SWAP_AGAIN) { anon_vma_unlock_read(anon_vma); goto out; } - } - anon_vma_unlock_read(anon_vma); - } - if (!search_new_forks++) - goto again; -out: - return ret; -} - -#ifdef CONFIG_MIGRATION -int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) -{ - struct stable_node *stable_node; - struct hlist_node *hlist; - struct rmap_item *rmap_item; - int ret = SWAP_AGAIN; - int search_new_forks = 0; - - VM_BUG_ON(!PageKsm(page)); - VM_BUG_ON(!PageLocked(page)); - - stable_node = page_stable_node(page); - if (!stable_node) - return ret; -again: - hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { - struct anon_vma *anon_vma = rmap_item->anon_vma; - struct anon_vma_chain *vmac; - struct vm_area_struct *vma; - - anon_vma_lock_read(anon_vma); - anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, - 0, ULONG_MAX) { - vma = vmac->vma; - if (rmap_item->address < vma->vm_start || - rmap_item->address >= vma->vm_end) - continue; - /* - * Initially we examine only the vma which covers this - * rmap_item; but later, if there is still work to do, - * we examine covering vmas in other mms: in case they - * were forked from the original since ksmd passed. - */ - if ((rmap_item->mm == vma->vm_mm) == search_new_forks) - continue; - - ret = rmap_one(page, vma, rmap_item->address, arg); - if (ret != SWAP_AGAIN) { + if (rwc->done && rwc->done(page)) { anon_vma_unlock_read(anon_vma); goto out; } @@ -1761,76 +1952,128 @@ out: return ret; } +#ifdef CONFIG_MIGRATION void ksm_migrate_page(struct page *newpage, struct page *oldpage) { struct stable_node *stable_node; - VM_BUG_ON(!PageLocked(oldpage)); - VM_BUG_ON(!PageLocked(newpage)); - VM_BUG_ON(newpage->mapping != oldpage->mapping); + VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage); stable_node = page_stable_node(newpage); if (stable_node) { - VM_BUG_ON(stable_node->kpfn != page_to_pfn(oldpage)); + VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage); stable_node->kpfn = page_to_pfn(newpage); + /* + * newpage->mapping was set in advance; now we need smp_wmb() + * to make sure that the new stable_node->kpfn is visible + * to get_ksm_page() before it can see that oldpage->mapping + * has gone stale (or that PageSwapCache has been cleared). + */ + smp_wmb(); + set_page_stable_node(oldpage, NULL); } } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_HOTREMOVE -static struct stable_node *ksm_check_stable_tree(unsigned long start_pfn, - unsigned long end_pfn) +static int just_wait(void *word) { - struct rb_node *node; + schedule(); + return 0; +} - for (node = rb_first(&root_stable_tree); node; node = rb_next(node)) { - struct stable_node *stable_node; +static void wait_while_offlining(void) +{ + while (ksm_run & KSM_RUN_OFFLINE) { + mutex_unlock(&ksm_thread_mutex); + wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), + just_wait, TASK_UNINTERRUPTIBLE); + mutex_lock(&ksm_thread_mutex); + } +} - stable_node = rb_entry(node, struct stable_node, node); +static void ksm_check_stable_tree(unsigned long start_pfn, + unsigned long end_pfn) +{ + struct stable_node *stable_node; + struct list_head *this, *next; + struct rb_node *node; + int nid; + + for (nid = 0; nid < ksm_nr_node_ids; nid++) { + node = rb_first(root_stable_tree + nid); + while (node) { + stable_node = rb_entry(node, struct stable_node, node); + if (stable_node->kpfn >= start_pfn && + stable_node->kpfn < end_pfn) { + /* + * Don't get_ksm_page, page has already gone: + * which is why we keep kpfn instead of page* + */ + remove_node_from_stable_tree(stable_node); + node = rb_first(root_stable_tree + nid); + } else + node = rb_next(node); + cond_resched(); + } + } + list_for_each_safe(this, next, &migrate_nodes) { + stable_node = list_entry(this, struct stable_node, list); if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) - return stable_node; + remove_node_from_stable_tree(stable_node); + cond_resched(); } - return NULL; } static int ksm_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; - struct stable_node *stable_node; switch (action) { case MEM_GOING_OFFLINE: /* - * Keep it very simple for now: just lock out ksmd and - * MADV_UNMERGEABLE while any memory is going offline. - * mutex_lock_nested() is necessary because lockdep was alarmed - * that here we take ksm_thread_mutex inside notifier chain - * mutex, and later take notifier chain mutex inside - * ksm_thread_mutex to unlock it. But that's safe because both - * are inside mem_hotplug_mutex. + * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items() + * and remove_all_stable_nodes() while memory is going offline: + * it is unsafe for them to touch the stable tree at this time. + * But unmerge_ksm_pages(), rmap lookups and other entry points + * which do not need the ksm_thread_mutex are all safe. */ - mutex_lock_nested(&ksm_thread_mutex, SINGLE_DEPTH_NESTING); + mutex_lock(&ksm_thread_mutex); + ksm_run |= KSM_RUN_OFFLINE; + mutex_unlock(&ksm_thread_mutex); break; case MEM_OFFLINE: /* * Most of the work is done by page migration; but there might * be a few stable_nodes left over, still pointing to struct - * pages which have been offlined: prune those from the tree. + * pages which have been offlined: prune those from the tree, + * otherwise get_ksm_page() might later try to access a + * non-existent struct page. */ - while ((stable_node = ksm_check_stable_tree(mn->start_pfn, - mn->start_pfn + mn->nr_pages)) != NULL) - remove_node_from_stable_tree(stable_node); + ksm_check_stable_tree(mn->start_pfn, + mn->start_pfn + mn->nr_pages); /* fallthrough */ case MEM_CANCEL_OFFLINE: + mutex_lock(&ksm_thread_mutex); + ksm_run &= ~KSM_RUN_OFFLINE; mutex_unlock(&ksm_thread_mutex); + + smp_mb(); /* wake_up_bit advises this */ + wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE)); break; } return NOTIFY_OK; } +#else +static void wait_while_offlining(void) +{ +} #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_SYSFS @@ -1857,7 +2100,7 @@ static ssize_t sleep_millisecs_store(struct kobject *kobj, unsigned long msecs; int err; - err = strict_strtoul(buf, 10, &msecs); + err = kstrtoul(buf, 10, &msecs); if (err || msecs > UINT_MAX) return -EINVAL; @@ -1880,7 +2123,7 @@ static ssize_t pages_to_scan_store(struct kobject *kobj, int err; unsigned long nr_pages; - err = strict_strtoul(buf, 10, &nr_pages); + err = kstrtoul(buf, 10, &nr_pages); if (err || nr_pages > UINT_MAX) return -EINVAL; @@ -1893,7 +2136,7 @@ KSM_ATTR(pages_to_scan); static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", ksm_run); + return sprintf(buf, "%lu\n", ksm_run); } static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -1902,7 +2145,7 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, int err; unsigned long flags; - err = strict_strtoul(buf, 10, &flags); + err = kstrtoul(buf, 10, &flags); if (err || flags > UINT_MAX) return -EINVAL; if (flags > KSM_RUN_UNMERGE) @@ -1916,6 +2159,7 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, */ mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); if (ksm_run != flags) { ksm_run = flags; if (flags & KSM_RUN_UNMERGE) { @@ -1937,6 +2181,64 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, } KSM_ATTR(run); +#ifdef CONFIG_NUMA +static ssize_t merge_across_nodes_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", ksm_merge_across_nodes); +} + +static ssize_t merge_across_nodes_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long knob; + + err = kstrtoul(buf, 10, &knob); + if (err) + return err; + if (knob > 1) + return -EINVAL; + + mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); + if (ksm_merge_across_nodes != knob) { + if (ksm_pages_shared || remove_all_stable_nodes()) + err = -EBUSY; + else if (root_stable_tree == one_stable_tree) { + struct rb_root *buf; + /* + * This is the first time that we switch away from the + * default of merging across nodes: must now allocate + * a buffer to hold as many roots as may be needed. + * Allocate stable and unstable together: + * MAXSMP NODES_SHIFT 10 will use 16kB. + */ + buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf), + GFP_KERNEL); + /* Let us assume that RB_ROOT is NULL is zero */ + if (!buf) + err = -ENOMEM; + else { + root_stable_tree = buf; + root_unstable_tree = buf + nr_node_ids; + /* Stable tree is empty but not the unstable */ + root_unstable_tree[0] = one_unstable_tree[0]; + } + } + if (!err) { + ksm_merge_across_nodes = knob; + ksm_nr_node_ids = knob ? 1 : nr_node_ids; + } + } + mutex_unlock(&ksm_thread_mutex); + + return err ? err : count; +} +KSM_ATTR(merge_across_nodes); +#endif + static ssize_t pages_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -1991,6 +2293,9 @@ static struct attribute *ksm_attrs[] = { &pages_unshared_attr.attr, &pages_volatile_attr.attr, &full_scans_attr.attr, +#ifdef CONFIG_NUMA + &merge_across_nodes_attr.attr, +#endif NULL, }; @@ -2029,10 +2334,7 @@ static int __init ksm_init(void) #endif /* CONFIG_SYSFS */ #ifdef CONFIG_MEMORY_HOTREMOVE - /* - * Choose a high priority since the callback takes ksm_thread_mutex: - * later callbacks could only be taking locks which nest within that. - */ + /* There is no significance to this priority 100 */ hotplug_memory_notifier(ksm_memory_callback, 100); #endif return 0; @@ -2042,4 +2344,4 @@ out_free: out: return err; } -module_init(ksm_init) +subsys_initcall(ksm_init); diff --git a/mm/list_lru.c b/mm/list_lru.c new file mode 100644 index 00000000000..f1a0db19417 --- /dev/null +++ b/mm/list_lru.c @@ -0,0 +1,152 @@ +/* + * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. + * Authors: David Chinner and Glauber Costa + * + * Generic LRU infrastructure + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/list_lru.h> +#include <linux/slab.h> + +bool list_lru_add(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + WARN_ON_ONCE(nlru->nr_items < 0); + if (list_empty(item)) { + list_add_tail(item, &nlru->list); + if (nlru->nr_items++ == 0) + node_set(nid, lru->active_nodes); + spin_unlock(&nlru->lock); + return true; + } + spin_unlock(&nlru->lock); + return false; +} +EXPORT_SYMBOL_GPL(list_lru_add); + +bool list_lru_del(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + if (!list_empty(item)) { + list_del_init(item); + if (--nlru->nr_items == 0) + node_clear(nid, lru->active_nodes); + WARN_ON_ONCE(nlru->nr_items < 0); + spin_unlock(&nlru->lock); + return true; + } + spin_unlock(&nlru->lock); + return false; +} +EXPORT_SYMBOL_GPL(list_lru_del); + +unsigned long +list_lru_count_node(struct list_lru *lru, int nid) +{ + unsigned long count = 0; + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + WARN_ON_ONCE(nlru->nr_items < 0); + count += nlru->nr_items; + spin_unlock(&nlru->lock); + + return count; +} +EXPORT_SYMBOL_GPL(list_lru_count_node); + +unsigned long +list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, + void *cb_arg, unsigned long *nr_to_walk) +{ + + struct list_lru_node *nlru = &lru->node[nid]; + struct list_head *item, *n; + unsigned long isolated = 0; + + spin_lock(&nlru->lock); +restart: + list_for_each_safe(item, n, &nlru->list) { + enum lru_status ret; + + /* + * decrement nr_to_walk first so that we don't livelock if we + * get stuck on large numbesr of LRU_RETRY items + */ + if (!*nr_to_walk) + break; + --*nr_to_walk; + + ret = isolate(item, &nlru->lock, cb_arg); + switch (ret) { + case LRU_REMOVED_RETRY: + assert_spin_locked(&nlru->lock); + case LRU_REMOVED: + if (--nlru->nr_items == 0) + node_clear(nid, lru->active_nodes); + WARN_ON_ONCE(nlru->nr_items < 0); + isolated++; + /* + * If the lru lock has been dropped, our list + * traversal is now invalid and so we have to + * restart from scratch. + */ + if (ret == LRU_REMOVED_RETRY) + goto restart; + break; + case LRU_ROTATE: + list_move_tail(item, &nlru->list); + break; + case LRU_SKIP: + break; + case LRU_RETRY: + /* + * The lru lock has been dropped, our list traversal is + * now invalid and so we have to restart from scratch. + */ + assert_spin_locked(&nlru->lock); + goto restart; + default: + BUG(); + } + } + + spin_unlock(&nlru->lock); + return isolated; +} +EXPORT_SYMBOL_GPL(list_lru_walk_node); + +int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key) +{ + int i; + size_t size = sizeof(*lru->node) * nr_node_ids; + + lru->node = kzalloc(size, GFP_KERNEL); + if (!lru->node) + return -ENOMEM; + + nodes_clear(lru->active_nodes); + for (i = 0; i < nr_node_ids; i++) { + spin_lock_init(&lru->node[i].lock); + if (key) + lockdep_set_class(&lru->node[i].lock, key); + INIT_LIST_HEAD(&lru->node[i].list); + lru->node[i].nr_items = 0; + } + return 0; +} +EXPORT_SYMBOL_GPL(list_lru_init_key); + +void list_lru_destroy(struct list_lru *lru) +{ + kfree(lru->node); +} +EXPORT_SYMBOL_GPL(list_lru_destroy); diff --git a/mm/madvise.c b/mm/madvise.c index 03dfa5c7adb..a402f8fdc68 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -16,6 +16,9 @@ #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> +#include <linux/blkdev.h> +#include <linux/swap.h> +#include <linux/swapops.h> /* * Any behaviour which results in changes to the vma->vm_flags needs to @@ -39,11 +42,11 @@ static int madvise_need_mmap_write(int behavior) * We can potentially split a vm area into separate * areas, each area with its own behavior. */ -static long madvise_behavior(struct vm_area_struct * vma, +static long madvise_behavior(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, int behavior) { - struct mm_struct * mm = vma->vm_mm; + struct mm_struct *mm = vma->vm_mm; int error = 0; pgoff_t pgoff; unsigned long new_flags = vma->vm_flags; @@ -131,15 +134,105 @@ out: return error; } +#ifdef CONFIG_SWAP +static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, + unsigned long end, struct mm_walk *walk) +{ + pte_t *orig_pte; + struct vm_area_struct *vma = walk->private; + unsigned long index; + + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + return 0; + + for (index = start; index != end; index += PAGE_SIZE) { + pte_t pte; + swp_entry_t entry; + struct page *page; + spinlock_t *ptl; + + orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl); + pte = *(orig_pte + ((index - start) / PAGE_SIZE)); + pte_unmap_unlock(orig_pte, ptl); + + if (pte_present(pte) || pte_none(pte) || pte_file(pte)) + continue; + entry = pte_to_swp_entry(pte); + if (unlikely(non_swap_entry(entry))) + continue; + + page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, + vma, index); + if (page) + page_cache_release(page); + } + + return 0; +} + +static void force_swapin_readahead(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + struct mm_walk walk = { + .mm = vma->vm_mm, + .pmd_entry = swapin_walk_pmd_entry, + .private = vma, + }; + + walk_page_range(start, end, &walk); + + lru_add_drain(); /* Push any new pages onto the LRU now */ +} + +static void force_shm_swapin_readahead(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct address_space *mapping) +{ + pgoff_t index; + struct page *page; + swp_entry_t swap; + + for (; start < end; start += PAGE_SIZE) { + index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + + page = find_get_entry(mapping, index); + if (!radix_tree_exceptional_entry(page)) { + if (page) + page_cache_release(page); + continue; + } + swap = radix_to_swp_entry(page); + page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE, + NULL, 0); + if (page) + page_cache_release(page); + } + + lru_add_drain(); /* Push any new pages onto the LRU now */ +} +#endif /* CONFIG_SWAP */ + /* * Schedule all required I/O operations. Do not wait for completion. */ -static long madvise_willneed(struct vm_area_struct * vma, - struct vm_area_struct ** prev, +static long madvise_willneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct file *file = vma->vm_file; +#ifdef CONFIG_SWAP + if (!file || mapping_cap_swap_backed(file->f_mapping)) { + *prev = vma; + if (!file) + force_swapin_readahead(vma, start, end); + else + force_shm_swapin_readahead(vma, start, end, + file->f_mapping); + return 0; + } +#endif + if (!file) return -EBADF; @@ -177,8 +270,8 @@ static long madvise_willneed(struct vm_area_struct * vma, * An interface that causes the system to free clean pages and flush * dirty pages is already available as msync(MS_INVALIDATE). */ -static long madvise_dontneed(struct vm_area_struct * vma, - struct vm_area_struct ** prev, +static long madvise_dontneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, unsigned long end) { *prev = vma; @@ -250,29 +343,35 @@ static long madvise_remove(struct vm_area_struct *vma, */ static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end) { - int ret = 0; - + struct page *p; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - for (; start < end; start += PAGE_SIZE) { - struct page *p; - int ret = get_user_pages_fast(start, 1, 0, &p); + for (; start < end; start += PAGE_SIZE << + compound_order(compound_head(p))) { + int ret; + + ret = get_user_pages_fast(start, 1, 0, &p); if (ret != 1) return ret; + + if (PageHWPoison(p)) { + put_page(p); + continue; + } if (bhv == MADV_SOFT_OFFLINE) { - printk(KERN_INFO "Soft offlining page %lx at %lx\n", + pr_info("Soft offlining page %#lx at %#lx\n", page_to_pfn(p), start); ret = soft_offline_page(p, MF_COUNT_INCREASED); if (ret) - break; + return ret; continue; } - printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n", + pr_info("Injecting memory failure for page %#lx at %#lx\n", page_to_pfn(p), start); /* Ignore return value for now */ memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED); } - return ret; + return 0; } #endif @@ -366,11 +465,12 @@ madvise_behavior_valid(int behavior) SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { unsigned long end, tmp; - struct vm_area_struct * vma, *prev; + struct vm_area_struct *vma, *prev; int unmapped_error = 0; int error = -EINVAL; int write; size_t len; + struct blk_plug plug; #ifdef CONFIG_MEMORY_FAILURE if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE) @@ -379,27 +479,27 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) if (!madvise_behavior_valid(behavior)) return error; - write = madvise_need_mmap_write(behavior); - if (write) - down_write(¤t->mm->mmap_sem); - else - down_read(¤t->mm->mmap_sem); - if (start & ~PAGE_MASK) - goto out; + return error; len = (len_in + ~PAGE_MASK) & PAGE_MASK; /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) - goto out; + return error; end = start + len; if (end < start) - goto out; + return error; error = 0; if (end == start) - goto out; + return error; + + write = madvise_need_mmap_write(behavior); + if (write) + down_write(¤t->mm->mmap_sem); + else + down_read(¤t->mm->mmap_sem); /* * If the interval [start,end) covers some unmapped address @@ -410,6 +510,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) if (vma && start > vma->vm_start) prev = vma; + blk_start_plug(&plug); for (;;) { /* Still start < end. */ error = -ENOMEM; @@ -445,6 +546,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) vma = find_vma(current->mm, start); } out: + blk_finish_plug(&plug); if (write) up_write(¤t->mm->mmap_sem); else diff --git a/mm/memblock.c b/mm/memblock.c index 88adc8afb61..6d2f219a48b 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,8 +20,16 @@ #include <linux/seq_file.h> #include <linux/memblock.h> +#include <asm-generic/sections.h> +#include <linux/io.h> + +#include "internal.h" + static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock; +#endif struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, @@ -32,10 +40,20 @@ struct memblock memblock __initdata_memblock = { .reserved.cnt = 1, /* empty dummy entry */ .reserved.max = INIT_MEMBLOCK_REGIONS, +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP + .physmem.regions = memblock_physmem_init_regions, + .physmem.cnt = 1, /* empty dummy entry */ + .physmem.max = INIT_PHYSMEM_REGIONS, +#endif + + .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; int memblock_debug __initdata_memblock; +#ifdef CONFIG_MOVABLE_NODE +bool movable_node_enabled __initdata_memblock = false; +#endif static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock = 0; static int memblock_reserved_in_slab __initdata_memblock = 0; @@ -82,33 +100,57 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type, return (i < type->cnt) ? i : -1; } -/** - * memblock_find_in_range_node - find free area in given range and node +/* + * __memblock_find_range_bottom_up - find free area utility in bottom-up * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} * @size: size of free area to find * @align: alignment of free area to find - * @nid: nid of the free area to find, %MAX_NUMNODES for any node + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * - * Find @size free area aligned to @align in the specified range and node. + * Utility called from memblock_find_in_range_node(), find free area bottom-up. * * RETURNS: - * Found address on success, %0 on failure. + * Found address on success, 0 on failure. */ -phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, - phys_addr_t end, phys_addr_t size, - phys_addr_t align, int nid) +static phys_addr_t __init_memblock +__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align, int nid) { phys_addr_t this_start, this_end, cand; u64 i; - /* pump up @end */ - if (end == MEMBLOCK_ALLOC_ACCESSIBLE) - end = memblock.current_limit; + for_each_free_mem_range(i, nid, &this_start, &this_end, NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); - /* avoid allocating the first page */ - start = max_t(phys_addr_t, start, PAGE_SIZE); - end = max(start, end); + cand = round_up(this_start, align); + if (cand < this_end && this_end - cand >= size) + return cand; + } + + return 0; +} + +/** + * __memblock_find_range_top_down - find free area utility, in top-down + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @size: size of free area to find + * @align: alignment of free area to find + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Utility called from memblock_find_in_range_node(), find free area top-down. + * + * RETURNS: + * Found address on success, 0 on failure. + */ +static phys_addr_t __init_memblock +__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align, int nid) +{ + phys_addr_t this_start, this_end, cand; + u64 i; for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); @@ -121,10 +163,81 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, if (cand >= this_start) return cand; } + return 0; } /** + * memblock_find_in_range_node - find free area in given range and node + * @size: size of free area to find + * @align: alignment of free area to find + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Find @size free area aligned to @align in the specified range and node. + * + * When allocation direction is bottom-up, the @start should be greater + * than the end of the kernel image. Otherwise, it will be trimmed. The + * reason is that we want the bottom-up allocation just near the kernel + * image so it is highly likely that the allocated memory and the kernel + * will reside in the same node. + * + * If bottom-up allocation failed, will try to allocate memory top-down. + * + * RETURNS: + * Found address on success, 0 on failure. + */ +phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, + phys_addr_t align, phys_addr_t start, + phys_addr_t end, int nid) +{ + int ret; + phys_addr_t kernel_end; + + /* pump up @end */ + if (end == MEMBLOCK_ALLOC_ACCESSIBLE) + end = memblock.current_limit; + + /* avoid allocating the first page */ + start = max_t(phys_addr_t, start, PAGE_SIZE); + end = max(start, end); + kernel_end = __pa_symbol(_end); + + /* + * try bottom-up allocation only when bottom-up mode + * is set and @end is above the kernel image. + */ + if (memblock_bottom_up() && end > kernel_end) { + phys_addr_t bottom_up_start; + + /* make sure we will allocate above the kernel */ + bottom_up_start = max(start, kernel_end); + + /* ok, try bottom-up allocation first */ + ret = __memblock_find_range_bottom_up(bottom_up_start, end, + size, align, nid); + if (ret) + return ret; + + /* + * we always limit bottom-up allocation above the kernel, + * but top-down allocation doesn't have the limit, so + * retrying top-down allocation may succeed when bottom-up + * allocation failed. + * + * bottom-up allocation is expected to be fail very rarely, + * so we use WARN_ONCE() here to see the stack trace if + * fail happens. + */ + WARN_ONCE(1, "memblock: bottom-up allocation failed, " + "memory hotunplug may be affected\n"); + } + + return __memblock_find_range_top_down(start, end, size, align, nid); +} + +/** * memblock_find_in_range - find free area in given range * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} @@ -134,14 +247,14 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, * Find @size free area aligned to @align in the specified range. * * RETURNS: - * Found address on success, %0 on failure. + * Found address on success, 0 on failure. */ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { - return memblock_find_in_range_node(start, end, size, align, - MAX_NUMNODES); + return memblock_find_in_range_node(size, align, start, end, + NUMA_NO_NODE); } static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) @@ -157,10 +270,13 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u type->cnt = 1; type->regions[0].base = 0; type->regions[0].size = 0; + type->regions[0].flags = 0; memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK + phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info( phys_addr_t *addr) { @@ -173,6 +289,20 @@ phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info( memblock.reserved.max); } +phys_addr_t __init_memblock get_allocated_memblock_memory_regions_info( + phys_addr_t *addr) +{ + if (memblock.memory.regions == memblock_memory_init_regions) + return 0; + + *addr = __pa(memblock.memory.regions); + + return PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.memory.max); +} + +#endif + /** * memblock_double_array - double the size of the memblock regions array * @type: memblock type of the regions array being doubled @@ -307,7 +437,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type) if (this->base + this->size != next->base || memblock_get_region_node(this) != - memblock_get_region_node(next)) { + memblock_get_region_node(next) || + this->flags != next->flags) { BUG_ON(this->base + this->size > next->base); i++; continue; @@ -322,17 +453,20 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type) /** * memblock_insert_region - insert new memblock region - * @type: memblock type to insert into - * @idx: index for the insertion point - * @base: base address of the new region - * @size: size of the new region + * @type: memblock type to insert into + * @idx: index for the insertion point + * @base: base address of the new region + * @size: size of the new region + * @nid: node id of the new region + * @flags: flags of the new region * * Insert new memblock region [@base,@base+@size) into @type at @idx. * @type must already have extra room to accomodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, - phys_addr_t size, int nid) + phys_addr_t size, + int nid, unsigned long flags) { struct memblock_region *rgn = &type->regions[idx]; @@ -340,17 +474,19 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); rgn->base = base; rgn->size = size; + rgn->flags = flags; memblock_set_region_node(rgn, nid); type->cnt++; type->total_size += size; } /** - * memblock_add_region - add new memblock region + * memblock_add_range - add new memblock region * @type: memblock type to add new region into * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region + * @flags: flags of the new region * * Add new memblock region [@base,@base+@size) into @type. The new region * is allowed to overlap with existing ones - overlaps don't affect already @@ -360,8 +496,9 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, * RETURNS: * 0 on success, -errno on failure. */ -static int __init_memblock memblock_add_region(struct memblock_type *type, - phys_addr_t base, phys_addr_t size, int nid) +int __init_memblock memblock_add_range(struct memblock_type *type, + phys_addr_t base, phys_addr_t size, + int nid, unsigned long flags) { bool insert = false; phys_addr_t obase = base; @@ -376,6 +513,7 @@ static int __init_memblock memblock_add_region(struct memblock_type *type, WARN_ON(type->cnt != 1 || type->total_size); type->regions[0].base = base; type->regions[0].size = size; + type->regions[0].flags = flags; memblock_set_region_node(&type->regions[0], nid); type->total_size = size; return 0; @@ -406,7 +544,8 @@ repeat: nr_new++; if (insert) memblock_insert_region(type, i++, base, - rbase - base, nid); + rbase - base, nid, + flags); } /* area below @rend is dealt with, forget about it */ base = min(rend, end); @@ -416,7 +555,8 @@ repeat: if (base < end) { nr_new++; if (insert) - memblock_insert_region(type, i, base, end - base, nid); + memblock_insert_region(type, i, base, end - base, + nid, flags); } /* @@ -438,12 +578,13 @@ repeat: int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int nid) { - return memblock_add_region(&memblock.memory, base, size, nid); + return memblock_add_range(&memblock.memory, base, size, nid, 0); } int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { - return memblock_add_region(&memblock.memory, base, size, MAX_NUMNODES); + return memblock_add_range(&memblock.memory, base, size, + MAX_NUMNODES, 0); } /** @@ -498,7 +639,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, rgn->size -= base - rbase; type->total_size -= base - rbase; memblock_insert_region(type, i, rbase, base - rbase, - memblock_get_region_node(rgn)); + memblock_get_region_node(rgn), + rgn->flags); } else if (rend > end) { /* * @rgn intersects from above. Split and redo the @@ -508,7 +650,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, rgn->size -= end - rbase; type->total_size -= end - rbase; memblock_insert_region(type, i--, rbase, end - rbase, - memblock_get_region_node(rgn)); + memblock_get_region_node(rgn), + rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) @@ -520,8 +663,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, return 0; } -static int __init_memblock __memblock_remove(struct memblock_type *type, - phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_remove_range(struct memblock_type *type, + phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; @@ -537,43 +680,108 @@ static int __init_memblock __memblock_remove(struct memblock_type *type, int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) { - return __memblock_remove(&memblock.memory, base, size); + return memblock_remove_range(&memblock.memory, base, size); } + int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) { memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n", (unsigned long long)base, - (unsigned long long)base + size, + (unsigned long long)base + size - 1, (void *)_RET_IP_); - return __memblock_remove(&memblock.reserved, base, size); + kmemleak_free_part(__va(base), size); + return memblock_remove_range(&memblock.reserved, base, size); } -int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) +static int __init_memblock memblock_reserve_region(phys_addr_t base, + phys_addr_t size, + int nid, + unsigned long flags) { struct memblock_type *_rgn = &memblock.reserved; - memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n", + memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n", (unsigned long long)base, - (unsigned long long)base + size, - (void *)_RET_IP_); + (unsigned long long)base + size - 1, + flags, (void *)_RET_IP_); + + return memblock_add_range(_rgn, base, size, nid, flags); +} + +int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) +{ + return memblock_reserve_region(base, size, MAX_NUMNODES, 0); +} - return memblock_add_region(_rgn, base, size, MAX_NUMNODES); +/** + * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. + * @base: the base phys addr of the region + * @size: the size of the region + * + * This function isolates region [@base, @base + @size), and mark it with flag + * MEMBLOCK_HOTPLUG. + * + * Return 0 on succees, -errno on failure. + */ +int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) +{ + struct memblock_type *type = &memblock.memory; + int i, ret, start_rgn, end_rgn; + + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; + + for (i = start_rgn; i < end_rgn; i++) + memblock_set_region_flags(&type->regions[i], MEMBLOCK_HOTPLUG); + + memblock_merge_regions(type); + return 0; } /** - * __next_free_mem_range - next function for for_each_free_mem_range() + * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. + * @base: the base phys addr of the region + * @size: the size of the region + * + * This function isolates region [@base, @base + @size), and clear flag + * MEMBLOCK_HOTPLUG for the isolated regions. + * + * Return 0 on succees, -errno on failure. + */ +int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) +{ + struct memblock_type *type = &memblock.memory; + int i, ret, start_rgn, end_rgn; + + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; + + for (i = start_rgn; i < end_rgn; i++) + memblock_clear_region_flags(&type->regions[i], + MEMBLOCK_HOTPLUG); + + memblock_merge_regions(type); + return 0; +} + +/** + * __next__mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable - * @nid: nid: node selector, %MAX_NUMNODES for all nodes + * @nid: node selector, %NUMA_NO_NODE for all nodes + * @type_a: pointer to memblock_type from where the range is taken + * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * - * Find the first free area from *@idx which matches @nid, fill the out + * Find the first area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of - * *@idx contains index into memory region and the upper 32bit indexes the - * areas before each reserved region. For example, if reserved regions + * *@idx contains index into type_a and the upper 32bit indexes the + * areas before each region in type_b. For example, if type_b regions * look like the following, * * 0:[0-16), 1:[32-48), 2:[128-130) @@ -585,50 +793,77 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ -void __init_memblock __next_free_mem_range(u64 *idx, int nid, - phys_addr_t *out_start, - phys_addr_t *out_end, int *out_nid) +void __init_memblock __next_mem_range(u64 *idx, int nid, + struct memblock_type *type_a, + struct memblock_type *type_b, + phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) { - struct memblock_type *mem = &memblock.memory; - struct memblock_type *rsv = &memblock.reserved; - int mi = *idx & 0xffffffff; - int ri = *idx >> 32; + int idx_a = *idx & 0xffffffff; + int idx_b = *idx >> 32; + + if (WARN_ONCE(nid == MAX_NUMNODES, + "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + + for (; idx_a < type_a->cnt; idx_a++) { + struct memblock_region *m = &type_a->regions[idx_a]; - for ( ; mi < mem->cnt; mi++) { - struct memblock_region *m = &mem->regions[mi]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; + int m_nid = memblock_get_region_node(m); /* only memory regions are associated with nodes, check it */ - if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m)) + if (nid != NUMA_NO_NODE && nid != m_nid) continue; - /* scan areas before each reservation for intersection */ - for ( ; ri < rsv->cnt + 1; ri++) { - struct memblock_region *r = &rsv->regions[ri]; - phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0; - phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX; + if (!type_b) { + if (out_start) + *out_start = m_start; + if (out_end) + *out_end = m_end; + if (out_nid) + *out_nid = m_nid; + idx_a++; + *idx = (u32)idx_a | (u64)idx_b << 32; + return; + } + + /* scan areas before each reservation */ + for (; idx_b < type_b->cnt + 1; idx_b++) { + struct memblock_region *r; + phys_addr_t r_start; + phys_addr_t r_end; + + r = &type_b->regions[idx_b]; + r_start = idx_b ? r[-1].base + r[-1].size : 0; + r_end = idx_b < type_b->cnt ? + r->base : ULLONG_MAX; - /* if ri advanced past mi, break out to advance mi */ + /* + * if idx_b advanced past idx_a, + * break out to advance idx_a + */ if (r_start >= m_end) break; /* if the two regions intersect, we're done */ if (m_start < r_end) { if (out_start) - *out_start = max(m_start, r_start); + *out_start = + max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) - *out_nid = memblock_get_region_node(m); + *out_nid = m_nid; /* - * The region which ends first is advanced - * for the next iteration. + * The region which ends first is + * advanced for the next iteration. */ if (m_end <= r_end) - mi++; + idx_a++; else - ri++; - *idx = (u32)mi | (u64)ri << 32; + idx_b++; + *idx = (u32)idx_a | (u64)idx_b << 32; return; } } @@ -639,45 +874,80 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid, } /** - * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse() + * __next_mem_range_rev - generic next function for for_each_*_range_rev() + * + * Finds the next range from type_a which is not marked as unsuitable + * in type_b. + * * @idx: pointer to u64 loop variable - * @nid: nid: node selector, %MAX_NUMNODES for all nodes + * @nid: nid: node selector, %NUMA_NO_NODE for all nodes + * @type_a: pointer to memblock_type from where the range is taken + * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * - * Reverse of __next_free_mem_range(). + * Reverse of __next_mem_range(). */ -void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid, - phys_addr_t *out_start, - phys_addr_t *out_end, int *out_nid) +void __init_memblock __next_mem_range_rev(u64 *idx, int nid, + struct memblock_type *type_a, + struct memblock_type *type_b, + phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) { - struct memblock_type *mem = &memblock.memory; - struct memblock_type *rsv = &memblock.reserved; - int mi = *idx & 0xffffffff; - int ri = *idx >> 32; + int idx_a = *idx & 0xffffffff; + int idx_b = *idx >> 32; + + if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; if (*idx == (u64)ULLONG_MAX) { - mi = mem->cnt - 1; - ri = rsv->cnt; + idx_a = type_a->cnt - 1; + idx_b = type_b->cnt; } - for ( ; mi >= 0; mi--) { - struct memblock_region *m = &mem->regions[mi]; + for (; idx_a >= 0; idx_a--) { + struct memblock_region *m = &type_a->regions[idx_a]; + phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; + int m_nid = memblock_get_region_node(m); /* only memory regions are associated with nodes, check it */ - if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m)) + if (nid != NUMA_NO_NODE && nid != m_nid) + continue; + + /* skip hotpluggable memory regions if needed */ + if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) continue; - /* scan areas before each reservation for intersection */ - for ( ; ri >= 0; ri--) { - struct memblock_region *r = &rsv->regions[ri]; - phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0; - phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX; + if (!type_b) { + if (out_start) + *out_start = m_start; + if (out_end) + *out_end = m_end; + if (out_nid) + *out_nid = m_nid; + idx_a++; + *idx = (u32)idx_a | (u64)idx_b << 32; + return; + } + + /* scan areas before each reservation */ + for (; idx_b >= 0; idx_b--) { + struct memblock_region *r; + phys_addr_t r_start; + phys_addr_t r_end; + + r = &type_b->regions[idx_b]; + r_start = idx_b ? r[-1].base + r[-1].size : 0; + r_end = idx_b < type_b->cnt ? + r->base : ULLONG_MAX; + /* + * if idx_b advanced past idx_a, + * break out to advance idx_a + */ - /* if ri advanced past mi, break out to advance mi */ if (r_end <= m_start) break; /* if the two regions intersect, we're done */ @@ -687,18 +957,17 @@ void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid, if (out_end) *out_end = min(m_end, r_end); if (out_nid) - *out_nid = memblock_get_region_node(m); - + *out_nid = m_nid; if (m_start >= r_start) - mi--; + idx_a--; else - ri--; - *idx = (u32)mi | (u64)ri << 32; + idx_b--; + *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } - + /* signal end of iteration */ *idx = ULLONG_MAX; } @@ -738,18 +1007,18 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for * @size: size of area to set node ID for + * @type: memblock type to set node ID for * @nid: node ID to set * - * Set the nid of memblock memory regions in [@base,@base+@size) to @nid. + * Set the nid of memblock @type regions in [@base,@base+@size) to @nid. * Regions which cross the area boundaries are split as necessary. * * RETURNS: * 0 on success, -errno on failure. */ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, - int nid) + struct memblock_type *type, int nid) { - struct memblock_type *type = &memblock.memory; int start_rgn, end_rgn; int i, ret; @@ -765,22 +1034,40 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, - phys_addr_t align, phys_addr_t max_addr, - int nid) +static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, + phys_addr_t align, phys_addr_t start, + phys_addr_t end, int nid) { phys_addr_t found; - /* align @size to avoid excessive fragmentation on reserved array */ - size = round_up(size, align); + if (!align) + align = SMP_CACHE_BYTES; - found = memblock_find_in_range_node(0, max_addr, size, align, nid); - if (found && !memblock_reserve(found, size)) + found = memblock_find_in_range_node(size, align, start, end, nid); + if (found && !memblock_reserve(found, size)) { + /* + * The min_count is set to 0 so that memblock allocations are + * never reported as leaks. + */ + kmemleak_alloc(__va(found), size, 0, 0); return found; - + } return 0; } +phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, + phys_addr_t start, phys_addr_t end) +{ + return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE); +} + +static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, + phys_addr_t align, phys_addr_t max_addr, + int nid) +{ + return memblock_alloc_range_nid(size, align, 0, max_addr, nid); +} + phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE, nid); @@ -788,7 +1075,7 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) { - return memblock_alloc_base_nid(size, align, max_addr, MAX_NUMNODES); + return memblock_alloc_base_nid(size, align, max_addr, NUMA_NO_NODE); } phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) @@ -818,6 +1105,207 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } +/** + * memblock_virt_alloc_internal - allocate boot memory block + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region to allocate (phys address) + * @max_addr: the upper bound of the memory region to allocate (phys address) + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * The @min_addr limit is dropped if it can not be satisfied and the allocation + * will fall back to memory below @min_addr. Also, allocation may fall back + * to any node in the system if the specified node can not + * hold the requested memory. + * + * The allocation is performed from memory region limited by + * memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE. + * + * The memory block is aligned on SMP_CACHE_BYTES if @align == 0. + * + * The phys address of allocated boot memory block is converted to virtual and + * allocated memory is reset to 0. + * + * In addition, function sets the min_count to 0 using kmemleak_alloc for + * allocated boot memory block, so that it is never reported as leaks. + * + * RETURNS: + * Virtual address of allocated memory block on success, NULL on failure. + */ +static void * __init memblock_virt_alloc_internal( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + phys_addr_t alloc; + void *ptr; + + if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + + /* + * Detect any accidental use of these APIs after slab is ready, as at + * this moment memblock may be deinitialized already and its + * internal data may be destroyed (after execution of free_all_bootmem) + */ + if (WARN_ON_ONCE(slab_is_available())) + return kzalloc_node(size, GFP_NOWAIT, nid); + + if (!align) + align = SMP_CACHE_BYTES; + + if (max_addr > memblock.current_limit) + max_addr = memblock.current_limit; + +again: + alloc = memblock_find_in_range_node(size, align, min_addr, max_addr, + nid); + if (alloc) + goto done; + + if (nid != NUMA_NO_NODE) { + alloc = memblock_find_in_range_node(size, align, min_addr, + max_addr, NUMA_NO_NODE); + if (alloc) + goto done; + } + + if (min_addr) { + min_addr = 0; + goto again; + } else { + goto error; + } + +done: + memblock_reserve(alloc, size); + ptr = phys_to_virt(alloc); + memset(ptr, 0, size); + + /* + * The min_count is set to 0 so that bootmem allocated blocks + * are never reported as leaks. This is because many of these blocks + * are only referred via the physical address which is not + * looked up by kmemleak. + */ + kmemleak_alloc(ptr, size, 0, 0); + + return ptr; + +error: + return NULL; +} + +/** + * memblock_virt_alloc_try_nid_nopanic - allocate boot memory block + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public version of _memblock_virt_alloc_try_nid_nopanic() which provides + * additional debug information (including caller info), if enabled. + * + * RETURNS: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_virt_alloc_try_nid_nopanic( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx %pF\n", + __func__, (u64)size, (u64)align, nid, (u64)min_addr, + (u64)max_addr, (void *)_RET_IP_); + return memblock_virt_alloc_internal(size, align, min_addr, + max_addr, nid); +} + +/** + * memblock_virt_alloc_try_nid - allocate boot memory block with panicking + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public panicking version of _memblock_virt_alloc_try_nid_nopanic() + * which provides debug information (including caller info), if enabled, + * and panics if the request can not be satisfied. + * + * RETURNS: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_virt_alloc_try_nid( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + void *ptr; + + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx %pF\n", + __func__, (u64)size, (u64)align, nid, (u64)min_addr, + (u64)max_addr, (void *)_RET_IP_); + ptr = memblock_virt_alloc_internal(size, align, + min_addr, max_addr, nid); + if (ptr) + return ptr; + + panic("%s: Failed to allocate %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx\n", + __func__, (u64)size, (u64)align, nid, (u64)min_addr, + (u64)max_addr); + return NULL; +} + +/** + * __memblock_free_early - free boot memory block + * @base: phys starting address of the boot memory block + * @size: size of the boot memory block in bytes + * + * Free boot memory block previously allocated by memblock_virt_alloc_xx() API. + * The freeing memory will not be released to the buddy allocator. + */ +void __init __memblock_free_early(phys_addr_t base, phys_addr_t size) +{ + memblock_dbg("%s: [%#016llx-%#016llx] %pF\n", + __func__, (u64)base, (u64)base + size - 1, + (void *)_RET_IP_); + kmemleak_free_part(__va(base), size); + memblock_remove_range(&memblock.reserved, base, size); +} + +/* + * __memblock_free_late - free bootmem block pages directly to buddy allocator + * @addr: phys starting address of the boot memory block + * @size: size of the boot memory block in bytes + * + * This is only useful when the bootmem allocator has already been torn + * down, but we are still initializing the system. Pages are released directly + * to the buddy allocator, no bootmem metadata is updated because it is gone. + */ +void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) +{ + u64 cursor, end; + + memblock_dbg("%s: [%#016llx-%#016llx] %pF\n", + __func__, (u64)base, (u64)base + size - 1, + (void *)_RET_IP_); + kmemleak_free_part(__va(base), size); + cursor = PFN_UP(base); + end = PFN_DOWN(base + size); + + for (; cursor < end; cursor++) { + __free_pages_bootmem(pfn_to_page(cursor), 0); + totalram_pages++; + } +} /* * Remaining API functions @@ -828,6 +1316,23 @@ phys_addr_t __init memblock_phys_mem_size(void) return memblock.memory.total_size; } +phys_addr_t __init memblock_mem_size(unsigned long limit_pfn) +{ + unsigned long pages = 0; + struct memblock_region *r; + unsigned long start_pfn, end_pfn; + + for_each_memblock(memory, r) { + start_pfn = memblock_region_memory_base_pfn(r); + end_pfn = memblock_region_memory_end_pfn(r); + start_pfn = min_t(unsigned long, start_pfn, limit_pfn); + end_pfn = min_t(unsigned long, end_pfn, limit_pfn); + pages += end_pfn - start_pfn; + } + + return PFN_PHYS(pages); +} + /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { @@ -843,16 +1348,14 @@ phys_addr_t __init_memblock memblock_end_of_DRAM(void) void __init memblock_enforce_memory_limit(phys_addr_t limit) { - unsigned long i; phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; + struct memblock_region *r; if (!limit) return; /* find out max address */ - for (i = 0; i < memblock.memory.cnt; i++) { - struct memblock_region *r = &memblock.memory.regions[i]; - + for_each_memblock(memory, r) { if (limit <= r->size) { max_addr = r->base + limit; break; @@ -861,8 +1364,10 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit) } /* truncate both memory and reserved regions */ - __memblock_remove(&memblock.memory, max_addr, (phys_addr_t)ULLONG_MAX); - __memblock_remove(&memblock.reserved, max_addr, (phys_addr_t)ULLONG_MAX); + memblock_remove_range(&memblock.memory, max_addr, + (phys_addr_t)ULLONG_MAX); + memblock_remove_range(&memblock.reserved, max_addr, + (phys_addr_t)ULLONG_MAX); } static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) @@ -893,6 +1398,23 @@ int __init_memblock memblock_is_memory(phys_addr_t addr) return memblock_search(&memblock.memory, addr) != -1; } +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +int __init_memblock memblock_search_pfn_nid(unsigned long pfn, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + struct memblock_type *type = &memblock.memory; + int mid = memblock_search(type, PFN_PHYS(pfn)); + + if (mid == -1) + return -1; + + *start_pfn = PFN_DOWN(type->regions[mid].base); + *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); + + return type->regions[mid].nid; +} +#endif + /** * memblock_is_region_memory - check if a region is a subset of memory * @base: base of region to check @@ -933,13 +1455,12 @@ int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t si void __init_memblock memblock_trim_memory(phys_addr_t align) { - int i; phys_addr_t start, end, orig_start, orig_end; - struct memblock_type *mem = &memblock.memory; + struct memblock_region *r; - for (i = 0; i < mem->cnt; i++) { - orig_start = mem->regions[i].base; - orig_end = mem->regions[i].base + mem->regions[i].size; + for_each_memblock(memory, r) { + orig_start = r->base; + orig_end = r->base + r->size; start = round_up(orig_start, align); end = round_down(orig_end, align); @@ -947,11 +1468,12 @@ void __init_memblock memblock_trim_memory(phys_addr_t align) continue; if (start < end) { - mem->regions[i].base = start; - mem->regions[i].size = end - start; + r->base = start; + r->size = end - start; } else { - memblock_remove_region(mem, i); - i--; + memblock_remove_region(&memblock.memory, + r - memblock.memory.regions); + r--; } } } @@ -961,9 +1483,15 @@ void __init_memblock memblock_set_current_limit(phys_addr_t limit) memblock.current_limit = limit; } +phys_addr_t __init_memblock memblock_get_current_limit(void) +{ + return memblock.current_limit; +} + static void __init_memblock memblock_dump(struct memblock_type *type, char *name) { unsigned long long base, size; + unsigned long flags; int i; pr_info(" %s.cnt = 0x%lx\n", name, type->cnt); @@ -974,13 +1502,14 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name base = rgn->base; size = rgn->size; + flags = rgn->flags; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP if (memblock_get_region_node(rgn) != MAX_NUMNODES) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif - pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s\n", - name, i, base, base + size - 1, size, nid_buf); + pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n", + name, i, base, base + size - 1, size, nid_buf, flags); } } @@ -1051,6 +1580,9 @@ static int __init memblock_init_debugfs(void) return -ENXIO; debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops); debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops); +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP + debugfs_create_file("physmem", S_IRUGO, root, &memblock.physmem, &memblock_debug_fops); +#endif return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09255ec8159..1f14a430c65 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -45,25 +45,29 @@ #include <linux/swapops.h> #include <linux/spinlock.h> #include <linux/eventfd.h> +#include <linux/poll.h> #include <linux/sort.h> #include <linux/fs.h> #include <linux/seq_file.h> -#include <linux/vmalloc.h> +#include <linux/vmpressure.h> #include <linux/mm_inline.h> #include <linux/page_cgroup.h> #include <linux/cpu.h> #include <linux/oom.h> +#include <linux/lockdep.h> +#include <linux/file.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> #include <net/tcp_memcontrol.h> +#include "slab.h" #include <asm/uaccess.h> #include <trace/events/vmscan.h> -struct cgroup_subsys mem_cgroup_subsys __read_mostly; -EXPORT_SYMBOL(mem_cgroup_subsys); +struct cgroup_subsys memory_cgrp_subsys __read_mostly; +EXPORT_SYMBOL(memory_cgrp_subsys); #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; @@ -76,7 +80,7 @@ int do_swap_account __read_mostly; #ifdef CONFIG_MEMCG_SWAP_ENABLED static int really_do_swap_account __initdata = 1; #else -static int really_do_swap_account __initdata = 0; +static int really_do_swap_account __initdata; #endif #else @@ -84,24 +88,12 @@ static int really_do_swap_account __initdata = 0; #endif -/* - * Statistics for memory cgroup. - */ -enum mem_cgroup_stat_index { - /* - * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. - */ - MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ - MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ - MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ - MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ - MEM_CGROUP_STAT_NSTATS, -}; - static const char * const mem_cgroup_stat_names[] = { "cache", "rss", + "rss_huge", "mapped_file", + "writeback", "swap", }; @@ -120,6 +112,14 @@ static const char * const mem_cgroup_events_names[] = { "pgmajfault", }; +static const char * const mem_cgroup_lru_names[] = { + "inactive_anon", + "active_anon", + "inactive_file", + "active_file", + "unevictable", +}; + /* * Per memcg event counter is incremented at every pagein/pageout. With THP, * it will be incremated by the number of pages. This counter is used for @@ -144,8 +144,13 @@ struct mem_cgroup_stat_cpu { }; struct mem_cgroup_reclaim_iter { - /* css_id of the last scanned hierarchy member */ - int position; + /* + * last scanned hierarchy member. Valid only if last_dead_count + * matches memcg->dead_count of the hierarchy root group. + */ + struct mem_cgroup *last_visited; + int last_dead_count; + /* scan generation, increased every round-trip */ unsigned int generation; }; @@ -171,10 +176,6 @@ struct mem_cgroup_per_node { struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; }; -struct mem_cgroup_lru_info { - struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES]; -}; - /* * Cgroups above their limits are maintained in a RB-Tree, independent of * their hierarchy representation @@ -227,6 +228,46 @@ struct mem_cgroup_eventfd_list { struct eventfd_ctx *eventfd; }; +/* + * cgroup_event represents events which userspace want to receive. + */ +struct mem_cgroup_event { + /* + * memcg which the event belongs to. + */ + struct mem_cgroup *memcg; + /* + * eventfd to signal userspace about the event. + */ + struct eventfd_ctx *eventfd; + /* + * Each of these stored in a list by the cgroup. + */ + struct list_head list; + /* + * register_event() callback will be used to add new userspace + * waiter for changes related to this event. Use eventfd_signal() + * on eventfd to send notification to userspace. + */ + int (*register_event)(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args); + /* + * unregister_event() callback will be called when userspace closes + * the eventfd or on cgroup removing. This callback must be set, + * if you want provide notification functionality. + */ + void (*unregister_event)(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd); + /* + * All fields below needed to unregister event when + * userspace closes eventfd. + */ + poll_table pt; + wait_queue_head_t *wqh; + wait_queue_t wait; + struct work_struct remove; +}; + static void mem_cgroup_threshold(struct mem_cgroup *memcg); static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); @@ -248,45 +289,19 @@ struct mem_cgroup { */ struct res_counter res; - union { - /* - * the counter to account for mem+swap usage. - */ - struct res_counter memsw; + /* vmpressure notifications */ + struct vmpressure vmpressure; - /* - * rcu_freeing is used only when freeing struct mem_cgroup, - * so put it into a union to avoid wasting more memory. - * It must be disjoint from the css field. It could be - * in a union with the res field, but res plays a much - * larger part in mem_cgroup life than memsw, and might - * be of interest, even at time of free, when debugging. - * So share rcu_head with the less interesting memsw. - */ - struct rcu_head rcu_freeing; - /* - * We also need some space for a worker in deferred freeing. - * By the time we call it, rcu_freeing is no longer in use. - */ - struct work_struct work_freeing; - }; + /* + * the counter to account for mem+swap usage. + */ + struct res_counter memsw; /* * the counter to account for kernel memory usage. */ struct res_counter kmem; /* - * Per cgroup active and inactive list, similar to the - * per zone LRU lists. - */ - struct mem_cgroup_lru_info info; - int last_scanned_node; -#if MAX_NUMNODES > 1 - nodemask_t scan_nodes; - atomic_t numainfo_events; - atomic_t numainfo_updating; -#endif - /* * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; @@ -294,8 +309,7 @@ struct mem_cgroup { bool oom_lock; atomic_t under_oom; - - atomic_t refcnt; + atomic_t oom_wakeups; int swappiness; /* OOM-Killer disable */ @@ -320,7 +334,7 @@ struct mem_cgroup { * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ - unsigned long move_charge_at_immigrate; + unsigned long move_charge_at_immigrate; /* * set > 0 if pages under this cgroup are moving to other cgroup. */ @@ -338,30 +352,39 @@ struct mem_cgroup { struct mem_cgroup_stat_cpu nocpu_base; spinlock_t pcp_counter_lock; + atomic_t dead_count; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) - struct tcp_memcontrol tcp_mem; + struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) - /* analogous to slab_common's slab_caches list. per-memcg */ + /* analogous to slab_common's slab_caches list, but per-memcg; + * protected by memcg_slab_mutex */ struct list_head memcg_slab_caches; - /* Not a spinlock, we can take a lot of time walking the list */ - struct mutex slab_caches_mutex; /* Index in the kmem_cache->memcg_params->memcg_caches array */ int kmemcg_id; #endif + + int last_scanned_node; +#if MAX_NUMNODES > 1 + nodemask_t scan_nodes; + atomic_t numainfo_events; + atomic_t numainfo_updating; +#endif + + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; + + struct mem_cgroup_per_node *nodeinfo[0]; + /* WARNING: nodeinfo must be the last member here */ }; /* internal only representation about the status of kmem accounting. */ enum { - KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */ - KMEM_ACCOUNTED_ACTIVATED, /* static key enabled. */ + KMEM_ACCOUNTED_ACTIVE, /* accounted by this cgroup itself */ KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */ }; -/* We account when limit is on, but only after call sites are patched */ -#define KMEM_ACCOUNTED_MASK \ - ((1 << KMEM_ACCOUNTED_ACTIVE) | (1 << KMEM_ACCOUNTED_ACTIVATED)) - #ifdef CONFIG_MEMCG_KMEM static inline void memcg_kmem_set_active(struct mem_cgroup *memcg) { @@ -373,18 +396,13 @@ static bool memcg_kmem_is_active(struct mem_cgroup *memcg) return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags); } -static void memcg_kmem_set_activated(struct mem_cgroup *memcg) -{ - set_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags); -} - -static void memcg_kmem_clear_activated(struct mem_cgroup *memcg) -{ - clear_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags); -} - static void memcg_kmem_mark_dead(struct mem_cgroup *memcg) { + /* + * Our caller must use css_get() first, because memcg_uncharge_kmem() + * will call css_put() if it sees the memcg is dead. + */ + smp_wmb(); if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags)) set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags); } @@ -398,8 +416,8 @@ static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg) /* Stuffs for move charges at task migration. */ /* - * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a - * left-shifted bitmap of these types. + * Types of charges to be moved. "move_charge_at_immitgrate" and + * "immigrate_flags" are treated as a left-shifted bitmap of these types. */ enum move_type { MOVE_CHARGE_TYPE_ANON, /* private anonymous page and swap of it */ @@ -412,6 +430,7 @@ static struct move_charge_struct { spinlock_t lock; /* for from, to */ struct mem_cgroup *from; struct mem_cgroup *to; + unsigned long immigrate_flags; unsigned long precharge; unsigned long moved_charge; unsigned long moved_swap; @@ -424,14 +443,12 @@ static struct move_charge_struct { static bool move_anon(void) { - return test_bit(MOVE_CHARGE_TYPE_ANON, - &mc.to->move_charge_at_immigrate); + return test_bit(MOVE_CHARGE_TYPE_ANON, &mc.immigrate_flags); } static bool move_file(void) { - return test_bit(MOVE_CHARGE_TYPE_FILE, - &mc.to->move_charge_at_immigrate); + return test_bit(MOVE_CHARGE_TYPE_FILE, &mc.immigrate_flags); } /* @@ -471,13 +488,29 @@ enum res_type { #define MEM_CGROUP_RECLAIM_SHRINK_BIT 0x1 #define MEM_CGROUP_RECLAIM_SHRINK (1 << MEM_CGROUP_RECLAIM_SHRINK_BIT) -static void mem_cgroup_get(struct mem_cgroup *memcg); -static void mem_cgroup_put(struct mem_cgroup *memcg); +/* + * The memcg_create_mutex will be held whenever a new cgroup is created. + * As a consequence, any change that needs to protect against new child cgroups + * appearing has to hold it as well. + */ +static DEFINE_MUTEX(memcg_create_mutex); -static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s) { - return container_of(s, struct mem_cgroup, css); + return s ? container_of(s, struct mem_cgroup, css) : NULL; +} + +/* Some nice accessors for the vmpressure. */ +struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) +{ + if (!memcg) + memcg = root_mem_cgroup; + return &memcg->vmpressure; +} + +struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) +{ + return &container_of(vmpr, struct mem_cgroup, vmpressure)->css; } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) @@ -485,6 +518,25 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) return (memcg == root_mem_cgroup); } +/* + * We restrict the id in the range of [1, 65535], so it can fit into + * an unsigned short. + */ +#define MEM_CGROUP_ID_MAX USHRT_MAX + +static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) +{ + return memcg->css.id; +} + +static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + struct cgroup_subsys_state *css; + + css = css_from_id(id, &memory_cgrp_subsys); + return mem_cgroup_from_css(css); +} + /* Writing them here to avoid exposing memcg's inner layout */ #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) @@ -506,15 +558,16 @@ void sock_update_memcg(struct sock *sk) */ if (sk->sk_cgrp) { BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg)); - mem_cgroup_get(sk->sk_cgrp->memcg); + css_get(&sk->sk_cgrp->memcg->css); return; } rcu_read_lock(); memcg = mem_cgroup_from_task(current); cg_proto = sk->sk_prot->proto_cgroup(memcg); - if (!mem_cgroup_is_root(memcg) && memcg_proto_active(cg_proto)) { - mem_cgroup_get(memcg); + if (!mem_cgroup_is_root(memcg) && + memcg_proto_active(cg_proto) && + css_tryget_online(&memcg->css)) { sk->sk_cgrp = cg_proto; } rcu_read_unlock(); @@ -528,7 +581,7 @@ void sock_release_memcg(struct sock *sk) struct mem_cgroup *memcg; WARN_ON(!sk->sk_cgrp->memcg); memcg = sk->sk_cgrp->memcg; - mem_cgroup_put(memcg); + css_put(&sk->sk_cgrp->memcg->css); } } @@ -537,13 +590,13 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) if (!memcg || mem_cgroup_is_root(memcg)) return NULL; - return &memcg->tcp_mem.cg_proto; + return &memcg->tcp_mem; } EXPORT_SYMBOL(tcp_proto_cgroup); static void disarm_sock_keys(struct mem_cgroup *memcg) { - if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto)) + if (!memcg_proto_activated(&memcg->tcp_mem)) return; static_key_slow_dec(&memcg_socket_limit_enabled); } @@ -556,16 +609,11 @@ static void disarm_sock_keys(struct mem_cgroup *memcg) #ifdef CONFIG_MEMCG_KMEM /* * This will be the memcg's index in each cache's ->memcg_params->memcg_caches. - * There are two main reasons for not using the css_id for this: - * 1) this works better in sparse environments, where we have a lot of memcgs, - * but only a few kmem-limited. Or also, if we have, for instance, 200 - * memcgs, and none but the 200th is kmem-limited, we'd have to have a - * 200 entry array for that. - * - * 2) In order not to violate the cgroup API, we would like to do all memory - * allocation in ->create(). At that point, we haven't yet allocated the - * css_id. Having a separate index prevents us from messing with the cgroup - * core for this + * The main reason for not using cgroup id for this: + * this works better in sparse environments, where we have a lot of memcgs, + * but only a few kmem-limited. Or also, if we have, for instance, 200 + * memcgs, and none but the 200th is kmem-limited, we'd have to have a + * 200 entry array for that. * * The current size of the caches array is stored in * memcg_limited_groups_array_size. It will double each time we have to @@ -580,14 +628,14 @@ int memcg_limited_groups_array_size; * cgroups is a reasonable guess. In the future, it could be a parameter or * tunable, but that is strictly not necessary. * - * MAX_SIZE should be as large as the number of css_ids. Ideally, we could get + * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get * this constant directly from cgroup, but it is understandable that this is * better kept as an internal representation in cgroup.c. In any case, the - * css_id space is not getting any smaller, and we don't have to necessarily + * cgrp_id space is not getting any smaller, and we don't have to necessarily * increase ours as well if it increases. */ #define MEMCG_CACHES_MIN_SIZE 4 -#define MEMCG_CACHES_MAX_SIZE 65535 +#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX /* * A lot of the calls to the cache allocation functions are expected to be @@ -625,9 +673,12 @@ static void disarm_static_keys(struct mem_cgroup *memcg) static void drain_all_stock_async(struct mem_cgroup *memcg); static struct mem_cgroup_per_zone * -mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid) +mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) { - return &memcg->info.nodeinfo[nid]->zoneinfo[zid]; + int nid = zone_to_nid(zone); + int zid = zone_idx(zone); + + return &memcg->nodeinfo[nid]->zoneinfo[zid]; } struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) @@ -636,12 +687,12 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) } static struct mem_cgroup_per_zone * -page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page) +mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page) { int nid = page_to_nid(page); int zid = page_zonenum(page); - return mem_cgroup_zoneinfo(memcg, nid, zid); + return &memcg->nodeinfo[nid]->zoneinfo[zid]; } static struct mem_cgroup_tree_per_zone * @@ -659,11 +710,9 @@ soft_limit_tree_from_page(struct page *page) return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; } -static void -__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz, - unsigned long long new_usage_in_excess) +static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz, + unsigned long long new_usage_in_excess) { struct rb_node **p = &mctz->rb_root.rb_node; struct rb_node *parent = NULL; @@ -693,10 +742,8 @@ __mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, mz->on_tree = true; } -static void -__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) { if (!mz->on_tree) return; @@ -704,13 +751,11 @@ __mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, mz->on_tree = false; } -static void -mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) { spin_lock(&mctz->lock); - __mem_cgroup_remove_exceeded(memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); spin_unlock(&mctz->lock); } @@ -720,16 +765,14 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) unsigned long long excess; struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; - int nid = page_to_nid(page); - int zid = page_zonenum(page); - mctz = soft_limit_tree_from_page(page); + mctz = soft_limit_tree_from_page(page); /* * Necessary to update all ancestors when hierarchy is used. * because their event counter is not touched. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_zoneinfo(memcg, nid, zid); + mz = mem_cgroup_page_zoneinfo(memcg, page); excess = res_counter_soft_limit_excess(&memcg->res); /* * We have to update the tree if mz is on RB-tree or @@ -739,12 +782,12 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) spin_lock(&mctz->lock); /* if on-tree, remove it */ if (mz->on_tree) - __mem_cgroup_remove_exceeded(memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); /* * Insert again. mz->usage_in_excess will be updated. * If excess is 0, no tree ops. */ - __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess); + __mem_cgroup_insert_exceeded(mz, mctz, excess); spin_unlock(&mctz->lock); } } @@ -752,15 +795,15 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) { - int node, zone; - struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; + struct mem_cgroup_per_zone *mz; + int nid, zid; - for_each_node(node) { - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - mz = mem_cgroup_zoneinfo(memcg, node, zone); - mctz = soft_limit_tree_node_zone(node, zone); - mem_cgroup_remove_exceeded(memcg, mz, mctz); + for_each_node(nid) { + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; + mctz = soft_limit_tree_node_zone(nid, zid); + mem_cgroup_remove_exceeded(mz, mctz); } } } @@ -783,9 +826,9 @@ retry: * we will to add it back at the end of reclaim to its correct * position in the tree. */ - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); if (!res_counter_soft_limit_excess(&mz->memcg->res) || - !css_tryget(&mz->memcg->css)) + !css_tryget_online(&mz->memcg->css)) goto retry; done: return mz; @@ -852,6 +895,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, unsigned long val = 0; int cpu; + get_online_cpus(); for_each_online_cpu(cpu) val += per_cpu(memcg->stat->events[idx], cpu); #ifdef CONFIG_HOTPLUG_CPU @@ -859,14 +903,14 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, val += memcg->nocpu_base.events[idx]; spin_unlock(&memcg->pcp_counter_lock); #endif + put_online_cpus(); return val; } static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, + struct page *page, bool anon, int nr_pages) { - preempt_disable(); - /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is * counted as CACHE even if it's on ANON LRU. @@ -878,6 +922,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages); + if (PageTransHuge(page)) + __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], + nr_pages); + /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]); @@ -887,12 +935,9 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, } __this_cpu_add(memcg->stat->nr_page_events, nr_pages); - - preempt_enable(); } -unsigned long -mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) +unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { struct mem_cgroup_per_zone *mz; @@ -900,46 +945,38 @@ mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) return mz->lru_size[lru]; } -static unsigned long -mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid, - unsigned int lru_mask) -{ - struct mem_cgroup_per_zone *mz; - enum lru_list lru; - unsigned long ret = 0; - - mz = mem_cgroup_zoneinfo(memcg, nid, zid); - - for_each_lru(lru) { - if (BIT(lru) & lru_mask) - ret += mz->lru_size[lru]; - } - return ret; -} - -static unsigned long -mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, - int nid, unsigned int lru_mask) +static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, + int nid, + unsigned int lru_mask) { - u64 total = 0; + unsigned long nr = 0; int zid; - for (zid = 0; zid < MAX_NR_ZONES; zid++) - total += mem_cgroup_zone_nr_lru_pages(memcg, - nid, zid, lru_mask); + VM_BUG_ON((unsigned)nid >= nr_node_ids); - return total; + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct mem_cgroup_per_zone *mz; + enum lru_list lru; + + for_each_lru(lru) { + if (!(BIT(lru) & lru_mask)) + continue; + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; + nr += mz->lru_size[lru]; + } + } + return nr; } static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg, unsigned int lru_mask) { + unsigned long nr = 0; int nid; - u64 total = 0; for_each_node_state(nid, N_MEMORY) - total += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); - return total; + nr += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); + return nr; } static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, @@ -1002,12 +1039,6 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) preempt_enable(); } -struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) -{ - return mem_cgroup_from_css( - cgroup_subsys_state(cont, mem_cgroup_subsys_id)); -} - struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) { /* @@ -1018,30 +1049,137 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) if (unlikely(!p)) return NULL; - return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id)); + return mem_cgroup_from_css(task_css(p, memory_cgrp_id)); } -struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) +static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *memcg = NULL; - if (!mm) - return NULL; - /* - * Because we have no locks, mm->owner's may be being moved to other - * cgroup. We use css_tryget() here even if this looks - * pessimistic (rather than adding locks here). - */ rcu_read_lock(); do { - memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!memcg)) - break; - } while (!css_tryget(&memcg->css)); + /* + * Page cache insertions can happen withou an + * actual mm context, e.g. during disk probing + * on boot, loopback IO, acct() writes etc. + */ + if (unlikely(!mm)) + memcg = root_mem_cgroup; + else { + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) + memcg = root_mem_cgroup; + } + } while (!css_tryget_online(&memcg->css)); rcu_read_unlock(); return memcg; } +/* + * Returns a next (in a pre-order walk) alive memcg (with elevated css + * ref. count) or NULL if the whole root's subtree has been visited. + * + * helper function to be used by mem_cgroup_iter + */ +static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root, + struct mem_cgroup *last_visited) +{ + struct cgroup_subsys_state *prev_css, *next_css; + + prev_css = last_visited ? &last_visited->css : NULL; +skip_node: + next_css = css_next_descendant_pre(prev_css, &root->css); + + /* + * Even if we found a group we have to make sure it is + * alive. css && !memcg means that the groups should be + * skipped and we should continue the tree walk. + * last_visited css is safe to use because it is + * protected by css_get and the tree walk is rcu safe. + * + * We do not take a reference on the root of the tree walk + * because we might race with the root removal when it would + * be the only node in the iterated hierarchy and mem_cgroup_iter + * would end up in an endless loop because it expects that at + * least one valid node will be returned. Root cannot disappear + * because caller of the iterator should hold it already so + * skipping css reference should be safe. + */ + if (next_css) { + if ((next_css == &root->css) || + ((next_css->flags & CSS_ONLINE) && + css_tryget_online(next_css))) + return mem_cgroup_from_css(next_css); + + prev_css = next_css; + goto skip_node; + } + + return NULL; +} + +static void mem_cgroup_iter_invalidate(struct mem_cgroup *root) +{ + /* + * When a group in the hierarchy below root is destroyed, the + * hierarchy iterator can no longer be trusted since it might + * have pointed to the destroyed group. Invalidate it. + */ + atomic_inc(&root->dead_count); +} + +static struct mem_cgroup * +mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter, + struct mem_cgroup *root, + int *sequence) +{ + struct mem_cgroup *position = NULL; + /* + * A cgroup destruction happens in two stages: offlining and + * release. They are separated by a RCU grace period. + * + * If the iterator is valid, we may still race with an + * offlining. The RCU lock ensures the object won't be + * released, tryget will fail if we lost the race. + */ + *sequence = atomic_read(&root->dead_count); + if (iter->last_dead_count == *sequence) { + smp_rmb(); + position = iter->last_visited; + + /* + * We cannot take a reference to root because we might race + * with root removal and returning NULL would end up in + * an endless loop on the iterator user level when root + * would be returned all the time. + */ + if (position && position != root && + !css_tryget_online(&position->css)) + position = NULL; + } + return position; +} + +static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter, + struct mem_cgroup *last_visited, + struct mem_cgroup *new_position, + struct mem_cgroup *root, + int sequence) +{ + /* root reference counting symmetric to mem_cgroup_iter_load */ + if (last_visited && last_visited != root) + css_put(&last_visited->css); + /* + * We store the sequence count from the time @last_visited was + * loaded successfully instead of rereading it here so that we + * don't lose destruction events in between. We could have + * raced with the destruction of @new_position after all. + */ + iter->last_visited = new_position; + smp_wmb(); + iter->last_dead_count = sequence; +} + /** * mem_cgroup_iter - iterate over memory cgroup hierarchy * @root: hierarchy root @@ -1064,7 +1202,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup_reclaim_cookie *reclaim) { struct mem_cgroup *memcg = NULL; - int id = 0; + struct mem_cgroup *last_visited = NULL; if (mem_cgroup_disabled()) return NULL; @@ -1073,53 +1211,53 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, root = root_mem_cgroup; if (prev && !reclaim) - id = css_id(&prev->css); - - if (prev && prev != root) - css_put(&prev->css); + last_visited = prev; if (!root->use_hierarchy && root != root_mem_cgroup) { if (prev) - return NULL; + goto out_css_put; return root; } + rcu_read_lock(); while (!memcg) { struct mem_cgroup_reclaim_iter *uninitialized_var(iter); - struct cgroup_subsys_state *css; + int uninitialized_var(seq); if (reclaim) { - int nid = zone_to_nid(reclaim->zone); - int zid = zone_idx(reclaim->zone); struct mem_cgroup_per_zone *mz; - mz = mem_cgroup_zoneinfo(root, nid, zid); + mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone); iter = &mz->reclaim_iter[reclaim->priority]; - if (prev && reclaim->generation != iter->generation) - return NULL; - id = iter->position; + if (prev && reclaim->generation != iter->generation) { + iter->last_visited = NULL; + goto out_unlock; + } + + last_visited = mem_cgroup_iter_load(iter, root, &seq); } - rcu_read_lock(); - css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id); - if (css) { - if (css == &root->css || css_tryget(css)) - memcg = mem_cgroup_from_css(css); - } else - id = 0; - rcu_read_unlock(); + memcg = __mem_cgroup_iter_next(root, last_visited); if (reclaim) { - iter->position = id; - if (!css) + mem_cgroup_iter_update(iter, last_visited, memcg, root, + seq); + + if (!memcg) iter->generation++; else if (!prev && memcg) reclaim->generation = iter->generation; } - if (prev && !css) - return NULL; + if (prev && !memcg) + goto out_unlock; } +out_unlock: + rcu_read_unlock(); +out_css_put: + if (prev && prev != root) + css_put(&prev->css); + return memcg; } @@ -1196,7 +1334,7 @@ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, goto out; } - mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone)); + mz = mem_cgroup_zone_zoneinfo(memcg, zone); lruvec = &mz->lruvec; out: /* @@ -1255,7 +1393,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) if (!PageLRU(page) && !PageCgroupUsed(pc) && memcg != root_mem_cgroup) pc->mem_cgroup = memcg = root_mem_cgroup; - mz = page_cgroup_zoneinfo(memcg, page); + mz = mem_cgroup_page_zoneinfo(memcg, page); lruvec = &mz->lruvec; out: /* @@ -1303,7 +1441,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, return true; if (!root_memcg->use_hierarchy || !memcg) return false; - return css_is_ancestor(&memcg->css, &root_memcg->css); + return cgroup_is_descendant(memcg->css.cgroup, root_memcg->css.cgroup); } static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, @@ -1317,15 +1455,16 @@ static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, return ret; } -int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg) +bool task_in_mem_cgroup(struct task_struct *task, + const struct mem_cgroup *memcg) { - int ret; struct mem_cgroup *curr = NULL; struct task_struct *p; + bool ret; p = find_lock_task_mm(task); if (p) { - curr = try_get_mem_cgroup_from_mm(p->mm); + curr = get_mem_cgroup_from_mm(p->mm); task_unlock(p); } else { /* @@ -1333,14 +1472,12 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg) * killer still needs to detect if they have already been oom * killed to prevent needlessly killing additional tasks. */ - task_lock(task); + rcu_read_lock(); curr = mem_cgroup_from_task(task); if (curr) css_get(&curr->css); - task_unlock(task); + rcu_read_unlock(); } - if (!curr) - return 0; /* * We should check use_hierarchy of "memcg" not "curr". Because checking * use_hierarchy of "curr" here make this function true if hierarchy is @@ -1371,17 +1508,6 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return inactive * inactive_ratio < active; } -int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec) -{ - unsigned long active; - unsigned long inactive; - - inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_FILE); - active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_FILE); - - return (active > inactive); -} - #define mem_cgroup_from_res_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) @@ -1404,10 +1530,8 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) int mem_cgroup_swappiness(struct mem_cgroup *memcg) { - struct cgroup *cgrp = memcg->css.cgroup; - /* root ? */ - if (cgrp->parent == NULL) + if (mem_cgroup_disabled() || !memcg->css.parent) return vm_swappiness; return memcg->swappiness; @@ -1451,23 +1575,12 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg) } /* - * 2 routines for checking "mem" is under move_account() or not. - * - * mem_cgroup_stolen() - checking whether a cgroup is mc.from or not. This - * is used for avoiding races in accounting. If true, - * pc->mem_cgroup may be overwritten. + * A routine for checking "mem" is under move_account() or not. * - * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or - * under hierarchy of moving cgroups. This is for - * waiting at hith-memory prressure caused by "move". + * Checking a cgroup is mc.from or mc.to or under hierarchy of + * moving cgroups. This is for waiting at high-memory pressure + * caused by "move". */ - -static bool mem_cgroup_stolen(struct mem_cgroup *memcg) -{ - VM_BUG_ON(!rcu_read_lock_held()); - return atomic_read(&memcg->moving_account) > 0; -} - static bool mem_cgroup_under_move(struct mem_cgroup *memcg) { struct mem_cgroup *from; @@ -1510,7 +1623,6 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) * Take this lock when * - a code tries to modify page's memcg while it's USED. * - a code tries to modify page state accounting in a memcg. - * see mem_cgroup_stolen(), too. */ static void move_lock_mem_cgroup(struct mem_cgroup *memcg, unsigned long *flags) @@ -1524,8 +1636,9 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg, spin_unlock_irqrestore(&memcg->move_lock, *flags); } +#define K(x) ((x) << (PAGE_SHIFT-10)) /** - * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode. + * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller. * @memcg: The memory cgroup that went over limit * @p: Task that is going to be killed * @@ -1534,64 +1647,57 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg, */ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { - struct cgroup *task_cgrp; - struct cgroup *mem_cgrp; - /* - * Need a buffer in BSS, can't rely on allocations. The code relies - * on the assumption that OOM is serialized for memory controller. - * If this assumption is broken, revisit this code. - */ - static char memcg_name[PATH_MAX]; - int ret; + /* oom_info_lock ensures that parallel ooms do not interleave */ + static DEFINE_MUTEX(oom_info_lock); + struct mem_cgroup *iter; + unsigned int i; - if (!memcg || !p) + if (!p) return; + mutex_lock(&oom_info_lock); rcu_read_lock(); - mem_cgrp = memcg->css.cgroup; - task_cgrp = task_cgroup(p, mem_cgroup_subsys_id); - - ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX); - if (ret < 0) { - /* - * Unfortunately, we are unable to convert to a useful name - * But we'll still print out the usage information - */ - rcu_read_unlock(); - goto done; - } - rcu_read_unlock(); - - printk(KERN_INFO "Task in %s killed", memcg_name); + pr_info("Task in "); + pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id)); + pr_info(" killed as a result of limit of "); + pr_cont_cgroup_path(memcg->css.cgroup); + pr_info("\n"); - rcu_read_lock(); - ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX); - if (ret < 0) { - rcu_read_unlock(); - goto done; - } rcu_read_unlock(); - /* - * Continues from above, so we don't need an KERN_ level - */ - printk(KERN_CONT " as a result of limit of %s\n", memcg_name); -done: - - printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n", + pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n", res_counter_read_u64(&memcg->res, RES_USAGE) >> 10, res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10, res_counter_read_u64(&memcg->res, RES_FAILCNT)); - printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, " - "failcnt %llu\n", + pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %llu\n", res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10, res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10, res_counter_read_u64(&memcg->memsw, RES_FAILCNT)); - printk(KERN_INFO "kmem: usage %llukB, limit %llukB, failcnt %llu\n", + pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n", res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10, res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10, res_counter_read_u64(&memcg->kmem, RES_FAILCNT)); + + for_each_mem_cgroup_tree(iter, memcg) { + pr_info("Memory cgroup stats for "); + pr_cont_cgroup_path(iter->css.cgroup); + pr_cont(":"); + + for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) + continue; + pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i], + K(mem_cgroup_read_stat(iter, i))); + } + + for (i = 0; i < NR_LRU_LISTS; i++) + pr_cont(" %s:%luKB", mem_cgroup_lru_names[i], + K(mem_cgroup_nr_lru_pages(iter, BIT(i)))); + + pr_cont("\n"); + } + mutex_unlock(&oom_info_lock); } /* @@ -1646,11 +1752,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, struct task_struct *chosen = NULL; /* - * If current has a pending SIGKILL, then automatically select it. The - * goal is to allow it to allocate so that it may quickly exit and free - * its memory. + * If current has a pending SIGKILL or is exiting, then automatically + * select it. The goal is to allow it to allocate so that it may + * quickly exit and free its memory. */ - if (fatal_signal_pending(current)) { + if (fatal_signal_pending(current) || current->flags & PF_EXITING) { set_thread_flag(TIF_MEMDIE); return; } @@ -1658,12 +1764,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; for_each_mem_cgroup_tree(iter, memcg) { - struct cgroup *cgroup = iter->css.cgroup; - struct cgroup_iter it; + struct css_task_iter it; struct task_struct *task; - cgroup_iter_start(cgroup, &it); - while ((task = cgroup_iter_next(cgroup, &it))) { + css_task_iter_start(&iter->css, &it); + while ((task = css_task_iter_next(&it))) { switch (oom_scan_process_thread(task, totalpages, NULL, false)) { case OOM_SCAN_SELECT: @@ -1676,7 +1781,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, case OOM_SCAN_CONTINUE: continue; case OOM_SCAN_ABORT: - cgroup_iter_end(cgroup, &it); + css_task_iter_end(&it); mem_cgroup_iter_break(memcg, iter); if (chosen) put_task_struct(chosen); @@ -1685,15 +1790,20 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, break; }; points = oom_badness(task, memcg, NULL, totalpages); - if (points > chosen_points) { - if (chosen) - put_task_struct(chosen); - chosen = task; - chosen_points = points; - get_task_struct(chosen); - } + if (!points || points < chosen_points) + continue; + /* Prefer thread group leaders for display purposes */ + if (points == chosen_points && + thread_group_leader(chosen)) + continue; + + if (chosen) + put_task_struct(chosen); + chosen = task; + chosen_points = points; + get_task_struct(chosen); } - cgroup_iter_end(cgroup, &it); + css_task_iter_end(&it); } if (!chosen) @@ -1929,15 +2039,24 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, return total; } +#ifdef CONFIG_LOCKDEP +static struct lockdep_map memcg_oom_lock_dep_map = { + .name = "memcg_oom_lock", +}; +#endif + +static DEFINE_SPINLOCK(memcg_oom_lock); + /* * Check OOM-Killer is already running under our hierarchy. * If someone is running, return false. - * Has to be called with memcg_oom_lock */ -static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg) +static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg) { struct mem_cgroup *iter, *failed = NULL; + spin_lock(&memcg_oom_lock); + for_each_mem_cgroup_tree(iter, memcg) { if (iter->oom_lock) { /* @@ -1951,33 +2070,35 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg) iter->oom_lock = true; } - if (!failed) - return true; - - /* - * OK, we failed to lock the whole subtree so we have to clean up - * what we set up to the failing subtree - */ - for_each_mem_cgroup_tree(iter, memcg) { - if (iter == failed) { - mem_cgroup_iter_break(memcg, iter); - break; + if (failed) { + /* + * OK, we failed to lock the whole subtree so we have + * to clean up what we set up to the failing subtree + */ + for_each_mem_cgroup_tree(iter, memcg) { + if (iter == failed) { + mem_cgroup_iter_break(memcg, iter); + break; + } + iter->oom_lock = false; } - iter->oom_lock = false; - } - return false; + } else + mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_); + + spin_unlock(&memcg_oom_lock); + + return !failed; } -/* - * Has to be called with memcg_oom_lock - */ -static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg) +static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg) { struct mem_cgroup *iter; + spin_lock(&memcg_oom_lock); + mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_); for_each_mem_cgroup_tree(iter, memcg) iter->oom_lock = false; - return 0; + spin_unlock(&memcg_oom_lock); } static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg) @@ -2001,7 +2122,6 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) atomic_add_unless(&iter->under_oom, -1, 0); } -static DEFINE_SPINLOCK(memcg_oom_lock); static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); struct oom_wait_info { @@ -2031,6 +2151,7 @@ static int memcg_oom_wake_function(wait_queue_t *wait, static void memcg_wakeup_oom(struct mem_cgroup *memcg) { + atomic_inc(&memcg->oom_wakeups); /* for filtering, pass "memcg" as argument. */ __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); } @@ -2041,67 +2162,106 @@ static void memcg_oom_recover(struct mem_cgroup *memcg) memcg_wakeup_oom(memcg); } -/* - * try to call OOM killer. returns false if we should exit memory-reclaim loop. +static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) +{ + if (!current->memcg_oom.may_oom) + return; + /* + * We are in the middle of the charge context here, so we + * don't want to block when potentially sitting on a callstack + * that holds all kinds of filesystem and mm locks. + * + * Also, the caller may handle a failed allocation gracefully + * (like optional page cache readahead) and so an OOM killer + * invocation might not even be necessary. + * + * That's why we don't do anything here except remember the + * OOM context and then deal with it at the end of the page + * fault when the stack is unwound, the locks are released, + * and when we know whether the fault was overall successful. + */ + css_get(&memcg->css); + current->memcg_oom.memcg = memcg; + current->memcg_oom.gfp_mask = mask; + current->memcg_oom.order = order; +} + +/** + * mem_cgroup_oom_synchronize - complete memcg OOM handling + * @handle: actually kill/wait or just clean up the OOM state + * + * This has to be called at the end of a page fault if the memcg OOM + * handler was enabled. + * + * Memcg supports userspace OOM handling where failed allocations must + * sleep on a waitqueue until the userspace task resolves the + * situation. Sleeping directly in the charge context with all kinds + * of locks held is not a good idea, instead we remember an OOM state + * in the task and mem_cgroup_oom_synchronize() has to be called at + * the end of the page fault to complete the OOM handling. + * + * Returns %true if an ongoing memcg OOM situation was detected and + * completed, %false otherwise. */ -static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask, - int order) +bool mem_cgroup_oom_synchronize(bool handle) { + struct mem_cgroup *memcg = current->memcg_oom.memcg; struct oom_wait_info owait; - bool locked, need_to_kill; + bool locked; + + /* OOM is global, do not handle */ + if (!memcg) + return false; + + if (!handle) + goto cleanup; owait.memcg = memcg; owait.wait.flags = 0; owait.wait.func = memcg_oom_wake_function; owait.wait.private = current; INIT_LIST_HEAD(&owait.wait.task_list); - need_to_kill = true; - mem_cgroup_mark_under_oom(memcg); - /* At first, try to OOM lock hierarchy under memcg.*/ - spin_lock(&memcg_oom_lock); - locked = mem_cgroup_oom_lock(memcg); - /* - * Even if signal_pending(), we can't quit charge() loop without - * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL - * under OOM is always welcomed, use TASK_KILLABLE here. - */ prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); - if (!locked || memcg->oom_kill_disable) - need_to_kill = false; + mem_cgroup_mark_under_oom(memcg); + + locked = mem_cgroup_oom_trylock(memcg); + if (locked) mem_cgroup_oom_notify(memcg); - spin_unlock(&memcg_oom_lock); - if (need_to_kill) { + if (locked && !memcg->oom_kill_disable) { + mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); - mem_cgroup_out_of_memory(memcg, mask, order); + mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask, + current->memcg_oom.order); } else { schedule(); + mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); } - spin_lock(&memcg_oom_lock); - if (locked) - mem_cgroup_oom_unlock(memcg); - memcg_wakeup_oom(memcg); - spin_unlock(&memcg_oom_lock); - - mem_cgroup_unmark_under_oom(memcg); - if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current)) - return false; - /* Give chance to dying process */ - schedule_timeout_uninterruptible(1); + if (locked) { + mem_cgroup_oom_unlock(memcg); + /* + * There is no guarantee that an OOM-lock contender + * sees the wakeups triggered by the OOM kill + * uncharges. Wake any sleepers explicitely. + */ + memcg_oom_recover(memcg); + } +cleanup: + current->memcg_oom.memcg = NULL; + css_put(&memcg->css); return true; } /* - * Currently used to update mapped file statistics, but the routine can be - * generalized to update other statistics as well. + * Used to update mapped file or writeback or other statistics. * * Notes: Race condition * - * We usually use page_cgroup_lock() for accessing page_cgroup member but + * We usually use lock_page_cgroup() for accessing page_cgroup member but * it tends to be costly. But considering some conditions, we doesn't need * to do so _always_. * @@ -2115,8 +2275,8 @@ static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask, * by flags. * * Considering "move", this is an only case we see a race. To make the race - * small, we check mm->moving_account and detect there are possibility of race - * If there is, we take a lock. + * small, we check memcg->moving_account and detect there are possibility + * of race or not. If there is, we take a lock. */ void __mem_cgroup_begin_update_page_stat(struct page *page, @@ -2134,9 +2294,10 @@ again: * If this memory cgroup is not under account moving, we don't * need to take move_lock_mem_cgroup(). Because we already hold * rcu_read_lock(), any calls to move_account will be delayed until - * rcu_read_unlock() if mem_cgroup_stolen() == true. + * rcu_read_unlock(). */ - if (!mem_cgroup_stolen(memcg)) + VM_BUG_ON(!rcu_read_lock_held()); + if (atomic_read(&memcg->moving_account) <= 0) return; move_lock_mem_cgroup(memcg, flags); @@ -2160,7 +2321,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) } void mem_cgroup_update_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx, int val) + enum mem_cgroup_stat_index idx, int val) { struct mem_cgroup *memcg; struct page_cgroup *pc = lookup_page_cgroup(page); @@ -2169,18 +2330,11 @@ void mem_cgroup_update_page_stat(struct page *page, if (mem_cgroup_disabled()) return; + VM_BUG_ON(!rcu_read_lock_held()); memcg = pc->mem_cgroup; if (unlikely(!memcg || !PageCgroupUsed(pc))) return; - switch (idx) { - case MEMCG_NR_FILE_MAPPED: - idx = MEM_CGROUP_STAT_FILE_MAPPED; - break; - default: - BUG(); - } - this_cpu_add(memcg->stat->count[idx], val); } @@ -2251,11 +2405,22 @@ static void drain_stock(struct memcg_stock_pcp *stock) */ static void drain_local_stock(struct work_struct *dummy) { - struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock); + struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); } +static void __init memcg_stock_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct memcg_stock_pcp *stock = + &per_cpu(memcg_stock, cpu); + INIT_WORK(&stock->work, drain_local_stock); + } +} + /* * Cache charges(val) which is from res_counter, to local per_cpu area. * This will be consumed by consume_stock() function, later. @@ -2311,7 +2476,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync) flush_work(&stock->work); } out: - put_online_cpus(); + put_online_cpus(); } /* @@ -2364,7 +2529,7 @@ static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu) spin_unlock(&memcg->pcp_counter_lock); } -static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb, +static int memcg_cpu_hotplug_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { @@ -2387,18 +2552,17 @@ static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb, } -/* See __mem_cgroup_try_charge() for details */ +/* See mem_cgroup_try_charge() for details */ enum { CHARGE_OK, /* success */ CHARGE_RETRY, /* need to retry but retry is not bad */ CHARGE_NOMEM, /* we can't do more. return -ENOMEM */ CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */ - CHARGE_OOM_DIE, /* the current is killed because of OOM */ }; static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned int nr_pages, unsigned int min_pages, - bool oom_check) + bool invoke_oom) { unsigned long csize = nr_pages * PAGE_SIZE; struct mem_cgroup *mem_over_limit; @@ -2455,171 +2619,117 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, if (mem_cgroup_wait_acct_move(mem_over_limit)) return CHARGE_RETRY; - /* If we don't need to call oom-killer at el, return immediately */ - if (!oom_check) - return CHARGE_NOMEM; - /* check OOM */ - if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize))) - return CHARGE_OOM_DIE; + if (invoke_oom) + mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize)); - return CHARGE_RETRY; + return CHARGE_NOMEM; } -/* - * __mem_cgroup_try_charge() does - * 1. detect memcg to be charged against from passed *mm and *ptr, - * 2. update res_counter - * 3. call memory reclaim if necessary. - * - * In some special case, if the task is fatal, fatal_signal_pending() or - * has TIF_MEMDIE, this function returns -EINTR while writing root_mem_cgroup - * to *ptr. There are two reasons for this. 1: fatal threads should quit as soon - * as possible without any hazards. 2: all pages should have a valid - * pc->mem_cgroup. If mm is NULL and the caller doesn't pass a valid memcg - * pointer, that is treated as a charge to root_mem_cgroup. - * - * So __mem_cgroup_try_charge() will return - * 0 ... on success, filling *ptr with a valid memcg pointer. - * -ENOMEM ... charge failure because of resource limits. - * -EINTR ... if thread is fatal. *ptr is filled with root_mem_cgroup. +/** + * mem_cgroup_try_charge - try charging a memcg + * @memcg: memcg to charge + * @nr_pages: number of pages to charge + * @oom: trigger OOM if reclaim fails * - * Unlike the exported interface, an "oom" parameter is added. if oom==true, - * the oom-killer can be invoked. + * Returns 0 if @memcg was charged successfully, -EINTR if the charge + * was bypassed to root_mem_cgroup, and -ENOMEM if the charge failed. */ -static int __mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t gfp_mask, - unsigned int nr_pages, - struct mem_cgroup **ptr, - bool oom) +static int mem_cgroup_try_charge(struct mem_cgroup *memcg, + gfp_t gfp_mask, + unsigned int nr_pages, + bool oom) { unsigned int batch = max(CHARGE_BATCH, nr_pages); int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct mem_cgroup *memcg = NULL; int ret; + if (mem_cgroup_is_root(memcg)) + goto done; /* - * Unlike gloval-vm's OOM-kill, we're not in memory shortage - * in system level. So, allow to go ahead dying process in addition to - * MEMDIE process. + * Unlike in global OOM situations, memcg is not in a physical + * memory shortage. Allow dying and OOM-killed tasks to + * bypass the last charges so that they can exit quickly and + * free their memory. */ - if (unlikely(test_thread_flag(TIF_MEMDIE) - || fatal_signal_pending(current))) + if (unlikely(test_thread_flag(TIF_MEMDIE) || + fatal_signal_pending(current) || + current->flags & PF_EXITING)) goto bypass; - /* - * We always charge the cgroup the mm_struct belongs to. - * The mm_struct's mem_cgroup changes on task migration if the - * thread group leader migrates. It's possible that mm is not - * set, if so charge the root memcg (happens for pagecache usage). - */ - if (!*ptr && !mm) - *ptr = root_mem_cgroup; -again: - if (*ptr) { /* css should be a valid one */ - memcg = *ptr; - if (mem_cgroup_is_root(memcg)) - goto done; - if (consume_stock(memcg, nr_pages)) - goto done; - css_get(&memcg->css); - } else { - struct task_struct *p; + if (unlikely(task_in_memcg_oom(current))) + goto nomem; - rcu_read_lock(); - p = rcu_dereference(mm->owner); - /* - * Because we don't have task_lock(), "p" can exit. - * In that case, "memcg" can point to root or p can be NULL with - * race with swapoff. Then, we have small risk of mis-accouning. - * But such kind of mis-account by race always happens because - * we don't have cgroup_mutex(). It's overkill and we allo that - * small race, here. - * (*) swapoff at el will charge against mm-struct not against - * task-struct. So, mm->owner can be NULL. - */ - memcg = mem_cgroup_from_task(p); - if (!memcg) - memcg = root_mem_cgroup; - if (mem_cgroup_is_root(memcg)) { - rcu_read_unlock(); - goto done; - } - if (consume_stock(memcg, nr_pages)) { - /* - * It seems dagerous to access memcg without css_get(). - * But considering how consume_stok works, it's not - * necessary. If consume_stock success, some charges - * from this memcg are cached on this cpu. So, we - * don't need to call css_get()/css_tryget() before - * calling consume_stock(). - */ - rcu_read_unlock(); - goto done; - } - /* after here, we may be blocked. we need to get refcnt */ - if (!css_tryget(&memcg->css)) { - rcu_read_unlock(); - goto again; - } - rcu_read_unlock(); - } + if (gfp_mask & __GFP_NOFAIL) + oom = false; +again: + if (consume_stock(memcg, nr_pages)) + goto done; do { - bool oom_check; + bool invoke_oom = oom && !nr_oom_retries; /* If killed, bypass charge */ - if (fatal_signal_pending(current)) { - css_put(&memcg->css); + if (fatal_signal_pending(current)) goto bypass; - } - - oom_check = false; - if (oom && !nr_oom_retries) { - oom_check = true; - nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; - } - ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages, - oom_check); + ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, + nr_pages, invoke_oom); switch (ret) { case CHARGE_OK: break; case CHARGE_RETRY: /* not in OOM situation but retry */ batch = nr_pages; - css_put(&memcg->css); - memcg = NULL; goto again; case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */ - css_put(&memcg->css); goto nomem; case CHARGE_NOMEM: /* OOM routine works */ - if (!oom) { - css_put(&memcg->css); + if (!oom || invoke_oom) goto nomem; - } - /* If oom, we never return -ENOMEM */ nr_oom_retries--; break; - case CHARGE_OOM_DIE: /* Killed by OOM Killer */ - css_put(&memcg->css); - goto bypass; } } while (ret != CHARGE_OK); if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); - css_put(&memcg->css); done: - *ptr = memcg; return 0; nomem: - *ptr = NULL; - return -ENOMEM; + if (!(gfp_mask & __GFP_NOFAIL)) + return -ENOMEM; bypass: - *ptr = root_mem_cgroup; return -EINTR; } +/** + * mem_cgroup_try_charge_mm - try charging a mm + * @mm: mm_struct to charge + * @nr_pages: number of pages to charge + * @oom: trigger OOM if reclaim fails + * + * Returns the charged mem_cgroup associated with the given mm_struct or + * NULL the charge failed. + */ +static struct mem_cgroup *mem_cgroup_try_charge_mm(struct mm_struct *mm, + gfp_t gfp_mask, + unsigned int nr_pages, + bool oom) + +{ + struct mem_cgroup *memcg; + int ret; + + memcg = get_mem_cgroup_from_mm(mm); + ret = mem_cgroup_try_charge(memcg, gfp_mask, nr_pages, oom); + css_put(&memcg->css); + if (ret == -EINTR) + memcg = root_mem_cgroup; + else if (ret) + memcg = NULL; + + return memcg; +} + /* * Somemtimes we have to undo a charge we got by try_charge(). * This function is for that and do uncharge, put css's refcnt. @@ -2657,21 +2767,16 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg, /* * A helper function to get mem_cgroup from ID. must be called under - * rcu_read_lock(). The caller is responsible for calling css_tryget if - * the mem_cgroup is used for charging. (dropping refcnt from swap can be - * called against removed memcg.) + * rcu_read_lock(). The caller is responsible for calling + * css_tryget_online() if the mem_cgroup is used for charging. (dropping + * refcnt from swap can be called against removed memcg.) */ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) { - struct cgroup_subsys_state *css; - /* ID 0 is unused ID */ if (!id) return NULL; - css = css_lookup(&mem_cgroup_subsys, id); - if (!css) - return NULL; - return mem_cgroup_from_css(css); + return mem_cgroup_from_id(id); } struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) @@ -2681,20 +2786,20 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) unsigned short id; swp_entry_t ent; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); pc = lookup_page_cgroup(page); lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { memcg = pc->mem_cgroup; - if (memcg && !css_tryget(&memcg->css)) + if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; } else if (PageSwapCache(page)) { ent.val = page_private(page); id = lookup_swap_cgroup_id(ent); rcu_read_lock(); memcg = mem_cgroup_lookup(id); - if (memcg && !css_tryget(&memcg->css)) + if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; rcu_read_unlock(); } @@ -2715,7 +2820,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, bool anon; lock_page_cgroup(pc); - VM_BUG_ON(PageCgroupUsed(pc)); + VM_BUG_ON_PAGE(PageCgroupUsed(pc), page); /* * we don't need page_cgroup_lock about tail pages, becase they are not * accessed by any other context at this point. @@ -2743,14 +2848,14 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, * is accessed after testing USED bit. To make pc->mem_cgroup visible * before USED bit, we need memory barrier here. * See mem_cgroup_add_lru_list(), etc. - */ + */ smp_wmb(); SetPageCgroupUsed(pc); if (lrucare) { if (was_on_lru) { lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, page_lru(page)); } @@ -2762,7 +2867,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, else anon = false; - mem_cgroup_charge_statistics(memcg, anon, nr_pages); + mem_cgroup_charge_statistics(memcg, page, anon, nr_pages); unlock_page_cgroup(pc); /* @@ -2776,10 +2881,18 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, static DEFINE_MUTEX(set_limit_mutex); #ifdef CONFIG_MEMCG_KMEM +/* + * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or + * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists. + */ +static DEFINE_MUTEX(memcg_slab_mutex); + +static DEFINE_MUTEX(activate_kmem_mutex); + static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg) { return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) && - (memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK); + memcg_kmem_is_active(memcg); } /* @@ -2792,14 +2905,13 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) VM_BUG_ON(p->is_root_cache); cachep = p->root_cache; - return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)]; + return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg)); } #ifdef CONFIG_SLABINFO -static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft, - struct seq_file *m) +static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); struct memcg_cache_params *params; if (!memcg_can_account_kmem(memcg)) @@ -2807,10 +2919,10 @@ static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft, print_slabinfo_header(m); - mutex_lock(&memcg->slab_caches_mutex); + mutex_lock(&memcg_slab_mutex); list_for_each_entry(params, &memcg->memcg_slab_caches, list) cache_show(memcg_params_to_cache(params), m); - mutex_unlock(&memcg->slab_caches_mutex); + mutex_unlock(&memcg_slab_mutex); return 0; } @@ -2819,27 +2931,17 @@ static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft, static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) { struct res_counter *fail_res; - struct mem_cgroup *_memcg; int ret = 0; - bool may_oom; ret = res_counter_charge(&memcg->kmem, size, &fail_res); if (ret) return ret; - /* - * Conditions under which we can wait for the oom_killer. Those are - * the same conditions tested by the core page allocator - */ - may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY); - - _memcg = memcg; - ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT, - &_memcg, may_oom); - + ret = mem_cgroup_try_charge(memcg, gfp, size >> PAGE_SHIFT, + oom_gfp_allowed(gfp)); if (ret == -EINTR) { /* - * __mem_cgroup_try_charge() chosed to bypass to root due to + * mem_cgroup_try_charge() chosed to bypass to root due to * OOM kill or fatal signal. Since our only options are to * either fail the allocation or charge it to this cgroup, do * it as a temporary condition. But we can't fail. From a @@ -2849,7 +2951,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) * * This condition will only trigger if the task entered * memcg_charge_kmem in a sane state, but was OOM-killed during - * __mem_cgroup_try_charge() above. Tasks that were already + * mem_cgroup_try_charge() above. Tasks that were already * dying when the allocation triggers should have been already * directed to the root cgroup in memcontrol.h */ @@ -2874,18 +2976,16 @@ static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size) if (res_counter_uncharge(&memcg->kmem, size)) return; + /* + * Releases a reference taken in kmem_cgroup_css_offline in case + * this last uncharge is racing with the offlining code or it is + * outliving the memcg existence. + * + * The memory barrier imposed by test&clear is paired with the + * explicit one in memcg_kmem_mark_dead(). + */ if (memcg_kmem_test_and_clear_dead(memcg)) - mem_cgroup_put(memcg); -} - -void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep) -{ - if (!memcg) - return; - - mutex_lock(&memcg->slab_caches_mutex); - list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); - mutex_unlock(&memcg->slab_caches_mutex); + css_put(&memcg->css); } /* @@ -2898,43 +2998,6 @@ int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -/* - * This ends up being protected by the set_limit mutex, during normal - * operation, because that is its main call site. - * - * But when we create a new cache, we can call this as well if its parent - * is kmem-limited. That will have to hold set_limit_mutex as well. - */ -int memcg_update_cache_sizes(struct mem_cgroup *memcg) -{ - int num, ret; - - num = ida_simple_get(&kmem_limited_groups, - 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); - if (num < 0) - return num; - /* - * After this point, kmem_accounted (that we test atomically in - * the beginning of this conditional), is no longer 0. This - * guarantees only one process will set the following boolean - * to true. We don't need test_and_set because we're protected - * by the set_limit_mutex anyway. - */ - memcg_kmem_set_activated(memcg); - - ret = memcg_update_all_caches(num+1); - if (ret) { - ida_simple_remove(&kmem_limited_groups, num); - memcg_kmem_clear_activated(memcg); - return ret; - } - - memcg->kmemcg_id = num; - INIT_LIST_HEAD(&memcg->memcg_slab_caches); - mutex_init(&memcg->slab_caches_mutex); - return 0; -} - static size_t memcg_caches_array_size(int num_groups) { ssize_t size; @@ -2965,22 +3028,21 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) { struct memcg_cache_params *cur_params = s->memcg_params; - VM_BUG_ON(s->memcg_params && !s->memcg_params->is_root_cache); + VM_BUG_ON(!is_root_cache(s)); if (num_groups > memcg_limited_groups_array_size) { int i; + struct memcg_cache_params *new_params; ssize_t size = memcg_caches_array_size(num_groups); size *= sizeof(void *); - size += sizeof(struct memcg_cache_params); + size += offsetof(struct memcg_cache_params, memcg_caches); - s->memcg_params = kzalloc(size, GFP_KERNEL); - if (!s->memcg_params) { - s->memcg_params = cur_params; + new_params = kzalloc(size, GFP_KERNEL); + if (!new_params) return -ENOMEM; - } - s->memcg_params->is_root_cache = true; + new_params->is_root_cache = true; /* * There is the chance it will be bigger than @@ -2994,7 +3056,7 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) for (i = 0; i < memcg_limited_groups_array_size; i++) { if (!cur_params->memcg_caches[i]) continue; - s->memcg_params->memcg_caches[i] = + new_params->memcg_caches[i] = cur_params->memcg_caches[i]; } @@ -3007,21 +3069,26 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) * bigger than the others. And all updates will reset this * anyway. */ - kfree(cur_params); + rcu_assign_pointer(s->memcg_params, new_params); + if (cur_params) + kfree_rcu(cur_params, rcu_head); } return 0; } -int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s, - struct kmem_cache *root_cache) +int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, + struct kmem_cache *root_cache) { - size_t size = sizeof(struct memcg_cache_params); + size_t size; if (!memcg_kmem_enabled()) return 0; - if (!memcg) + if (!memcg) { + size = offsetof(struct memcg_cache_params, memcg_caches); size += memcg_limited_groups_array_size * sizeof(void *); + } else + size = sizeof(struct memcg_cache_params); s->memcg_params = kzalloc(size, GFP_KERNEL); if (!s->memcg_params) @@ -3030,39 +3097,85 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s, if (memcg) { s->memcg_params->memcg = memcg; s->memcg_params->root_cache = root_cache; - } + css_get(&memcg->css); + } else + s->memcg_params->is_root_cache = true; + return 0; } -void memcg_release_cache(struct kmem_cache *s) +void memcg_free_cache_params(struct kmem_cache *s) { - struct kmem_cache *root; - struct mem_cgroup *memcg; + if (!s->memcg_params) + return; + if (!s->memcg_params->is_root_cache) + css_put(&s->memcg_params->memcg->css); + kfree(s->memcg_params); +} + +static void memcg_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) +{ + static char memcg_name_buf[NAME_MAX + 1]; /* protected by + memcg_slab_mutex */ + struct kmem_cache *cachep; int id; + lockdep_assert_held(&memcg_slab_mutex); + + id = memcg_cache_id(memcg); + /* - * This happens, for instance, when a root cache goes away before we - * add any memcg. + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. */ - if (!s->memcg_params) + if (cache_from_memcg_idx(root_cache, id)) return; - if (s->memcg_params->is_root_cache) - goto out; + cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); + cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf); + /* + * If we could not create a memcg cache, do not complain, because + * that's not critical at all as we can always proceed with the root + * cache. + */ + if (!cachep) + return; - memcg = s->memcg_params->memcg; - id = memcg_cache_id(memcg); + list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); - root = s->memcg_params->root_cache; - root->memcg_params->memcg_caches[id] = NULL; - mem_cgroup_put(memcg); + /* + * Since readers won't lock (see cache_from_memcg_idx()), we need a + * barrier here to ensure nobody will see the kmem_cache partially + * initialized. + */ + smp_wmb(); - mutex_lock(&memcg->slab_caches_mutex); - list_del(&s->memcg_params->list); - mutex_unlock(&memcg->slab_caches_mutex); + BUG_ON(root_cache->memcg_params->memcg_caches[id]); + root_cache->memcg_params->memcg_caches[id] = cachep; +} -out: - kfree(s->memcg_params); +static void memcg_unregister_cache(struct kmem_cache *cachep) +{ + struct kmem_cache *root_cache; + struct mem_cgroup *memcg; + int id; + + lockdep_assert_held(&memcg_slab_mutex); + + BUG_ON(is_root_cache(cachep)); + + root_cache = cachep->memcg_params->root_cache; + memcg = cachep->memcg_params->memcg; + id = memcg_cache_id(memcg); + + BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep); + root_cache->memcg_params->memcg_caches[id] = NULL; + + list_del(&cachep->memcg_params->list); + + kmem_cache_destroy(cachep); } /* @@ -3096,266 +3209,93 @@ static inline void memcg_resume_kmem_account(void) current->memcg_kmem_skip_account--; } -static void kmem_cache_destroy_work_func(struct work_struct *w) -{ - struct kmem_cache *cachep; - struct memcg_cache_params *p; - - p = container_of(w, struct memcg_cache_params, destroy); - - cachep = memcg_params_to_cache(p); - - /* - * If we get down to 0 after shrink, we could delete right away. - * However, memcg_release_pages() already puts us back in the workqueue - * in that case. If we proceed deleting, we'll get a dangling - * reference, and removing the object from the workqueue in that case - * is unnecessary complication. We are not a fast path. - * - * Note that this case is fundamentally different from racing with - * shrink_slab(): if memcg_cgroup_destroy_cache() is called in - * kmem_cache_shrink, not only we would be reinserting a dead cache - * into the queue, but doing so from inside the worker racing to - * destroy it. - * - * So if we aren't down to zero, we'll just schedule a worker and try - * again - */ - if (atomic_read(&cachep->memcg_params->nr_pages) != 0) { - kmem_cache_shrink(cachep); - if (atomic_read(&cachep->memcg_params->nr_pages) == 0) - return; - } else - kmem_cache_destroy(cachep); -} - -void mem_cgroup_destroy_cache(struct kmem_cache *cachep) -{ - if (!cachep->memcg_params->dead) - return; - - /* - * There are many ways in which we can get here. - * - * We can get to a memory-pressure situation while the delayed work is - * still pending to run. The vmscan shrinkers can then release all - * cache memory and get us to destruction. If this is the case, we'll - * be executed twice, which is a bug (the second time will execute over - * bogus data). In this case, cancelling the work should be fine. - * - * But we can also get here from the worker itself, if - * kmem_cache_shrink is enough to shake all the remaining objects and - * get the page count to 0. In this case, we'll deadlock if we try to - * cancel the work (the worker runs with an internal lock held, which - * is the same lock we would hold for cancel_work_sync().) - * - * Since we can't possibly know who got us here, just refrain from - * running if there is already work pending - */ - if (work_pending(&cachep->memcg_params->destroy)) - return; - /* - * We have to defer the actual destroying to a workqueue, because - * we might currently be in a context that cannot sleep. - */ - schedule_work(&cachep->memcg_params->destroy); -} - -static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s) -{ - char *name; - struct dentry *dentry; - - rcu_read_lock(); - dentry = rcu_dereference(memcg->css.cgroup->dentry); - rcu_read_unlock(); - - BUG_ON(dentry == NULL); - - name = kasprintf(GFP_KERNEL, "%s(%d:%s)", s->name, - memcg_cache_id(memcg), dentry->d_name.name); - - return name; -} - -static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg, - struct kmem_cache *s) -{ - char *name; - struct kmem_cache *new; - - name = memcg_cache_name(memcg, s); - if (!name) - return NULL; - - new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align, - (s->flags & ~SLAB_PANIC), s->ctor, s); - - if (new) - new->allocflags |= __GFP_KMEMCG; - - kfree(name); - return new; -} - -/* - * This lock protects updaters, not readers. We want readers to be as fast as - * they can, and they will either see NULL or a valid cache value. Our model - * allow them to see NULL, in which case the root memcg will be selected. - * - * We need this lock because multiple allocations to the same cache from a non - * will span more than one worker. Only one of them can create the cache. - */ -static DEFINE_MUTEX(memcg_cache_mutex); -static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +int __memcg_cleanup_cache_params(struct kmem_cache *s) { - struct kmem_cache *new_cachep; - int idx; + struct kmem_cache *c; + int i, failed = 0; - BUG_ON(!memcg_can_account_kmem(memcg)); + mutex_lock(&memcg_slab_mutex); + for_each_memcg_cache_index(i) { + c = cache_from_memcg_idx(s, i); + if (!c) + continue; - idx = memcg_cache_id(memcg); + memcg_unregister_cache(c); - mutex_lock(&memcg_cache_mutex); - new_cachep = cachep->memcg_params->memcg_caches[idx]; - if (new_cachep) - goto out; - - new_cachep = kmem_cache_dup(memcg, cachep); - if (new_cachep == NULL) { - new_cachep = cachep; - goto out; + if (cache_from_memcg_idx(s, i)) + failed++; } - - mem_cgroup_get(memcg); - atomic_set(&new_cachep->memcg_params->nr_pages , 0); - - cachep->memcg_params->memcg_caches[idx] = new_cachep; - /* - * the readers won't lock, make sure everybody sees the updated value, - * so they won't put stuff in the queue again for no reason - */ - wmb(); -out: - mutex_unlock(&memcg_cache_mutex); - return new_cachep; + mutex_unlock(&memcg_slab_mutex); + return failed; } -void kmem_cache_destroy_memcg_children(struct kmem_cache *s) +static void memcg_unregister_all_caches(struct mem_cgroup *memcg) { - struct kmem_cache *c; - int i; + struct kmem_cache *cachep; + struct memcg_cache_params *params, *tmp; - if (!s->memcg_params) - return; - if (!s->memcg_params->is_root_cache) + if (!memcg_kmem_is_active(memcg)) return; - /* - * If the cache is being destroyed, we trust that there is no one else - * requesting objects from it. Even if there are, the sanity checks in - * kmem_cache_destroy should caught this ill-case. - * - * Still, we don't want anyone else freeing memcg_caches under our - * noses, which can happen if a new memcg comes to life. As usual, - * we'll take the set_limit_mutex to protect ourselves against this. - */ - mutex_lock(&set_limit_mutex); - for (i = 0; i < memcg_limited_groups_array_size; i++) { - c = s->memcg_params->memcg_caches[i]; - if (!c) - continue; - - /* - * We will now manually delete the caches, so to avoid races - * we need to cancel all pending destruction workers and - * proceed with destruction ourselves. - * - * kmem_cache_destroy() will call kmem_cache_shrink internally, - * and that could spawn the workers again: it is likely that - * the cache still have active pages until this very moment. - * This would lead us back to mem_cgroup_destroy_cache. - * - * But that will not execute at all if the "dead" flag is not - * set, so flip it down to guarantee we are in control. - */ - c->memcg_params->dead = false; - cancel_work_sync(&c->memcg_params->destroy); - kmem_cache_destroy(c); + mutex_lock(&memcg_slab_mutex); + list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { + cachep = memcg_params_to_cache(params); + kmem_cache_shrink(cachep); + if (atomic_read(&cachep->memcg_params->nr_pages) == 0) + memcg_unregister_cache(cachep); } - mutex_unlock(&set_limit_mutex); + mutex_unlock(&memcg_slab_mutex); } -struct create_work { +struct memcg_register_cache_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; struct work_struct work; }; -static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) +static void memcg_register_cache_func(struct work_struct *w) { - struct kmem_cache *cachep; - struct memcg_cache_params *params; + struct memcg_register_cache_work *cw = + container_of(w, struct memcg_register_cache_work, work); + struct mem_cgroup *memcg = cw->memcg; + struct kmem_cache *cachep = cw->cachep; - if (!memcg_kmem_is_active(memcg)) - return; + mutex_lock(&memcg_slab_mutex); + memcg_register_cache(memcg, cachep); + mutex_unlock(&memcg_slab_mutex); - mutex_lock(&memcg->slab_caches_mutex); - list_for_each_entry(params, &memcg->memcg_slab_caches, list) { - cachep = memcg_params_to_cache(params); - cachep->memcg_params->dead = true; - INIT_WORK(&cachep->memcg_params->destroy, - kmem_cache_destroy_work_func); - schedule_work(&cachep->memcg_params->destroy); - } - mutex_unlock(&memcg->slab_caches_mutex); -} - -static void memcg_create_cache_work_func(struct work_struct *w) -{ - struct create_work *cw; - - cw = container_of(w, struct create_work, work); - memcg_create_kmem_cache(cw->memcg, cw->cachep); - /* Drop the reference gotten when we enqueued. */ - css_put(&cw->memcg->css); + css_put(&memcg->css); kfree(cw); } /* * Enqueue the creation of a per-memcg kmem_cache. - * Called with rcu_read_lock. */ -static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { - struct create_work *cw; - - cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT); - if (cw == NULL) - return; + struct memcg_register_cache_work *cw; - /* The corresponding put will be done in the workqueue. */ - if (!css_tryget(&memcg->css)) { - kfree(cw); + cw = kmalloc(sizeof(*cw), GFP_NOWAIT); + if (cw == NULL) { + css_put(&memcg->css); return; } cw->memcg = memcg; cw->cachep = cachep; - INIT_WORK(&cw->work, memcg_create_cache_work_func); + INIT_WORK(&cw->work, memcg_register_cache_func); schedule_work(&cw->work); } -static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void memcg_schedule_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { /* * We need to stop accounting when we kmalloc, because if the * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_create_cache_enqueue will recurse. + * in __memcg_schedule_register_cache will recurse. * * However, it is better to enclose the whole function. Depending on * the debugging options enabled, INIT_WORK(), for instance, can @@ -3364,9 +3304,27 @@ static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, * the safest choice is to do it like this, wrapping the whole function. */ memcg_stop_kmem_account(); - __memcg_create_cache_enqueue(memcg, cachep); + __memcg_schedule_register_cache(memcg, cachep); memcg_resume_kmem_account(); } + +int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) +{ + int res; + + res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, + PAGE_SIZE << order); + if (!res) + atomic_add(1 << order, &cachep->memcg_params->nr_pages); + return res; +} + +void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) +{ + memcg_uncharge_kmem(cachep->memcg_params->memcg, PAGE_SIZE << order); + atomic_sub(1 << order, &cachep->memcg_params->nr_pages); +} + /* * Return the kmem_cache we're supposed to use for a slab allocation. * We try to use the current memcg's version of the cache. @@ -3384,7 +3342,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { struct mem_cgroup *memcg; - int idx; + struct kmem_cache *memcg_cachep; VM_BUG_ON(!cachep->memcg_params); VM_BUG_ON(!cachep->memcg_params->is_root_cache); @@ -3394,43 +3352,39 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner)); - rcu_read_unlock(); if (!memcg_can_account_kmem(memcg)) - return cachep; + goto out; - idx = memcg_cache_id(memcg); + memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg)); + if (likely(memcg_cachep)) { + cachep = memcg_cachep; + goto out; + } + + /* The corresponding put will be done in the workqueue. */ + if (!css_tryget_online(&memcg->css)) + goto out; + rcu_read_unlock(); /* - * barrier to mare sure we're always seeing the up to date value. The - * code updating memcg_caches will issue a write barrier to match this. + * If we are in a safe context (can wait, and not in interrupt + * context), we could be be predictable and return right away. + * This would guarantee that the allocation being performed + * already belongs in the new cache. + * + * However, there are some clashes that can arrive from locking. + * For instance, because we acquire the slab_mutex while doing + * memcg_create_kmem_cache, this means no further allocation + * could happen with the slab_mutex held. So it's better to + * defer everything. */ - read_barrier_depends(); - if (unlikely(cachep->memcg_params->memcg_caches[idx] == NULL)) { - /* - * If we are in a safe context (can wait, and not in interrupt - * context), we could be be predictable and return right away. - * This would guarantee that the allocation being performed - * already belongs in the new cache. - * - * However, there are some clashes that can arrive from locking. - * For instance, because we acquire the slab_mutex while doing - * kmem_cache_dup, this means no further allocation could happen - * with the slab_mutex held. - * - * Also, because cache creation issue get_online_cpus(), this - * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex, - * that ends up reversed during cpu hotplug. (cpuset allocates - * a bunch of GFP_KERNEL memory during cpuup). Due to all that, - * better to defer everything. - */ - memcg_create_cache_enqueue(memcg, cachep); - return cachep; - } - - return cachep->memcg_params->memcg_caches[idx]; + memcg_schedule_register_cache(memcg, cachep); + return cachep; +out: + rcu_read_unlock(); + return cachep; } -EXPORT_SYMBOL(__memcg_kmem_get_cache); /* * We need to verify if the allocation against current->mm->owner's memcg is @@ -3453,16 +3407,37 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) int ret; *_memcg = NULL; - memcg = try_get_mem_cgroup_from_mm(current->mm); /* - * very rare case described in mem_cgroup_from_task. Unfortunately there - * isn't much we can do without complicating this too much, and it would - * be gfp-dependent anyway. Just let it go + * Disabling accounting is only relevant for some specific memcg + * internal allocations. Therefore we would initially not have such + * check here, since direct calls to the page allocator that are + * accounted to kmemcg (alloc_kmem_pages and friends) only happen + * outside memcg core. We are mostly concerned with cache allocations, + * and by having this test at memcg_kmem_get_cache, we are already able + * to relay the allocation to the root cache and bypass the memcg cache + * altogether. + * + * There is one exception, though: the SLUB allocator does not create + * large order caches, but rather service large kmallocs directly from + * the page allocator. Therefore, the following sequence when backed by + * the SLUB allocator: + * + * memcg_stop_kmem_account(); + * kmalloc(<large_number>) + * memcg_resume_kmem_account(); + * + * would effectively ignore the fact that we should skip accounting, + * since it will drive us directly to this function without passing + * through the cache selector memcg_kmem_get_cache. Such large + * allocations are extremely rare but can happen, for instance, for the + * cache arrays. We bring this test here. */ - if (unlikely(!memcg)) + if (!current->mm || current->memcg_kmem_skip_account) return true; + memcg = get_mem_cgroup_from_mm(current->mm); + if (!memcg_can_account_kmem(memcg)) { css_put(&memcg->css); return true; @@ -3524,11 +3499,11 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) if (!memcg) return; - VM_BUG_ON(mem_cgroup_is_root(memcg)); + VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); memcg_uncharge_kmem(memcg, PAGE_SIZE << order); } #else -static inline void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) +static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg) { } #endif /* CONFIG_MEMCG_KMEM */ @@ -3546,16 +3521,21 @@ void mem_cgroup_split_huge_fixup(struct page *head) { struct page_cgroup *head_pc = lookup_page_cgroup(head); struct page_cgroup *pc; + struct mem_cgroup *memcg; int i; if (mem_cgroup_disabled()) return; + + memcg = head_pc->mem_cgroup; for (i = 1; i < HPAGE_PMD_NR; i++) { pc = head_pc + i; - pc->mem_cgroup = head_pc->mem_cgroup; + pc->mem_cgroup = memcg; smp_wmb();/* see __commit_charge() */ pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT; } + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], + HPAGE_PMD_NR); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -3585,7 +3565,7 @@ static int mem_cgroup_move_account(struct page *page, bool anon = PageAnon(page); VM_BUG_ON(from == to); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); /* * The page is isolated from LRU. So, collapse function * will not handle this page. But page splitting can happen. @@ -3605,17 +3585,24 @@ static int mem_cgroup_move_account(struct page *page, move_lock_mem_cgroup(from, &flags); if (!anon && page_mapped(page)) { - /* Update mapped_file data for mem_cgroup */ - preempt_disable(); - __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); - __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); - preempt_enable(); + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + nr_pages); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + nr_pages); } - mem_cgroup_charge_statistics(from, anon, -nr_pages); + + if (PageWriteback(page)) { + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], + nr_pages); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_WRITEBACK], + nr_pages); + } + + mem_cgroup_charge_statistics(from, page, anon, -nr_pages); /* caller should have done css_get */ pc->mem_cgroup = to; - mem_cgroup_charge_statistics(to, anon, nr_pages); + mem_cgroup_charge_statistics(to, page, anon, nr_pages); move_unlock_mem_cgroup(from, &flags); ret = 0; unlock: @@ -3677,7 +3664,7 @@ static int mem_cgroup_move_parent(struct page *page, parent = root_mem_cgroup; if (nr_pages > 1) { - VM_BUG_ON(!PageTransHuge(page)); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); flags = compound_lock_irqsave(page); } @@ -3695,23 +3682,23 @@ out: return ret; } -/* - * Charge the memory controller for page usage. - * Return - * 0 if the charge was successful - * < 0 if the cgroup is over its limit - */ -static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, enum charge_type ctype) +int mem_cgroup_charge_anon(struct page *page, + struct mm_struct *mm, gfp_t gfp_mask) { - struct mem_cgroup *memcg = NULL; unsigned int nr_pages = 1; + struct mem_cgroup *memcg; bool oom = true; - int ret; + + if (mem_cgroup_disabled()) + return 0; + + VM_BUG_ON_PAGE(page_mapped(page), page); + VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page); + VM_BUG_ON(!mm); if (PageTransHuge(page)) { nr_pages <<= compound_order(page); - VM_BUG_ON(!PageTransHuge(page)); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* * Never OOM-kill a process for a huge page. The * fault handler will fall back to regular pages. @@ -3719,25 +3706,14 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, oom = false; } - ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom); - if (ret == -ENOMEM) - return ret; - __mem_cgroup_commit_charge(memcg, page, nr_pages, ctype, false); + memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, nr_pages, oom); + if (!memcg) + return -ENOMEM; + __mem_cgroup_commit_charge(memcg, page, nr_pages, + MEM_CGROUP_CHARGE_TYPE_ANON, false); return 0; } -int mem_cgroup_newpage_charge(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask) -{ - if (mem_cgroup_disabled()) - return 0; - VM_BUG_ON(page_mapped(page)); - VM_BUG_ON(page->mapping && !PageAnon(page)); - VM_BUG_ON(!mm); - return mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_ANON); -} - /* * While swap-in, try_charge -> commit or cancel, the page is locked. * And when try_charge() successfully returns, one refcnt to memcg without @@ -3749,7 +3725,7 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, gfp_t mask, struct mem_cgroup **memcgp) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg = NULL; struct page_cgroup *pc; int ret; @@ -3762,31 +3738,29 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, * in turn serializes uncharging. */ if (PageCgroupUsed(pc)) - return 0; - if (!do_swap_account) - goto charge_cur_mm; - memcg = try_get_mem_cgroup_from_page(page); + goto out; + if (do_swap_account) + memcg = try_get_mem_cgroup_from_page(page); if (!memcg) - goto charge_cur_mm; - *memcgp = memcg; - ret = __mem_cgroup_try_charge(NULL, mask, 1, memcgp, true); + memcg = get_mem_cgroup_from_mm(mm); + ret = mem_cgroup_try_charge(memcg, mask, 1, true); css_put(&memcg->css); if (ret == -EINTR) - ret = 0; - return ret; -charge_cur_mm: - ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true); - if (ret == -EINTR) - ret = 0; - return ret; + memcg = root_mem_cgroup; + else if (ret) + return ret; +out: + *memcgp = memcg; + return 0; } int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, gfp_t gfp_mask, struct mem_cgroup **memcgp) { - *memcgp = NULL; - if (mem_cgroup_disabled()) + if (mem_cgroup_disabled()) { + *memcgp = NULL; return 0; + } /* * A racing thread's fault, or swapoff, may have already * updated the pte, and even removed page from swap cache: in @@ -3794,12 +3768,13 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, * there's also a KSM case which does need to charge the page. */ if (!PageSwapCache(page)) { - int ret; + struct mem_cgroup *memcg; - ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, memcgp, true); - if (ret == -EINTR) - ret = 0; - return ret; + memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); + if (!memcg) + return -ENOMEM; + *memcgp = memcg; + return 0; } return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp); } @@ -3843,11 +3818,11 @@ void mem_cgroup_commit_charge_swapin(struct page *page, MEM_CGROUP_CHARGE_TYPE_ANON); } -int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, +int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { - struct mem_cgroup *memcg = NULL; enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; + struct mem_cgroup *memcg; int ret; if (mem_cgroup_disabled()) @@ -3855,15 +3830,20 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, if (PageCompound(page)) return 0; - if (!PageSwapCache(page)) - ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); - else { /* page is swapcache/shmem */ + if (PageSwapCache(page)) { /* shmem */ ret = __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg); - if (!ret) - __mem_cgroup_commit_charge_swapin(page, memcg, type); + if (ret) + return ret; + __mem_cgroup_commit_charge_swapin(page, memcg, type); + return 0; } - return ret; + + memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); + if (!memcg) + return -ENOMEM; + __mem_cgroup_commit_charge(memcg, page, 1, type, false); + return 0; } static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg, @@ -3934,11 +3914,9 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, if (mem_cgroup_disabled()) return NULL; - VM_BUG_ON(PageSwapCache(page)); - if (PageTransHuge(page)) { nr_pages <<= compound_order(page); - VM_BUG_ON(!PageTransHuge(page)); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); } /* * Check if our page_cgroup is valid @@ -3990,7 +3968,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, break; } - mem_cgroup_charge_statistics(memcg, anon, -nr_pages); + mem_cgroup_charge_statistics(memcg, page, anon, -nr_pages); ClearPageCgroupUsed(pc); /* @@ -4003,12 +3981,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, unlock_page_cgroup(pc); /* * even after unlock, we have memcg->res.usage here and this memcg - * will never be freed. + * will never be freed, so it's safe to call css_get(). */ memcg_check_events(memcg, page); if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) { mem_cgroup_swap_statistics(memcg, true); - mem_cgroup_get(memcg); + css_get(&memcg->css); } /* * Migration does not charge the res_counter for the @@ -4030,7 +4008,19 @@ void mem_cgroup_uncharge_page(struct page *page) /* early check. */ if (page_mapped(page)) return; - VM_BUG_ON(page->mapping && !PageAnon(page)); + VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page); + /* + * If the page is in swap cache, uncharge should be deferred + * to the swap path, which also properly accounts swap usage + * and handles memcg lifetime. + * + * Note that this check is not stable and reclaim may add the + * page to swap cache at any time after this. However, if the + * page is not in swap cache by the time page->mapcount hits + * 0, there won't be any page table references to the swap + * slot, and reclaim will free it and not actually write the + * page to disk. + */ if (PageSwapCache(page)) return; __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false); @@ -4038,8 +4028,8 @@ void mem_cgroup_uncharge_page(struct page *page) void mem_cgroup_uncharge_cache_page(struct page *page) { - VM_BUG_ON(page_mapped(page)); - VM_BUG_ON(page->mapping); + VM_BUG_ON_PAGE(page_mapped(page), page); + VM_BUG_ON_PAGE(page->mapping, page); __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); } @@ -4108,10 +4098,10 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) /* * record memcg information, if swapout && memcg != NULL, - * mem_cgroup_get() was called in uncharge(). + * css_get() was called in uncharge(). */ if (do_swap_account && swapout && memcg) - swap_cgroup_record(ent, css_id(&memcg->css)); + swap_cgroup_record(ent, mem_cgroup_id(memcg)); } #endif @@ -4133,13 +4123,13 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent) memcg = mem_cgroup_lookup(id); if (memcg) { /* - * We uncharge this because swap is freed. - * This memcg can be obsolete one. We avoid calling css_tryget + * We uncharge this because swap is freed. This memcg can + * be obsolete one. We avoid calling css_tryget_online(). */ if (!mem_cgroup_is_root(memcg)) res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_swap_statistics(memcg, false); - mem_cgroup_put(memcg); + css_put(&memcg->css); } rcu_read_unlock(); } @@ -4163,8 +4153,8 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry, { unsigned short old_id, new_id; - old_id = css_id(&from->css); - new_id = css_id(&to->css); + old_id = mem_cgroup_id(from); + new_id = mem_cgroup_id(to); if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { mem_cgroup_swap_statistics(from, false); @@ -4173,11 +4163,14 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry, * This function is only called from task migration context now. * It postpones res_counter and refcount handling till the end * of task migration(mem_cgroup_clear_mc()) for performance - * improvement. But we cannot postpone mem_cgroup_get(to) - * because if the process that has been moved to @to does - * swap-in, the refcount of @to might be decreased to 0. + * improvement. But we cannot postpone css_get(to) because if + * the process that has been moved to @to does swap-in, the + * refcount of @to might be decreased to 0. + * + * We are in attach() phase, so the cgroup is guaranteed to be + * alive, so we can just call css_get(). */ - mem_cgroup_get(to); + css_get(&to->css); return 0; } return -EINVAL; @@ -4340,7 +4333,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage, lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { memcg = pc->mem_cgroup; - mem_cgroup_charge_statistics(memcg, false, -1); + mem_cgroup_charge_statistics(memcg, oldpage, false, -1); ClearPageCgroupUsed(pc); } unlock_page_cgroup(pc); @@ -4389,8 +4382,8 @@ void mem_cgroup_print_bad_page(struct page *page) pc = lookup_page_cgroup_used(page); if (pc) { - printk(KERN_ALERT "pc:%p pc->flags:%lx pc->mem_cgroup:%p\n", - pc, pc->flags, pc->mem_cgroup); + pr_alert("pc:%p pc->flags:%lx pc->mem_cgroup:%p\n", + pc, pc->flags, pc->mem_cgroup); } } #endif @@ -4453,7 +4446,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, MEM_CGROUP_RECLAIM_SHRINK); curusage = res_counter_read_u64(&memcg->res, RES_USAGE); /* Usage is reduced ? */ - if (curusage >= oldusage) + if (curusage >= oldusage) retry_count--; else oldusage = curusage; @@ -4474,7 +4467,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, int enlarge = 0; /* see mem_cgroup_resize_res_limit */ - retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; + retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); while (retry_count) { if (signal_pending(current)) { @@ -4585,7 +4578,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, break; } while (1); } - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); excess = res_counter_soft_limit_excess(&mz->memcg->res); /* * One school of thought says that we should not add @@ -4596,7 +4589,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, * term TODO. */ /* If excess == 0, no tree ops */ - __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess); + __mem_cgroup_insert_exceeded(mz, mctz, excess); spin_unlock(&mctz->lock); css_put(&mz->memcg->css); loop++; @@ -4663,9 +4656,9 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg, if (mem_cgroup_move_parent(page, pc, memcg)) { /* found lock contention or "pc" is obsolete. */ busy = page; - cond_resched(); } else busy = NULL; + cond_resched(); } while (!list_empty(list)); } @@ -4717,6 +4710,30 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) } /* + * Test whether @memcg has children, dead or alive. Note that this + * function doesn't care whether @memcg has use_hierarchy enabled and + * returns %true if there are child csses according to the cgroup + * hierarchy. Testing use_hierarchy is the caller's responsiblity. + */ +static inline bool memcg_has_children(struct mem_cgroup *memcg) +{ + bool ret; + + /* + * The lock does not prevent addition or deletion of children, but + * it prevents a new child from being initialized based on this + * parent in css_online(), so it's enough to decide whether + * hierarchically inherited attributes can still be changed or not. + */ + lockdep_assert_held(&memcg_create_mutex); + + rcu_read_lock(); + ret = css_next_child(NULL, &memcg->css); + rcu_read_unlock(); + return ret; +} + +/* * Reclaims as many pages from the given memcg as possible and moves * the rest to the parent. * @@ -4725,11 +4742,6 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) static int mem_cgroup_force_empty(struct mem_cgroup *memcg) { int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct cgroup *cgrp = memcg->css.cgroup; - - /* returns EBUSY if there is a task or if we come here twice. */ - if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) - return -EBUSY; /* we call try-to-free pages for make this cgroup empty */ lru_add_drain_all(); @@ -4749,44 +4761,35 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) } } - lru_add_drain(); - mem_cgroup_reparent_charges(memcg); return 0; } -static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) +static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - int ret; + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); if (mem_cgroup_is_root(memcg)) return -EINVAL; - css_get(&memcg->css); - ret = mem_cgroup_force_empty(memcg); - css_put(&memcg->css); - - return ret; + return mem_cgroup_force_empty(memcg) ?: nbytes; } - -static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft) +static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - return mem_cgroup_from_cont(cont)->use_hierarchy; + return mem_cgroup_from_css(css)->use_hierarchy; } -static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, - u64 val) +static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) { int retval = 0; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - struct cgroup *parent = cont->parent; - struct mem_cgroup *parent_memcg = NULL; - - if (parent) - parent_memcg = mem_cgroup_from_cont(parent); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent); - cgroup_lock(); + mutex_lock(&memcg_create_mutex); if (memcg->use_hierarchy == val) goto out; @@ -4801,7 +4804,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, */ if ((!parent_memcg || !parent_memcg->use_hierarchy) && (val == 1 || val == 0)) { - if (list_empty(&cont->children)) + if (!memcg_has_children(memcg)) memcg->use_hierarchy = val; else retval = -EBUSY; @@ -4809,7 +4812,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, retval = -EINVAL; out: - cgroup_unlock(); + mutex_unlock(&memcg_create_mutex); return retval; } @@ -4841,6 +4844,10 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) return res_counter_read_u64(&memcg->memsw, RES_USAGE); } + /* + * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS + * as well as in MEM_CGROUP_STAT_RSS_HUGE. + */ val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE); val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS); @@ -4850,22 +4857,17 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) return val << PAGE_SHIFT; } -static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft, - struct file *file, char __user *buf, - size_t nbytes, loff_t *ppos) +static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - char str[64]; + struct mem_cgroup *memcg = mem_cgroup_from_css(css); u64 val; - int name, len; + int name; enum res_type type; type = MEMFILE_TYPE(cft->private); name = MEMFILE_ATTR(cft->private); - if (!do_swap_account && type == _MEMSWAP) - return -EOPNOTSUPP; - switch (type) { case _MEM: if (name == RES_USAGE) @@ -4886,17 +4888,26 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft, BUG(); } - len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val); - return simple_read_from_buffer(buf, nbytes, ppos, str, len); + return val; } -static int memcg_update_kmem_limit(struct cgroup *cont, u64 val) -{ - int ret = -EINVAL; #ifdef CONFIG_MEMCG_KMEM - bool must_inc_static_branch = false; +/* should be called with activate_kmem_mutex held */ +static int __memcg_activate_kmem(struct mem_cgroup *memcg, + unsigned long long limit) +{ + int err = 0; + int memcg_id; + + if (memcg_kmem_is_active(memcg)) + return 0; + + /* + * We are going to allocate memory for data shared by all memory + * cgroups so let's stop accounting here. + */ + memcg_stop_kmem_account(); - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); /* * For simplicity, we won't allow this to be disabled. It also can't * be changed if the cgroup has children already, or if tasks had @@ -4908,64 +4919,78 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val) * * After it first became limited, changes in the value of the limit are * of course permitted. - * - * Taking the cgroup_lock is really offensive, but it is so far the only - * way to guarantee that no children will appear. There are plenty of - * other offenders, and they should all go away. Fine grained locking - * is probably the way to go here. When we are fully hierarchical, we - * can also get rid of the use_hierarchy check. */ - cgroup_lock(); - mutex_lock(&set_limit_mutex); - if (!memcg->kmem_account_flags && val != RESOURCE_MAX) { - if (cgroup_task_count(cont) || (memcg->use_hierarchy && - !list_empty(&cont->children))) { - ret = -EBUSY; - goto out; - } - ret = res_counter_set_limit(&memcg->kmem, val); - VM_BUG_ON(ret); + mutex_lock(&memcg_create_mutex); + if (cgroup_has_tasks(memcg->css.cgroup) || + (memcg->use_hierarchy && memcg_has_children(memcg))) + err = -EBUSY; + mutex_unlock(&memcg_create_mutex); + if (err) + goto out; - ret = memcg_update_cache_sizes(memcg); - if (ret) { - res_counter_set_limit(&memcg->kmem, RESOURCE_MAX); - goto out; - } - must_inc_static_branch = true; - /* - * kmem charges can outlive the cgroup. In the case of slab - * pages, for instance, a page contain objects from various - * processes, so it is unfeasible to migrate them away. We - * need to reference count the memcg because of that. - */ - mem_cgroup_get(memcg); - } else - ret = res_counter_set_limit(&memcg->kmem, val); -out: - mutex_unlock(&set_limit_mutex); - cgroup_unlock(); + memcg_id = ida_simple_get(&kmem_limited_groups, + 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); + if (memcg_id < 0) { + err = memcg_id; + goto out; + } /* - * We are by now familiar with the fact that we can't inc the static - * branch inside cgroup_lock. See disarm functions for details. A - * worker here is overkill, but also wrong: After the limit is set, we - * must start accounting right away. Since this operation can't fail, - * we can safely defer it to here - no rollback will be needed. - * - * The boolean used to control this is also safe, because - * KMEM_ACCOUNTED_ACTIVATED guarantees that only one process will be - * able to set it to true; + * Make sure we have enough space for this cgroup in each root cache's + * memcg_params. */ - if (must_inc_static_branch) { - static_key_slow_inc(&memcg_kmem_enabled_key); - /* - * setting the active bit after the inc will guarantee no one - * starts accounting before all call sites are patched - */ - memcg_kmem_set_active(memcg); - } + mutex_lock(&memcg_slab_mutex); + err = memcg_update_all_caches(memcg_id + 1); + mutex_unlock(&memcg_slab_mutex); + if (err) + goto out_rmid; -#endif + memcg->kmemcg_id = memcg_id; + INIT_LIST_HEAD(&memcg->memcg_slab_caches); + + /* + * We couldn't have accounted to this cgroup, because it hasn't got the + * active bit set yet, so this should succeed. + */ + err = res_counter_set_limit(&memcg->kmem, limit); + VM_BUG_ON(err); + + static_key_slow_inc(&memcg_kmem_enabled_key); + /* + * Setting the active bit after enabling static branching will + * guarantee no one starts accounting before all call sites are + * patched. + */ + memcg_kmem_set_active(memcg); +out: + memcg_resume_kmem_account(); + return err; + +out_rmid: + ida_simple_remove(&kmem_limited_groups, memcg_id); + goto out; +} + +static int memcg_activate_kmem(struct mem_cgroup *memcg, + unsigned long long limit) +{ + int ret; + + mutex_lock(&activate_kmem_mutex); + ret = __memcg_activate_kmem(memcg, limit); + mutex_unlock(&activate_kmem_mutex); + return ret; +} + +static int memcg_update_kmem_limit(struct mem_cgroup *memcg, + unsigned long long val) +{ + int ret; + + if (!memcg_kmem_is_active(memcg)) + ret = memcg_activate_kmem(memcg, val); + else + ret = res_counter_set_limit(&memcg->kmem, val); return ret; } @@ -4973,59 +4998,44 @@ static int memcg_propagate_kmem(struct mem_cgroup *memcg) { int ret = 0; struct mem_cgroup *parent = parent_mem_cgroup(memcg); - if (!parent) - goto out; - memcg->kmem_account_flags = parent->kmem_account_flags; -#ifdef CONFIG_MEMCG_KMEM - /* - * When that happen, we need to disable the static branch only on those - * memcgs that enabled it. To achieve this, we would be forced to - * complicate the code by keeping track of which memcgs were the ones - * that actually enabled limits, and which ones got it from its - * parents. - * - * It is a lot simpler just to do static_key_slow_inc() on every child - * that is accounted. - */ - if (!memcg_kmem_is_active(memcg)) - goto out; + if (!parent) + return 0; + mutex_lock(&activate_kmem_mutex); /* - * destroy(), called if we fail, will issue static_key_slow_inc() and - * mem_cgroup_put() if kmem is enabled. We have to either call them - * unconditionally, or clear the KMEM_ACTIVE flag. I personally find - * this more consistent, since it always leads to the same destroy path + * If the parent cgroup is not kmem-active now, it cannot be activated + * after this point, because it has at least one child already. */ - mem_cgroup_get(memcg); - static_key_slow_inc(&memcg_kmem_enabled_key); - - mutex_lock(&set_limit_mutex); - ret = memcg_update_cache_sizes(memcg); - mutex_unlock(&set_limit_mutex); -#endif -out: + if (memcg_kmem_is_active(parent)) + ret = __memcg_activate_kmem(memcg, RES_COUNTER_MAX); + mutex_unlock(&activate_kmem_mutex); return ret; } +#else +static int memcg_update_kmem_limit(struct mem_cgroup *memcg, + unsigned long long val) +{ + return -EINVAL; +} +#endif /* CONFIG_MEMCG_KMEM */ /* * The user of this function is... * RES_LIMIT. */ -static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, - const char *buffer) +static ssize_t mem_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); enum res_type type; int name; unsigned long long val; int ret; - type = MEMFILE_TYPE(cft->private); - name = MEMFILE_ATTR(cft->private); - - if (!do_swap_account && type == _MEMSWAP) - return -EOPNOTSUPP; + buf = strstrip(buf); + type = MEMFILE_TYPE(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_LIMIT: @@ -5034,7 +5044,7 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, break; } /* This function does all necessary parse...reuse it */ - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; if (type == _MEM) @@ -5042,12 +5052,12 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, else if (type == _MEMSWAP) ret = mem_cgroup_resize_memsw_limit(memcg, val); else if (type == _KMEM) - ret = memcg_update_kmem_limit(cont, val); + ret = memcg_update_kmem_limit(memcg, val); else return -EINVAL; break; case RES_SOFT_LIMIT: - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; /* @@ -5064,24 +5074,21 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, ret = -EINVAL; /* should be BUG() ? */ break; } - return ret; + return ret ?: nbytes; } static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, unsigned long long *mem_limit, unsigned long long *memsw_limit) { - struct cgroup *cgroup; unsigned long long min_limit, min_memsw_limit, tmp; min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT); min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); - cgroup = memcg->css.cgroup; if (!memcg->use_hierarchy) goto out; - while (cgroup->parent) { - cgroup = cgroup->parent; - memcg = mem_cgroup_from_cont(cgroup); + while (memcg->css.parent) { + memcg = mem_cgroup_from_css(memcg->css.parent); if (!memcg->use_hierarchy) break; tmp = res_counter_read_u64(&memcg->res, RES_LIMIT); @@ -5094,17 +5101,15 @@ out: *memsw_limit = min_memsw_limit; } -static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) +static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); int name; enum res_type type; - type = MEMFILE_TYPE(event); - name = MEMFILE_ATTR(event); - - if (!do_swap_account && type == _MEMSWAP) - return -EOPNOTSUPP; + type = MEMFILE_TYPE(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_MAX_USAGE: @@ -5129,36 +5134,35 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) break; } - return 0; + return nbytes; } -static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp, +static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, struct cftype *cft) { - return mem_cgroup_from_cont(cgrp)->move_charge_at_immigrate; + return mem_cgroup_from_css(css)->move_charge_at_immigrate; } #ifdef CONFIG_MMU -static int mem_cgroup_move_charge_write(struct cgroup *cgrp, +static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); if (val >= (1 << NR_MOVE_TYPE)) return -EINVAL; + /* - * We check this value several times in both in can_attach() and - * attach(), so we need cgroup lock to prevent this value from being - * inconsistent. + * No kind of locking is needed in here, because ->can_attach() will + * check this value once in the beginning of the process, and then carry + * on with stale data. This means that changes to this value will only + * affect task migrations starting after the change. */ - cgroup_lock(); memcg->move_charge_at_immigrate = val; - cgroup_unlock(); - return 0; } #else -static int mem_cgroup_move_charge_write(struct cgroup *cgrp, +static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { return -ENOSYS; @@ -5166,69 +5170,64 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp, #endif #ifdef CONFIG_NUMA -static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft, - struct seq_file *m) +static int memcg_numa_stat_show(struct seq_file *m, void *v) { - int nid; - unsigned long total_nr, file_nr, anon_nr, unevictable_nr; - unsigned long node_nr; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - - total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL); - seq_printf(m, "total=%lu", total_nr); - for_each_node_state(nid, N_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL); - seq_printf(m, " N%d=%lu", nid, node_nr); - } - seq_putc(m, '\n'); + struct numa_stat { + const char *name; + unsigned int lru_mask; + }; - file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE); - seq_printf(m, "file=%lu", file_nr); - for_each_node_state(nid, N_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, - LRU_ALL_FILE); - seq_printf(m, " N%d=%lu", nid, node_nr); + static const struct numa_stat stats[] = { + { "total", LRU_ALL }, + { "file", LRU_ALL_FILE }, + { "anon", LRU_ALL_ANON }, + { "unevictable", BIT(LRU_UNEVICTABLE) }, + }; + const struct numa_stat *stat; + int nid; + unsigned long nr; + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + + for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { + nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask); + seq_printf(m, "%s=%lu", stat->name, nr); + for_each_node_state(nid, N_MEMORY) { + nr = mem_cgroup_node_nr_lru_pages(memcg, nid, + stat->lru_mask); + seq_printf(m, " N%d=%lu", nid, nr); + } + seq_putc(m, '\n'); } - seq_putc(m, '\n'); - anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON); - seq_printf(m, "anon=%lu", anon_nr); - for_each_node_state(nid, N_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, - LRU_ALL_ANON); - seq_printf(m, " N%d=%lu", nid, node_nr); + for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { + struct mem_cgroup *iter; + + nr = 0; + for_each_mem_cgroup_tree(iter, memcg) + nr += mem_cgroup_nr_lru_pages(iter, stat->lru_mask); + seq_printf(m, "hierarchical_%s=%lu", stat->name, nr); + for_each_node_state(nid, N_MEMORY) { + nr = 0; + for_each_mem_cgroup_tree(iter, memcg) + nr += mem_cgroup_node_nr_lru_pages( + iter, nid, stat->lru_mask); + seq_printf(m, " N%d=%lu", nid, nr); + } + seq_putc(m, '\n'); } - seq_putc(m, '\n'); - unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE)); - seq_printf(m, "unevictable=%lu", unevictable_nr); - for_each_node_state(nid, N_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, - BIT(LRU_UNEVICTABLE)); - seq_printf(m, " N%d=%lu", nid, node_nr); - } - seq_putc(m, '\n'); return 0; } #endif /* CONFIG_NUMA */ -static const char * const mem_cgroup_lru_names[] = { - "inactive_anon", - "active_anon", - "inactive_file", - "active_file", - "unevictable", -}; - static inline void mem_cgroup_lru_names_not_uptodate(void) { BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); } -static int memcg_stat_show(struct cgroup *cont, struct cftype *cft, - struct seq_file *m) +static int memcg_stat_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); struct mem_cgroup *mi; unsigned int i; @@ -5294,7 +5293,7 @@ static int memcg_stat_show(struct cgroup *cont, struct cftype *cft, for_each_online_node(nid) for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = mem_cgroup_zoneinfo(memcg, nid, zid); + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; rstat = &mz->lruvec.reclaim_stat; recent_rotated[0] += rstat->recent_rotated[0]; @@ -5312,39 +5311,26 @@ static int memcg_stat_show(struct cgroup *cont, struct cftype *cft, return 0; } -static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft) +static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); return mem_cgroup_swappiness(memcg); } -static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, - u64 val) +static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); - struct mem_cgroup *parent; + struct mem_cgroup *memcg = mem_cgroup_from_css(css); if (val > 100) return -EINVAL; - if (cgrp->parent == NULL) - return -EINVAL; - - parent = mem_cgroup_from_cont(cgrp->parent); - - cgroup_lock(); - - /* If under hierarchy, only empty-root can set this value */ - if ((parent->use_hierarchy) || - (memcg->use_hierarchy && !list_empty(&cgrp->children))) { - cgroup_unlock(); - return -EINVAL; - } - - memcg->swappiness = val; - - cgroup_unlock(); + if (css->parent) + memcg->swappiness = val; + else + vm_swappiness = val; return 0; } @@ -5416,15 +5402,25 @@ static int compare_thresholds(const void *a, const void *b) const struct mem_cgroup_threshold *_a = a; const struct mem_cgroup_threshold *_b = b; - return _a->threshold - _b->threshold; + if (_a->threshold > _b->threshold) + return 1; + + if (_a->threshold < _b->threshold) + return -1; + + return 0; } static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) { struct mem_cgroup_eventfd_list *ev; + spin_lock(&memcg_oom_lock); + list_for_each_entry(ev, &memcg->oom_notify, list) eventfd_signal(ev->eventfd, 1); + + spin_unlock(&memcg_oom_lock); return 0; } @@ -5436,13 +5432,11 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg) mem_cgroup_oom_notify_cb(iter); } -static int mem_cgroup_usage_register_event(struct cgroup *cgrp, - struct cftype *cft, struct eventfd_ctx *eventfd, const char *args) +static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args, enum res_type type) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup_thresholds *thresholds; struct mem_cgroup_threshold_ary *new; - enum res_type type = MEMFILE_TYPE(cft->private); u64 threshold, usage; int i, size, ret; @@ -5519,13 +5513,23 @@ unlock: return ret; } -static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp, - struct cftype *cft, struct eventfd_ctx *eventfd) +static int mem_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEM); +} + +static int memsw_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEMSWAP); +} + +static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, enum res_type type) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup_thresholds *thresholds; struct mem_cgroup_threshold_ary *new; - enum res_type type = MEMFILE_TYPE(cft->private); u64 usage; int i, j, size; @@ -5598,14 +5602,23 @@ unlock: mutex_unlock(&memcg->thresholds_lock); } -static int mem_cgroup_oom_register_event(struct cgroup *cgrp, - struct cftype *cft, struct eventfd_ctx *eventfd, const char *args) +static void mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEM); +} + +static void memsw_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEMSWAP); +} + +static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup_eventfd_list *event; - enum res_type type = MEMFILE_TYPE(cft->private); - BUG_ON(type != _OOM_TYPE); event = kmalloc(sizeof(*event), GFP_KERNEL); if (!event) return -ENOMEM; @@ -5623,14 +5636,10 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp, return 0; } -static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp, - struct cftype *cft, struct eventfd_ctx *eventfd) +static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup_eventfd_list *ev, *tmp; - enum res_type type = MEMFILE_TYPE(cft->private); - - BUG_ON(type != _OOM_TYPE); spin_lock(&memcg_oom_lock); @@ -5644,43 +5653,28 @@ static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp, spin_unlock(&memcg_oom_lock); } -static int mem_cgroup_oom_control_read(struct cgroup *cgrp, - struct cftype *cft, struct cgroup_map_cb *cb) +static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); - - cb->fill(cb, "oom_kill_disable", memcg->oom_kill_disable); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); - if (atomic_read(&memcg->under_oom)) - cb->fill(cb, "under_oom", 1); - else - cb->fill(cb, "under_oom", 0); + seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable); + seq_printf(sf, "under_oom %d\n", (bool)atomic_read(&memcg->under_oom)); return 0; } -static int mem_cgroup_oom_control_write(struct cgroup *cgrp, +static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); - struct mem_cgroup *parent; + struct mem_cgroup *memcg = mem_cgroup_from_css(css); /* cannot set to root cgroup and only 0 and 1 are allowed */ - if (!cgrp->parent || !((val == 0) || (val == 1))) + if (!css->parent || !((val == 0) || (val == 1))) return -EINVAL; - parent = mem_cgroup_from_cont(cgrp->parent); - - cgroup_lock(); - /* oom-kill-disable is a flag for subhierarchy. */ - if ((parent->use_hierarchy) || - (memcg->use_hierarchy && !list_empty(&cgrp->children))) { - cgroup_unlock(); - return -EINVAL; - } memcg->oom_kill_disable = val; if (!val) memcg_oom_recover(memcg); - cgroup_unlock(); + return 0; } @@ -5695,25 +5689,45 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) return ret; return mem_cgroup_sockets_init(memcg, ss); -}; +} -static void kmem_cgroup_destroy(struct mem_cgroup *memcg) +static void memcg_destroy_kmem(struct mem_cgroup *memcg) { mem_cgroup_sockets_destroy(memcg); +} + +static void kmem_cgroup_css_offline(struct mem_cgroup *memcg) +{ + if (!memcg_kmem_is_active(memcg)) + return; + + /* + * kmem charges can outlive the cgroup. In the case of slab + * pages, for instance, a page contain objects from various + * processes. As we prevent from taking a reference for every + * such allocation we have to be careful when doing uncharge + * (see memcg_uncharge_kmem) and here during offlining. + * + * The idea is that that only the _last_ uncharge which sees + * the dead memcg will drop the last reference. An additional + * reference is taken here before the group is marked dead + * which is then paired with css_put during uncharge resp. here. + * + * Although this might sound strange as this path is called from + * css_offline() when the referencemight have dropped down to 0 and + * shouldn't be incremented anymore (css_tryget_online() would + * fail) we do not have other options because of the kmem + * allocations lifetime. + */ + css_get(&memcg->css); memcg_kmem_mark_dead(memcg); if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0) return; - /* - * Charges already down to 0, undo mem_cgroup_get() done in the charge - * path here, being careful not to race with memcg_uncharge_kmem: it is - * possible that the charges went down to 0 between mark_dead and the - * res_counter read, so in that case, we don't need the put - */ if (memcg_kmem_test_and_clear_dead(memcg)) - mem_cgroup_put(memcg); + css_put(&memcg->css); } #else static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) @@ -5721,57 +5735,289 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) return 0; } -static void kmem_cgroup_destroy(struct mem_cgroup *memcg) +static void memcg_destroy_kmem(struct mem_cgroup *memcg) +{ +} + +static void kmem_cgroup_css_offline(struct mem_cgroup *memcg) { } #endif +/* + * DO NOT USE IN NEW FILES. + * + * "cgroup.event_control" implementation. + * + * This is way over-engineered. It tries to support fully configurable + * events for each user. Such level of flexibility is completely + * unnecessary especially in the light of the planned unified hierarchy. + * + * Please deprecate this and replace with something simpler if at all + * possible. + */ + +/* + * Unregister event and free resources. + * + * Gets called from workqueue. + */ +static void memcg_event_remove(struct work_struct *work) +{ + struct mem_cgroup_event *event = + container_of(work, struct mem_cgroup_event, remove); + struct mem_cgroup *memcg = event->memcg; + + remove_wait_queue(event->wqh, &event->wait); + + event->unregister_event(memcg, event->eventfd); + + /* Notify userspace the event is going away. */ + eventfd_signal(event->eventfd, 1); + + eventfd_ctx_put(event->eventfd); + kfree(event); + css_put(&memcg->css); +} + +/* + * Gets called on POLLHUP on eventfd when user closes it. + * + * Called with wqh->lock held and interrupts disabled. + */ +static int memcg_event_wake(wait_queue_t *wait, unsigned mode, + int sync, void *key) +{ + struct mem_cgroup_event *event = + container_of(wait, struct mem_cgroup_event, wait); + struct mem_cgroup *memcg = event->memcg; + unsigned long flags = (unsigned long)key; + + if (flags & POLLHUP) { + /* + * If the event has been detached at cgroup removal, we + * can simply return knowing the other side will cleanup + * for us. + * + * We can't race against event freeing since the other + * side will require wqh->lock via remove_wait_queue(), + * which we hold. + */ + spin_lock(&memcg->event_list_lock); + if (!list_empty(&event->list)) { + list_del_init(&event->list); + /* + * We are in atomic context, but cgroup_event_remove() + * may sleep, so we have to call it in workqueue. + */ + schedule_work(&event->remove); + } + spin_unlock(&memcg->event_list_lock); + } + + return 0; +} + +static void memcg_event_ptable_queue_proc(struct file *file, + wait_queue_head_t *wqh, poll_table *pt) +{ + struct mem_cgroup_event *event = + container_of(pt, struct mem_cgroup_event, pt); + + event->wqh = wqh; + add_wait_queue(wqh, &event->wait); +} + +/* + * DO NOT USE IN NEW FILES. + * + * Parse input and register new cgroup event handler. + * + * Input must be in format '<event_fd> <control_fd> <args>'. + * Interpretation of args is defined by control file implementation. + */ +static ssize_t memcg_write_event_control(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup_subsys_state *css = of_css(of); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup_event *event; + struct cgroup_subsys_state *cfile_css; + unsigned int efd, cfd; + struct fd efile; + struct fd cfile; + const char *name; + char *endp; + int ret; + + buf = strstrip(buf); + + efd = simple_strtoul(buf, &endp, 10); + if (*endp != ' ') + return -EINVAL; + buf = endp + 1; + + cfd = simple_strtoul(buf, &endp, 10); + if ((*endp != ' ') && (*endp != '\0')) + return -EINVAL; + buf = endp + 1; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + + event->memcg = memcg; + INIT_LIST_HEAD(&event->list); + init_poll_funcptr(&event->pt, memcg_event_ptable_queue_proc); + init_waitqueue_func_entry(&event->wait, memcg_event_wake); + INIT_WORK(&event->remove, memcg_event_remove); + + efile = fdget(efd); + if (!efile.file) { + ret = -EBADF; + goto out_kfree; + } + + event->eventfd = eventfd_ctx_fileget(efile.file); + if (IS_ERR(event->eventfd)) { + ret = PTR_ERR(event->eventfd); + goto out_put_efile; + } + + cfile = fdget(cfd); + if (!cfile.file) { + ret = -EBADF; + goto out_put_eventfd; + } + + /* the process need read permission on control file */ + /* AV: shouldn't we check that it's been opened for read instead? */ + ret = inode_permission(file_inode(cfile.file), MAY_READ); + if (ret < 0) + goto out_put_cfile; + + /* + * Determine the event callbacks and set them in @event. This used + * to be done via struct cftype but cgroup core no longer knows + * about these events. The following is crude but the whole thing + * is for compatibility anyway. + * + * DO NOT ADD NEW FILES. + */ + name = cfile.file->f_dentry->d_name.name; + + if (!strcmp(name, "memory.usage_in_bytes")) { + event->register_event = mem_cgroup_usage_register_event; + event->unregister_event = mem_cgroup_usage_unregister_event; + } else if (!strcmp(name, "memory.oom_control")) { + event->register_event = mem_cgroup_oom_register_event; + event->unregister_event = mem_cgroup_oom_unregister_event; + } else if (!strcmp(name, "memory.pressure_level")) { + event->register_event = vmpressure_register_event; + event->unregister_event = vmpressure_unregister_event; + } else if (!strcmp(name, "memory.memsw.usage_in_bytes")) { + event->register_event = memsw_cgroup_usage_register_event; + event->unregister_event = memsw_cgroup_usage_unregister_event; + } else { + ret = -EINVAL; + goto out_put_cfile; + } + + /* + * Verify @cfile should belong to @css. Also, remaining events are + * automatically removed on cgroup destruction but the removal is + * asynchronous, so take an extra ref on @css. + */ + cfile_css = css_tryget_online_from_dir(cfile.file->f_dentry->d_parent, + &memory_cgrp_subsys); + ret = -EINVAL; + if (IS_ERR(cfile_css)) + goto out_put_cfile; + if (cfile_css != css) { + css_put(cfile_css); + goto out_put_cfile; + } + + ret = event->register_event(memcg, event->eventfd, buf); + if (ret) + goto out_put_css; + + efile.file->f_op->poll(efile.file, &event->pt); + + spin_lock(&memcg->event_list_lock); + list_add(&event->list, &memcg->event_list); + spin_unlock(&memcg->event_list_lock); + + fdput(cfile); + fdput(efile); + + return nbytes; + +out_put_css: + css_put(css); +out_put_cfile: + fdput(cfile); +out_put_eventfd: + eventfd_ctx_put(event->eventfd); +out_put_efile: + fdput(efile); +out_kfree: + kfree(event); + + return ret; +} + static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), - .read = mem_cgroup_read, - .register_event = mem_cgroup_usage_register_event, - .unregister_event = mem_cgroup_usage_unregister_event, + .read_u64 = mem_cgroup_read_u64, }, { .name = "max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, }, { .name = "limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), - .write_string = mem_cgroup_write, - .read = mem_cgroup_read, + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, }, { .name = "soft_limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), - .write_string = mem_cgroup_write, - .read = mem_cgroup_read, + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, }, { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, }, { .name = "stat", - .read_seq_string = memcg_stat_show, + .seq_show = memcg_stat_show, }, { .name = "force_empty", - .trigger = mem_cgroup_force_empty_write, + .write = mem_cgroup_force_empty_write, }, { .name = "use_hierarchy", + .flags = CFTYPE_INSANE, .write_u64 = mem_cgroup_hierarchy_write, .read_u64 = mem_cgroup_hierarchy_read, }, { + .name = "cgroup.event_control", /* XXX: for compat */ + .write = memcg_write_event_control, + .flags = CFTYPE_NO_PREFIX, + .mode = S_IWUGO, + }, + { .name = "swappiness", .read_u64 = mem_cgroup_swappiness_read, .write_u64 = mem_cgroup_swappiness_write, @@ -5783,79 +6029,81 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "oom_control", - .read_map = mem_cgroup_oom_control_read, + .seq_show = mem_cgroup_oom_control_read, .write_u64 = mem_cgroup_oom_control_write, - .register_event = mem_cgroup_oom_register_event, - .unregister_event = mem_cgroup_oom_unregister_event, .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL), }, -#ifdef CONFIG_NUMA - { - .name = "numa_stat", - .read_seq_string = memcg_numa_stat_show, - }, -#endif -#ifdef CONFIG_MEMCG_SWAP - { - .name = "memsw.usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), - .read = mem_cgroup_read, - .register_event = mem_cgroup_usage_register_event, - .unregister_event = mem_cgroup_usage_unregister_event, - }, { - .name = "memsw.max_usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, - }, - { - .name = "memsw.limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), - .write_string = mem_cgroup_write, - .read = mem_cgroup_read, + .name = "pressure_level", }, +#ifdef CONFIG_NUMA { - .name = "memsw.failcnt", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .name = "numa_stat", + .seq_show = memcg_numa_stat_show, }, #endif #ifdef CONFIG_MEMCG_KMEM { .name = "kmem.limit_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), - .write_string = mem_cgroup_write, - .read = mem_cgroup_read, + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.failcnt", .private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, }, #ifdef CONFIG_SLABINFO { .name = "kmem.slabinfo", - .read_seq_string = mem_cgroup_slabinfo_read, + .seq_show = mem_cgroup_slabinfo_read, }, #endif #endif { }, /* terminate */ }; +#ifdef CONFIG_MEMCG_SWAP +static struct cftype memsw_cgroup_files[] = { + { + .name = "memsw.usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.failcnt", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { }, /* terminate */ +}; +#endif static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -5882,26 +6130,24 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) mz->on_tree = false; mz->memcg = memcg; } - memcg->info.nodeinfo[node] = pn; + memcg->nodeinfo[node] = pn; return 0; } static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { - kfree(memcg->info.nodeinfo[node]); + kfree(memcg->nodeinfo[node]); } static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; - int size = sizeof(struct mem_cgroup); + size_t size; - /* Can be very big if MAX_NUMNODES is very big */ - if (size < PAGE_SIZE) - memcg = kzalloc(size, GFP_KERNEL); - else - memcg = vzalloc(size); + size = sizeof(struct mem_cgroup); + size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); + memcg = kzalloc(size, GFP_KERNEL); if (!memcg) return NULL; @@ -5912,10 +6158,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) return memcg; out_free: - if (size < PAGE_SIZE) - kfree(memcg); - else - vfree(memcg); + kfree(memcg); return NULL; } @@ -5933,10 +6176,8 @@ out_free: static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - int size = sizeof(struct mem_cgroup); mem_cgroup_remove_from_trees(memcg); - free_css_id(&mem_cgroup_subsys, &memcg->css); for_each_node(node) free_mem_cgroup_per_zone_info(memcg, node); @@ -5955,53 +6196,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) * the cgroup_lock. */ disarm_static_keys(memcg); - if (size < PAGE_SIZE) - kfree(memcg); - else - vfree(memcg); -} - - -/* - * Helpers for freeing a kmalloc()ed/vzalloc()ed mem_cgroup by RCU, - * but in process context. The work_freeing structure is overlaid - * on the rcu_freeing structure, which itself is overlaid on memsw. - */ -static void free_work(struct work_struct *work) -{ - struct mem_cgroup *memcg; - - memcg = container_of(work, struct mem_cgroup, work_freeing); - __mem_cgroup_free(memcg); -} - -static void free_rcu(struct rcu_head *rcu_head) -{ - struct mem_cgroup *memcg; - - memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing); - INIT_WORK(&memcg->work_freeing, free_work); - schedule_work(&memcg->work_freeing); -} - -static void mem_cgroup_get(struct mem_cgroup *memcg) -{ - atomic_inc(&memcg->refcnt); -} - -static void __mem_cgroup_put(struct mem_cgroup *memcg, int count) -{ - if (atomic_sub_and_test(count, &memcg->refcnt)) { - struct mem_cgroup *parent = parent_mem_cgroup(memcg); - call_rcu(&memcg->rcu_freeing, free_rcu); - if (parent) - mem_cgroup_put(parent); - } -} - -static void mem_cgroup_put(struct mem_cgroup *memcg) -{ - __mem_cgroup_put(memcg, 1); + kfree(memcg); } /* @@ -6015,19 +6210,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); -#ifdef CONFIG_MEMCG_SWAP -static void __init enable_swap_cgroup(void) -{ - if (!mem_cgroup_disabled() && really_do_swap_account) - do_swap_account = 1; -} -#else -static void __init enable_swap_cgroup(void) -{ -} -#endif - -static int mem_cgroup_soft_limit_tree_init(void) +static void __init mem_cgroup_soft_limit_tree_init(void) { struct mem_cgroup_tree_per_node *rtpn; struct mem_cgroup_tree_per_zone *rtpz; @@ -6038,8 +6221,7 @@ static int mem_cgroup_soft_limit_tree_init(void) if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); - if (!rtpn) - goto err_cleanup; + BUG_ON(!rtpn); soft_limit_tree.rb_tree_per_node[node] = rtpn; @@ -6049,23 +6231,12 @@ static int mem_cgroup_soft_limit_tree_init(void) spin_lock_init(&rtpz->lock); } } - return 0; - -err_cleanup: - for_each_node(node) { - if (!soft_limit_tree.rb_tree_per_node[node]) - break; - kfree(soft_limit_tree.rb_tree_per_node[node]); - soft_limit_tree.rb_tree_per_node[node] = NULL; - } - return 1; - } static struct cgroup_subsys_state * __ref -mem_cgroup_css_alloc(struct cgroup *cont) +mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { - struct mem_cgroup *memcg, *parent; + struct mem_cgroup *memcg; long error = -ENOMEM; int node; @@ -6078,36 +6249,56 @@ mem_cgroup_css_alloc(struct cgroup *cont) goto free_out; /* root ? */ - if (cont->parent == NULL) { - int cpu; - enable_swap_cgroup(); - parent = NULL; - if (mem_cgroup_soft_limit_tree_init()) - goto free_out; + if (parent_css == NULL) { root_mem_cgroup = memcg; - for_each_possible_cpu(cpu) { - struct memcg_stock_pcp *stock = - &per_cpu(memcg_stock, cpu); - INIT_WORK(&stock->work, drain_local_stock); - } - } else { - parent = mem_cgroup_from_cont(cont->parent); - memcg->use_hierarchy = parent->use_hierarchy; - memcg->oom_kill_disable = parent->oom_kill_disable; + res_counter_init(&memcg->res, NULL); + res_counter_init(&memcg->memsw, NULL); + res_counter_init(&memcg->kmem, NULL); } - if (parent && parent->use_hierarchy) { + memcg->last_scanned_node = MAX_NUMNODES; + INIT_LIST_HEAD(&memcg->oom_notify); + memcg->move_charge_at_immigrate = 0; + mutex_init(&memcg->thresholds_lock); + spin_lock_init(&memcg->move_lock); + vmpressure_init(&memcg->vmpressure); + INIT_LIST_HEAD(&memcg->event_list); + spin_lock_init(&memcg->event_list_lock); + + return &memcg->css; + +free_out: + __mem_cgroup_free(memcg); + return ERR_PTR(error); +} + +static int +mem_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *parent = mem_cgroup_from_css(css->parent); + + if (css->id > MEM_CGROUP_ID_MAX) + return -ENOSPC; + + if (!parent) + return 0; + + mutex_lock(&memcg_create_mutex); + + memcg->use_hierarchy = parent->use_hierarchy; + memcg->oom_kill_disable = parent->oom_kill_disable; + memcg->swappiness = mem_cgroup_swappiness(parent); + + if (parent->use_hierarchy) { res_counter_init(&memcg->res, &parent->res); res_counter_init(&memcg->memsw, &parent->memsw); res_counter_init(&memcg->kmem, &parent->kmem); /* - * We increment refcnt of the parent to ensure that we can - * safely access it on res_counter_charge/uncharge. - * This refcnt will be decremented when freeing this - * mem_cgroup(see mem_cgroup_put). + * No need to take a reference to the parent because cgroup + * core guarantees its existence. */ - mem_cgroup_get(parent); } else { res_counter_init(&memcg->res, NULL); res_counter_init(&memcg->memsw, NULL); @@ -6117,50 +6308,107 @@ mem_cgroup_css_alloc(struct cgroup *cont) * much sense so let cgroup subsystem know about this * unfortunate state in our controller. */ - if (parent && parent != root_mem_cgroup) - mem_cgroup_subsys.broken_hierarchy = true; + if (parent != root_mem_cgroup) + memory_cgrp_subsys.broken_hierarchy = true; } - memcg->last_scanned_node = MAX_NUMNODES; - INIT_LIST_HEAD(&memcg->oom_notify); - - if (parent) - memcg->swappiness = mem_cgroup_swappiness(parent); - atomic_set(&memcg->refcnt, 1); - memcg->move_charge_at_immigrate = 0; - mutex_init(&memcg->thresholds_lock); - spin_lock_init(&memcg->move_lock); + mutex_unlock(&memcg_create_mutex); - error = memcg_init_kmem(memcg, &mem_cgroup_subsys); - if (error) { - /* - * We call put now because our (and parent's) refcnts - * are already in place. mem_cgroup_put() will internally - * call __mem_cgroup_free, so return directly - */ - mem_cgroup_put(memcg); - return ERR_PTR(error); - } - return &memcg->css; -free_out: - __mem_cgroup_free(memcg); - return ERR_PTR(error); + return memcg_init_kmem(memcg, &memory_cgrp_subsys); } -static void mem_cgroup_css_offline(struct cgroup *cont) +/* + * Announce all parents that a group from their hierarchy is gone. + */ +static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *parent = memcg; - mem_cgroup_reparent_charges(memcg); - mem_cgroup_destroy_all_caches(memcg); + while ((parent = parent_mem_cgroup(parent))) + mem_cgroup_iter_invalidate(parent); + + /* + * if the root memcg is not hierarchical we have to check it + * explicitely. + */ + if (!root_mem_cgroup->use_hierarchy) + mem_cgroup_iter_invalidate(root_mem_cgroup); } -static void mem_cgroup_css_free(struct cgroup *cont) +static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup_event *event, *tmp; + struct cgroup_subsys_state *iter; + + /* + * Unregister events and notify userspace. + * Notify userspace about cgroup removing only after rmdir of cgroup + * directory to avoid race between userspace and kernelspace. + */ + spin_lock(&memcg->event_list_lock); + list_for_each_entry_safe(event, tmp, &memcg->event_list, list) { + list_del_init(&event->list); + schedule_work(&event->remove); + } + spin_unlock(&memcg->event_list_lock); + + kmem_cgroup_css_offline(memcg); + + mem_cgroup_invalidate_reclaim_iterators(memcg); + + /* + * This requires that offlining is serialized. Right now that is + * guaranteed because css_killed_work_fn() holds the cgroup_mutex. + */ + css_for_each_descendant_post(iter, css) + mem_cgroup_reparent_charges(mem_cgroup_from_css(iter)); - kmem_cgroup_destroy(memcg); + memcg_unregister_all_caches(memcg); + vmpressure_cleanup(&memcg->vmpressure); +} + +static void mem_cgroup_css_free(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + /* + * XXX: css_offline() would be where we should reparent all + * memory to prepare the cgroup for destruction. However, + * memcg does not do css_tryget_online() and res_counter charging + * under the same RCU lock region, which means that charging + * could race with offlining. Offlining only happens to + * cgroups with no tasks in them but charges can show up + * without any tasks from the swapin path when the target + * memcg is looked up from the swapout record and not from the + * current task as it usually is. A race like this can leak + * charges and put pages with stale cgroup pointers into + * circulation: + * + * #0 #1 + * lookup_swap_cgroup_id() + * rcu_read_lock() + * mem_cgroup_lookup() + * css_tryget_online() + * rcu_read_unlock() + * disable css_tryget_online() + * call_rcu() + * offline_css() + * reparent_charges() + * res_counter_charge() + * css_put() + * css_free() + * pc->mem_cgroup = dead memcg + * add page to lru + * + * The bulk of the charges are still moved in offline_css() to + * avoid pinning a lot of pages in case a long-term reference + * like a swapout record is deferring the css_free() to long + * after offlining. But this makes sure we catch any charges + * made after offlining: + */ + mem_cgroup_reparent_charges(memcg); - mem_cgroup_put(memcg); + memcg_destroy_kmem(memcg); + __mem_cgroup_free(memcg); } #ifdef CONFIG_MMU @@ -6207,8 +6455,7 @@ one_by_one: batch_count = PRECHARGE_COUNT_AT_ONCE; cond_resched(); } - ret = __mem_cgroup_try_charge(NULL, - GFP_KERNEL, 1, &memcg, false); + ret = mem_cgroup_try_charge(memcg, GFP_KERNEL, 1, false); if (ret) /* mem_cgroup_clear_mc() will do uncharge later */ return ret; @@ -6279,7 +6526,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, * Because lookup_swap_cache() updates some statistics counter, * we call find_get_page() with swapper_space directly. */ - page = find_get_page(&swapper_space, ent.val); + page = find_get_page(swap_address_space(ent), ent.val); if (do_swap_account) entry->val = ent.val; @@ -6312,16 +6559,20 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, pgoff = pte_to_pgoff(ptent); /* page is moved even if it's not RSS of this task(page-faulted). */ - page = find_get_page(mapping, pgoff); - #ifdef CONFIG_SWAP /* shmem/tmpfs may report page out on swap: account for that too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - if (do_swap_account) - *entry = swap; - page = find_get_page(&swapper_space, swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + if (do_swap_account) + *entry = swp; + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif return page; } @@ -6360,7 +6611,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, } /* There is a swap entry and a page doesn't exist or isn't charged */ if (ent.val && !ret && - css_id(&mc.from->css) == lookup_swap_cgroup_id(ent)) { + mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) { ret = MC_TARGET_SWAP; if (target) target->ent = ent; @@ -6382,7 +6633,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, enum mc_target_type ret = MC_TARGET_NONE; page = pmd_page(pmd); - VM_BUG_ON(!page || !PageHead(page)); + VM_BUG_ON_PAGE(!page || !PageHead(page), page); if (!move_anon()) return ret; pc = lookup_page_cgroup(page); @@ -6411,10 +6662,10 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) mc.precharge += HPAGE_PMD_NR; - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } @@ -6469,6 +6720,7 @@ static void __mem_cgroup_clear_mc(void) { struct mem_cgroup *from = mc.from; struct mem_cgroup *to = mc.to; + int i; /* we must uncharge all the leftover precharges from mc.to */ if (mc.precharge) { @@ -6489,7 +6741,9 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.from)) res_counter_uncharge(&mc.from->memsw, PAGE_SIZE * mc.moved_swap); - __mem_cgroup_put(mc.from, mc.moved_swap); + + for (i = 0; i < mc.moved_swap; i++) + css_put(&mc.from->css); if (!mem_cgroup_is_root(mc.to)) { /* @@ -6499,7 +6753,7 @@ static void __mem_cgroup_clear_mc(void) res_counter_uncharge(&mc.to->res, PAGE_SIZE * mc.moved_swap); } - /* we've already done mem_cgroup_get(mc.to) */ + /* we've already done css_get(mc.to) */ mc.moved_swap = 0; } memcg_oom_recover(from); @@ -6524,14 +6778,21 @@ static void mem_cgroup_clear_mc(void) mem_cgroup_end_move(from); } -static int mem_cgroup_can_attach(struct cgroup *cgroup, +static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *p = cgroup_taskset_first(tset); int ret = 0; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + unsigned long move_charge_at_immigrate; - if (memcg->move_charge_at_immigrate) { + /* + * We are now commited to this value whatever it is. Changes in this + * tunable will only affect upcoming migrations, not the current one. + * So we need to save it, and keep it going. + */ + move_charge_at_immigrate = memcg->move_charge_at_immigrate; + if (move_charge_at_immigrate) { struct mm_struct *mm; struct mem_cgroup *from = mem_cgroup_from_task(p); @@ -6551,6 +6812,7 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup, spin_lock(&mc.lock); mc.from = from; mc.to = memcg; + mc.immigrate_flags = move_charge_at_immigrate; spin_unlock(&mc.lock); /* We set mc.moving_task later */ @@ -6563,7 +6825,7 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup *cgroup, +static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { mem_cgroup_clear_mc(); @@ -6592,9 +6854,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, * to be unlocked in __split_huge_page_splitting(), where the main * part of thp split is not executed yet. */ - if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { if (mc.precharge < HPAGE_PMD_NR) { - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); @@ -6611,7 +6873,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, } put_page(page); } - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } @@ -6711,7 +6973,7 @@ retry: up_read(&mm->mmap_sem); } -static void mem_cgroup_move_task(struct cgroup *cont, +static void mem_cgroup_move_task(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *p = cgroup_taskset_first(tset); @@ -6726,52 +6988,52 @@ static void mem_cgroup_move_task(struct cgroup *cont, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup *cgroup, +static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup *cgroup, +static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup *cont, +static void mem_cgroup_move_task(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { } #endif -struct cgroup_subsys mem_cgroup_subsys = { - .name = "memory", - .subsys_id = mem_cgroup_subsys_id, +/* + * Cgroup retains root cgroups across [un]mount cycles making it necessary + * to verify sane_behavior flag on each mount attempt. + */ +static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) +{ + /* + * use_hierarchy is forced with sane_behavior. cgroup core + * guarantees that @root doesn't have any children, so turning it + * on for the root memcg is enough. + */ + if (cgroup_sane_behavior(root_css->cgroup)) + mem_cgroup_from_css(root_css)->use_hierarchy = true; +} + +struct cgroup_subsys memory_cgrp_subsys = { .css_alloc = mem_cgroup_css_alloc, + .css_online = mem_cgroup_css_online, .css_offline = mem_cgroup_css_offline, .css_free = mem_cgroup_css_free, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, + .bind = mem_cgroup_bind, .base_cftypes = mem_cgroup_files, .early_init = 0, - .use_id = 1, }; -/* - * The rest of init is performed during ->css_alloc() for root css which - * happens before initcalls. hotcpu_notifier() can't be done together as - * it would introduce circular locking by adding cgroup_lock -> cpu hotplug - * dependency. Do it from a subsys_initcall(). - */ -static int __init mem_cgroup_init(void) -{ - hotcpu_notifier(memcg_cpu_hotplug_callback, 0); - return 0; -} -subsys_initcall(mem_cgroup_init); - #ifdef CONFIG_MEMCG_SWAP static int __init enable_swap_account(char *s) { - /* consider enabled if no parameter or 1 is given */ if (!strcmp(s, "1")) really_do_swap_account = 1; else if (!strcmp(s, "0")) @@ -6780,4 +7042,39 @@ static int __init enable_swap_account(char *s) } __setup("swapaccount=", enable_swap_account); +static void __init memsw_file_init(void) +{ + WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, memsw_cgroup_files)); +} + +static void __init enable_swap_cgroup(void) +{ + if (!mem_cgroup_disabled() && really_do_swap_account) { + do_swap_account = 1; + memsw_file_init(); + } +} + +#else +static void __init enable_swap_cgroup(void) +{ +} #endif + +/* + * subsys_initcall() for memory controller. + * + * Some parts like hotcpu_notifier() have to be initialized from this context + * because of lock dependencies (cgroup_lock -> cpu hotplug) but basically + * everything that doesn't depend on a specific mem_cgroup structure should + * be initialized from here. + */ +static int __init mem_cgroup_init(void) +{ + hotcpu_notifier(memcg_cpu_hotplug_callback, 0); + enable_swap_cgroup(); + mem_cgroup_soft_limit_tree_init(); + memcg_stock_init(); + return 0; +} +subsys_initcall(mem_cgroup_init); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c6e4dd3e1c0..a013bc94ebb 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -61,7 +61,7 @@ int sysctl_memory_failure_early_kill __read_mostly = 0; int sysctl_memory_failure_recovery __read_mostly = 1; -atomic_long_t mce_bad_pages __read_mostly = ATOMIC_LONG_INIT(0); +atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE) @@ -145,14 +145,10 @@ static int hwpoison_filter_task(struct page *p) return -EINVAL; css = mem_cgroup_css(mem); - /* root_mem_cgroup has NULL dentries */ - if (!css->cgroup->dentry) - return -EINVAL; - - ino = css->cgroup->dentry->d_inode->i_ino; + ino = cgroup_ino(css->cgroup); css_put(css); - if (ino != hwpoison_filter_memcg) + if (!ino || ino != hwpoison_filter_memcg) return -EINVAL; return 0; @@ -206,11 +202,11 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, #ifdef __ARCH_SI_TRAPNO si.si_trapno = trapno; #endif - si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT; + si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; - if ((flags & MF_ACTION_REQUIRED) && t == current) { + if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { si.si_code = BUS_MCEERR_AR; - ret = force_sig_info(SIGBUS, &si, t); + ret = force_sig_info(SIGBUS, &si, current); } else { /* * Don't use force here, it's convenient if the signal @@ -248,10 +244,12 @@ void shake_page(struct page *p, int access) */ if (access) { int nr; + int nid = page_to_nid(p); do { struct shrink_control shrink = { .gfp_mask = GFP_KERNEL, }; + node_set(nid, shrink.nodes_to_scan); nr = shrink_slab(&shrink, 1000, 1000); if (page_count(p) == 1) @@ -382,20 +380,51 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, } } -static int task_early_kill(struct task_struct *tsk) +/* + * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO) + * on behalf of the thread group. Return task_struct of the (first found) + * dedicated thread if found, and return NULL otherwise. + * + * We already hold read_lock(&tasklist_lock) in the caller, so we don't + * have to call rcu_read_lock/unlock() in this function. + */ +static struct task_struct *find_early_kill_thread(struct task_struct *tsk) { + struct task_struct *t; + + for_each_thread(tsk, t) + if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY)) + return t; + return NULL; +} + +/* + * Determine whether a given process is "early kill" process which expects + * to be signaled when some page under the process is hwpoisoned. + * Return task_struct of the dedicated thread (main thread unless explicitly + * specified) if the process is "early kill," and otherwise returns NULL. + */ +static struct task_struct *task_early_kill(struct task_struct *tsk, + int force_early) +{ + struct task_struct *t; if (!tsk->mm) - return 0; - if (tsk->flags & PF_MCE_PROCESS) - return !!(tsk->flags & PF_MCE_EARLY); - return sysctl_memory_failure_early_kill; + return NULL; + if (force_early) + return tsk; + t = find_early_kill_thread(tsk); + if (t) + return t; + if (sysctl_memory_failure_early_kill) + return tsk; + return NULL; } /* * Collect processes when the error hit an anonymous page. */ static void collect_procs_anon(struct page *page, struct list_head *to_kill, - struct to_kill **tkc) + struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -406,20 +435,21 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, if (av == NULL) /* Not actually mapped anymore */ return; - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff = page_to_pgoff(page); read_lock(&tasklist_lock); for_each_process (tsk) { struct anon_vma_chain *vmac; + struct task_struct *t = task_early_kill(tsk, force_early); - if (!task_early_kill(tsk)) + if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, pgoff, pgoff) { vma = vmac->vma; if (!page_mapped_in_vma(page, vma)) continue; - if (vma->vm_mm == tsk->mm) - add_to_kill(tsk, page, vma, to_kill, tkc); + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); @@ -430,7 +460,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, * Collect processes when the error hit a file mapped page. */ static void collect_procs_file(struct page *page, struct list_head *to_kill, - struct to_kill **tkc) + struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -439,11 +469,11 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, mutex_lock(&mapping->i_mmap_mutex); read_lock(&tasklist_lock); for_each_process(tsk) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page_to_pgoff(page); + struct task_struct *t = task_early_kill(tsk, force_early); - if (!task_early_kill(tsk)) + if (!t) continue; - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { /* @@ -453,8 +483,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * Assume applications who requested early kill want * to be informed of all such data corruptions. */ - if (vma->vm_mm == tsk->mm) - add_to_kill(tsk, page, vma, to_kill, tkc); + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); @@ -467,7 +497,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * First preallocate one tokill structure outside the spin locks, * so that we can kill at least one process reasonably reliable. */ -static void collect_procs(struct page *page, struct list_head *tokill) +static void collect_procs(struct page *page, struct list_head *tokill, + int force_early) { struct to_kill *tk; @@ -478,9 +509,9 @@ static void collect_procs(struct page *page, struct list_head *tokill) if (!tk) return; if (PageAnon(page)) - collect_procs_anon(page, tokill, &tk); + collect_procs_anon(page, tokill, &tk, force_early); else - collect_procs_file(page, tokill, &tk); + collect_procs_file(page, tokill, &tk, force_early); kfree(tk); } @@ -609,7 +640,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) } /* - * Dirty cache page page + * Dirty pagecache page * Issues: when the error hit a hole page the error is not properly * propagated. */ @@ -784,11 +815,11 @@ static struct page_state { { sc|dirty, sc|dirty, "dirty swapcache", me_swapcache_dirty }, { sc|dirty, sc, "clean swapcache", me_swapcache_clean }, - { unevict|dirty, unevict|dirty, "dirty unevictable LRU", me_pagecache_dirty }, - { unevict, unevict, "clean unevictable LRU", me_pagecache_clean }, - { mlock|dirty, mlock|dirty, "dirty mlocked LRU", me_pagecache_dirty }, - { mlock, mlock, "clean mlocked LRU", me_pagecache_clean }, + { mlock|dirty, mlock, "clean mlocked LRU", me_pagecache_clean }, + + { unevict|dirty, unevict|dirty, "dirty unevictable LRU", me_pagecache_dirty }, + { unevict|dirty, unevict, "clean unevictable LRU", me_pagecache_clean }, { lru|dirty, lru|dirty, "dirty LRU", me_pagecache_dirty }, { lru|dirty, lru, "clean LRU", me_pagecache_clean }, @@ -854,18 +885,24 @@ static int page_action(struct page_state *ps, struct page *p, * the pages and send SIGBUS to the processes if the data was dirty. */ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, - int trapno, int flags) + int trapno, int flags, struct page **hpagep) { enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; struct address_space *mapping; LIST_HEAD(tokill); int ret; int kill = 1, forcekill; - struct page *hpage = compound_head(p); + struct page *hpage = *hpagep; struct page *ppage; + /* + * Here we are interested only in user-mapped pages, so skip any + * other types of pages. + */ if (PageReserved(p) || PageSlab(p)) return SWAP_SUCCESS; + if (!(PageLRU(hpage) || PageHuge(p))) + return SWAP_SUCCESS; /* * This check implies we don't kill processes if their pages @@ -874,8 +911,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, if (!page_mapped(hpage)) return SWAP_SUCCESS; - if (PageKsm(p)) + if (PageKsm(p)) { + pr_err("MCE %#lx: can't handle KSM pages.\n", pfn); return SWAP_FAIL; + } if (PageSwapCache(p)) { printk(KERN_ERR @@ -936,6 +975,21 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, BUG_ON(!PageHWPoison(p)); return SWAP_FAIL; } + /* + * We pinned the head page for hwpoison handling, + * now we split the thp and we are interested in + * the hwpoisoned raw page, so move the refcount + * to it. Similarly, page lock is shifted. + */ + if (hpage != p) { + if (!(flags & MF_COUNT_INCREASED)) { + put_page(hpage); + get_page(p); + } + lock_page(p); + unlock_page(hpage); + *hpagep = p; + } /* THP is split, so ppage should be the real poisoned page. */ ppage = p; } @@ -950,19 +1004,13 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * there's nothing that can be done. */ if (kill) - collect_procs(ppage, &tokill); - - if (hpage != ppage) - lock_page(ppage); + collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED); ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(ppage)); - if (hpage != ppage) - unlock_page(ppage); - /* * Now that the dirty bit has been propagated to the * struct page and all unmaps done we can decide if @@ -983,7 +1031,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, static void set_page_hwpoison_huge_page(struct page *hpage) { int i; - int nr_pages = 1 << compound_trans_order(hpage); + int nr_pages = 1 << compound_order(hpage); for (i = 0; i < nr_pages; i++) SetPageHWPoison(hpage + i); } @@ -991,7 +1039,7 @@ static void set_page_hwpoison_huge_page(struct page *hpage) static void clear_page_hwpoison_huge_page(struct page *hpage) { int i; - int nr_pages = 1 << compound_trans_order(hpage); + int nr_pages = 1 << compound_order(hpage); for (i = 0; i < nr_pages; i++) ClearPageHWPoison(hpage + i); } @@ -1021,6 +1069,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) struct page *hpage; int res; unsigned int nr_pages; + unsigned long page_flags; if (!sysctl_memory_failure_recovery) panic("Memory failure from trap %d on page %lx", trapno, pfn); @@ -1039,8 +1088,18 @@ int memory_failure(unsigned long pfn, int trapno, int flags) return 0; } - nr_pages = 1 << compound_trans_order(hpage); - atomic_long_add(nr_pages, &mce_bad_pages); + /* + * Currently errors on hugetlbfs pages are measured in hugepage units, + * so nr_pages should be 1 << compound_order. OTOH when errors are on + * transparent hugepages, they are supposed to be split and error + * measurement is done in normal page units. So nr_pages should be one + * in this case. + */ + if (PageHuge(p)) + nr_pages = 1 << compound_order(hpage); + else /* normal page or thp */ + nr_pages = 1; + atomic_long_add(nr_pages, &num_poisoned_pages); /* * We need/can do nothing about count=0 pages. @@ -1063,15 +1122,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags) return 0; } else if (PageHuge(hpage)) { /* - * Check "just unpoisoned", "filter hit", and - * "race with other subpage." + * Check "filter hit" and "race with other subpage." */ lock_page(hpage); - if (!PageHWPoison(hpage) - || (hwpoison_filter(p) && TestClearPageHWPoison(p)) - || (p != hpage && TestSetPageHWPoison(hpage))) { - atomic_long_sub(nr_pages, &mce_bad_pages); - return 0; + if (PageHWPoison(hpage)) { + if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) + || (p != hpage && TestSetPageHWPoison(hpage))) { + atomic_long_sub(nr_pages, &num_poisoned_pages); + unlock_page(hpage); + return 0; + } } set_page_hwpoison_huge_page(hpage); res = dequeue_hwpoisoned_huge_page(hpage); @@ -1101,39 +1161,47 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * shake_page could have turned it free. */ if (is_free_buddy_page(p)) { - action_result(pfn, "free buddy, 2nd try", - DELAYED); + if (flags & MF_COUNT_INCREASED) + action_result(pfn, "free buddy", DELAYED); + else + action_result(pfn, "free buddy, 2nd try", DELAYED); return 0; } - action_result(pfn, "non LRU", IGNORED); - put_page(p); - return -EBUSY; } } + lock_page(hpage); + /* - * Lock the page and wait for writeback to finish. - * It's very difficult to mess with pages currently under IO - * and in many cases impossible, so we just avoid it here. + * We use page flags to determine what action should be taken, but + * the flags can be modified by the error containment action. One + * example is an mlocked page, where PG_mlocked is cleared by + * page_remove_rmap() in try_to_unmap_one(). So to determine page status + * correctly, we save a copy of the page flags at this time. */ - lock_page(hpage); + page_flags = p->flags; /* * unpoison always clear PG_hwpoison inside page lock */ if (!PageHWPoison(p)) { printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn); + atomic_long_sub(nr_pages, &num_poisoned_pages); + put_page(hpage); res = 0; goto out; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &mce_bad_pages); + atomic_long_sub(nr_pages, &num_poisoned_pages); unlock_page(hpage); put_page(hpage); return 0; } + if (!PageHuge(p) && !PageTransTail(p) && !PageLRU(p)) + goto identify_page_state; + /* * For error on the tail page, we should set PG_hwpoison * on the head page to show that the hugepage is hwpoisoned @@ -1154,14 +1222,22 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (PageHuge(p)) set_page_hwpoison_huge_page(hpage); + /* + * It's very difficult to mess with pages currently under IO + * and in many cases impossible, so we just avoid it here. + */ wait_on_page_writeback(p); /* * Now take care of user space mappings. * Abort on fail: __delete_from_page_cache() assumes unmapped page. + * + * When the raw error page is thp tail page, hpage points to the raw + * page after thp split. */ - if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) { - printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn); + if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage) + != SWAP_SUCCESS) { + action_result(pfn, "unmapping failed", IGNORED); res = -EBUSY; goto out; } @@ -1175,13 +1251,24 @@ int memory_failure(unsigned long pfn, int trapno, int flags) goto out; } +identify_page_state: res = -EBUSY; - for (ps = error_states;; ps++) { - if ((p->flags & ps->mask) == ps->res) { - res = page_action(ps, p, pfn); + /* + * The first check uses the current page flags which may not have any + * relevant information. The second check with the saved page flagss is + * carried out only if the first check can't determine the page status. + */ + for (ps = error_states;; ps++) + if ((p->flags & ps->mask) == ps->res) break; - } - } + + page_flags |= (p->flags & (1UL << PG_dirty)); + + if (!ps->mask) + for (ps = error_states;; ps++) + if ((page_flags & ps->mask) == ps->res) + break; + res = page_action(ps, p, pfn); out: unlock_page(hpage); return res; @@ -1235,10 +1322,10 @@ void memory_failure_queue(unsigned long pfn, int trapno, int flags) mf_cpu = &get_cpu_var(memory_failure_cpu); spin_lock_irqsave(&mf_cpu->lock, proc_flags); - if (kfifo_put(&mf_cpu->fifo, &entry)) + if (kfifo_put(&mf_cpu->fifo, entry)) schedule_work_on(smp_processor_id(), &mf_cpu->work); else - pr_err("Memory failure: buffer overflow when queuing memory failure at 0x%#lx\n", + pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n", pfn); spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); put_cpu_var(memory_failure_cpu); @@ -1252,14 +1339,17 @@ static void memory_failure_work_func(struct work_struct *work) unsigned long proc_flags; int gotten; - mf_cpu = &__get_cpu_var(memory_failure_cpu); + mf_cpu = this_cpu_ptr(&memory_failure_cpu); for (;;) { spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; - memory_failure(entry.pfn, entry.trapno, entry.flags); + if (entry.flags & MF_SOFT_OFFLINE) + soft_offline_page(pfn_to_page(entry.pfn), entry.flags); + else + memory_failure(entry.pfn, entry.trapno, entry.flags); } } @@ -1309,7 +1399,17 @@ int unpoison_memory(unsigned long pfn) return 0; } - nr_pages = 1 << compound_trans_order(page); + /* + * unpoison_memory() can encounter thp only when the thp is being + * worked by memory_failure() and the page lock is not held yet. + * In such case, we yield to memory_failure() and make unpoison fail. + */ + if (!PageHuge(page) && PageTransHuge(page)) { + pr_info("MCE: Memory failure is now running on %#lx\n", pfn); + return 0; + } + + nr_pages = 1 << compound_order(page); if (!get_page_unless_zero(page)) { /* @@ -1323,7 +1423,7 @@ int unpoison_memory(unsigned long pfn) return 0; } if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &mce_bad_pages); + atomic_long_dec(&num_poisoned_pages); pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn); return 0; } @@ -1337,7 +1437,7 @@ int unpoison_memory(unsigned long pfn) */ if (TestClearPageHWPoison(page)) { pr_info("MCE: Software-unpoisoned page %#lx\n", pfn); - atomic_long_sub(nr_pages, &mce_bad_pages); + atomic_long_sub(nr_pages, &num_poisoned_pages); freeit = 1; if (PageHuge(page)) clear_page_hwpoison_huge_page(page); @@ -1345,7 +1445,7 @@ int unpoison_memory(unsigned long pfn) unlock_page(page); put_page(page); - if (freeit) + if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) put_page(page); return 0; @@ -1368,7 +1468,7 @@ static struct page *new_page(struct page *p, unsigned long private, int **x) * that is not free, and 1 for any other page type. * For 1 the page is returned with increased page count, otherwise not. */ -static int get_any_page(struct page *p, unsigned long pfn, int flags) +static int __get_any_page(struct page *p, unsigned long pfn, int flags) { int ret; @@ -1376,28 +1476,15 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) return 1; /* - * The lock_memory_hotplug prevents a race with memory hotplug. - * This is a big hammer, a better would be nicer. - */ - lock_memory_hotplug(); - - /* - * Isolate the page, so that it doesn't get reallocated if it - * was free. - */ - set_migratetype_isolate(p, true); - /* * When the target page is a free hugepage, just remove it * from free hugepage list. */ if (!get_page_unless_zero(compound_head(p))) { if (PageHuge(p)) { pr_info("%s: %#lx free huge page\n", __func__, pfn); - ret = dequeue_hwpoisoned_huge_page(compound_head(p)); + ret = 0; } else if (is_free_buddy_page(p)) { pr_info("%s: %#lx free buddy page\n", __func__, pfn); - /* Set hwpoison bit while page is still isolated */ - SetPageHWPoison(p); ret = 0; } else { pr_info("%s: %#lx: unknown zero refcount page type %lx\n", @@ -1408,8 +1495,30 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) /* Not a free page */ ret = 1; } - unset_migratetype_isolate(p, MIGRATE_MOVABLE); - unlock_memory_hotplug(); + return ret; +} + +static int get_any_page(struct page *page, unsigned long pfn, int flags) +{ + int ret = __get_any_page(page, pfn, flags); + + if (ret == 1 && !PageHuge(page) && !PageLRU(page)) { + /* + * Try to free it. + */ + put_page(page); + shake_page(page, 1); + + /* + * Did it turn free? + */ + ret = __get_any_page(page, pfn, 0); + if (!PageLRU(page)) { + pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", + pfn, page->flags); + return -EIO; + } + } return ret; } @@ -1418,120 +1527,70 @@ static int soft_offline_huge_page(struct page *page, int flags) int ret; unsigned long pfn = page_to_pfn(page); struct page *hpage = compound_head(page); + LIST_HEAD(pagelist); - ret = get_any_page(page, pfn, flags); - if (ret < 0) - return ret; - if (ret == 0) - goto done; - + /* + * This double-check of PageHWPoison is to avoid the race with + * memory_failure(). See also comment in __soft_offline_page(). + */ + lock_page(hpage); if (PageHWPoison(hpage)) { + unlock_page(hpage); put_page(hpage); pr_info("soft offline: %#lx hugepage already poisoned\n", pfn); return -EBUSY; } + unlock_page(hpage); /* Keep page count to indicate a given hugepage is isolated. */ - ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, false, - MIGRATE_SYNC); - put_page(hpage); + list_move(&hpage->lru, &pagelist); + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, + MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); - return ret; + /* + * We know that soft_offline_huge_page() tries to migrate + * only one hugepage pointed to by hpage, so we need not + * run through the pagelist here. + */ + putback_active_hugepage(hpage); + if (ret > 0) + ret = -EIO; + } else { + /* overcommit hugetlb page will be freed to buddy */ + if (PageHuge(page)) { + set_page_hwpoison_huge_page(hpage); + dequeue_hwpoisoned_huge_page(hpage); + atomic_long_add(1 << compound_order(hpage), + &num_poisoned_pages); + } else { + SetPageHWPoison(page); + atomic_long_inc(&num_poisoned_pages); + } } -done: - if (!PageHWPoison(hpage)) - atomic_long_add(1 << compound_trans_order(hpage), - &mce_bad_pages); - set_page_hwpoison_huge_page(hpage); - dequeue_hwpoisoned_huge_page(hpage); - /* keep elevated page count for bad page */ return ret; } -/** - * soft_offline_page - Soft offline a page. - * @page: page to offline - * @flags: flags. Same as memory_failure(). - * - * Returns 0 on success, otherwise negated errno. - * - * Soft offline a page, by migration or invalidation, - * without killing anything. This is for the case when - * a page is not corrupted yet (so it's still valid to access), - * but has had a number of corrected errors and is better taken - * out. - * - * The actual policy on when to do that is maintained by - * user space. - * - * This should never impact any application or cause data loss, - * however it might take some time. - * - * This is not a 100% solution for all memory, but tries to be - * ``good enough'' for the majority of memory. - */ -int soft_offline_page(struct page *page, int flags) +static int __soft_offline_page(struct page *page, int flags) { int ret; unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_trans_head(page); - - if (PageHuge(page)) - return soft_offline_huge_page(page, flags); - if (PageTransHuge(hpage)) { - if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) { - pr_info("soft offline: %#lx: failed to split THP\n", - pfn); - return -EBUSY; - } - } - - ret = get_any_page(page, pfn, flags); - if (ret < 0) - return ret; - if (ret == 0) - goto done; /* - * Page cache page we can handle? + * Check PageHWPoison again inside page lock because PageHWPoison + * is set by memory_failure() outside page lock. Note that + * memory_failure() also double-checks PageHWPoison inside page lock, + * so there's no race between soft_offline_page() and memory_failure(). */ - if (!PageLRU(page)) { - /* - * Try to free it. - */ - put_page(page); - shake_page(page, 1); - - /* - * Did it turn free? - */ - ret = get_any_page(page, pfn, 0); - if (ret < 0) - return ret; - if (ret == 0) - goto done; - } - if (!PageLRU(page)) { - pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", - pfn, page->flags); - return -EIO; - } - lock_page(page); wait_on_page_writeback(page); - - /* - * Synchronized using the page lock with memory_failure() - */ if (PageHWPoison(page)) { unlock_page(page); put_page(page); pr_info("soft offline: %#lx page already poisoned\n", pfn); return -EBUSY; } - /* * Try to invalidate first. This should work for * non dirty unmapped page cache pages. @@ -1544,9 +1603,10 @@ int soft_offline_page(struct page *page, int flags) */ if (ret == 1) { put_page(page); - ret = 0; pr_info("soft_offline: %#lx: invalidated\n", pfn); - goto done; + SetPageHWPoison(page); + atomic_long_inc(&num_poisoned_pages); + return 0; } /* @@ -1563,28 +1623,116 @@ int soft_offline_page(struct page *page, int flags) if (!ret) { LIST_HEAD(pagelist); inc_zone_page_state(page, NR_ISOLATED_ANON + - page_is_file_cache(page)); + page_is_file_cache(page)); list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, - false, MIGRATE_SYNC, - MR_MEMORY_FAILURE); + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, + MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { - putback_lru_pages(&pagelist); + if (!list_empty(&pagelist)) { + list_del(&page->lru); + dec_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + putback_lru_page(page); + } + pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) ret = -EIO; + } else { + /* + * After page migration succeeds, the source page can + * be trapped in pagevec and actual freeing is delayed. + * Freeing code works differently based on PG_hwpoison, + * so there's a race. We need to make sure that the + * source page should be freed back to buddy before + * setting PG_hwpoison. + */ + if (!is_free_buddy_page(page)) + lru_add_drain_all(); + if (!is_free_buddy_page(page)) + drain_all_pages(); + SetPageHWPoison(page); + if (!is_free_buddy_page(page)) + pr_info("soft offline: %#lx: page leaked\n", + pfn); + atomic_long_inc(&num_poisoned_pages); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", pfn, ret, page_count(page), page->flags); } - if (ret) - return ret; + return ret; +} -done: - atomic_long_add(1, &mce_bad_pages); - SetPageHWPoison(page); - /* keep elevated page count for bad page */ +/** + * soft_offline_page - Soft offline a page. + * @page: page to offline + * @flags: flags. Same as memory_failure(). + * + * Returns 0 on success, otherwise negated errno. + * + * Soft offline a page, by migration or invalidation, + * without killing anything. This is for the case when + * a page is not corrupted yet (so it's still valid to access), + * but has had a number of corrected errors and is better taken + * out. + * + * The actual policy on when to do that is maintained by + * user space. + * + * This should never impact any application or cause data loss, + * however it might take some time. + * + * This is not a 100% solution for all memory, but tries to be + * ``good enough'' for the majority of memory. + */ +int soft_offline_page(struct page *page, int flags) +{ + int ret; + unsigned long pfn = page_to_pfn(page); + struct page *hpage = compound_head(page); + + if (PageHWPoison(page)) { + pr_info("soft offline: %#lx page already poisoned\n", pfn); + return -EBUSY; + } + if (!PageHuge(page) && PageTransHuge(hpage)) { + if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) { + pr_info("soft offline: %#lx: failed to split THP\n", + pfn); + return -EBUSY; + } + } + + get_online_mems(); + + /* + * Isolate the page, so that it doesn't get reallocated if it + * was free. This flag should be kept set until the source page + * is freed and PG_hwpoison on it is set. + */ + if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) + set_migratetype_isolate(page, true); + + ret = get_any_page(page, pfn, flags); + put_online_mems(); + if (ret > 0) { /* for in-use pages */ + if (PageHuge(page)) + ret = soft_offline_huge_page(page, flags); + else + ret = __soft_offline_page(page, flags); + } else if (ret == 0) { /* for free pages */ + if (PageHuge(page)) { + set_page_hwpoison_huge_page(hpage); + dequeue_hwpoisoned_huge_page(hpage); + atomic_long_add(1 << compound_order(hpage), + &num_poisoned_pages); + } else { + SetPageHWPoison(page); + atomic_long_inc(&num_poisoned_pages); + } + } + unset_migratetype_isolate(page, MIGRATE_MOVABLE); return ret; } diff --git a/mm/memory.c b/mm/memory.c index bb1369f7b9b..8b44f765b64 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -59,6 +59,8 @@ #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> +#include <linux/dma-debug.h> +#include <linux/debugfs.h> #include <asm/io.h> #include <asm/pgalloc.h> @@ -69,6 +71,10 @@ #include "internal.h" +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS +#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. +#endif + #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; @@ -78,7 +84,6 @@ EXPORT_SYMBOL(max_mapnr); EXPORT_SYMBOL(mem_map); #endif -unsigned long num_physpages; /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end @@ -88,7 +93,6 @@ unsigned long num_physpages; */ void * high_memory; -EXPORT_SYMBOL(num_physpages); EXPORT_SYMBOL(high_memory); /* @@ -207,15 +211,16 @@ static int tlb_next_batch(struct mmu_gather *tlb) * tear-down from @mm. The @fullmm argument is used when @mm is without * users and we're going to destroy the full address space (exit/execve). */ -void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) +void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) { tlb->mm = mm; - tlb->fullmm = fullmm; - tlb->start = -1UL; - tlb->end = 0; + /* Is it from 0 to ~0? */ + tlb->fullmm = !(start | (end+1)); + tlb->need_flush_all = 0; + tlb->start = start; + tlb->end = end; tlb->need_flush = 0; - tlb->fast_mode = (num_possible_cpus() == 1); tlb->local.next = NULL; tlb->local.nr = 0; tlb->local.max = ARRAY_SIZE(tlb->__pages); @@ -227,20 +232,18 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) #endif } -void tlb_flush_mmu(struct mmu_gather *tlb) +static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { - struct mmu_gather_batch *batch; - - if (!tlb->need_flush) - return; tlb->need_flush = 0; tlb_flush(tlb); #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb_table_flush(tlb); #endif +} - if (tlb_fast_mode(tlb)) - return; +static void tlb_flush_mmu_free(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch; for (batch = &tlb->local; batch; batch = batch->next) { free_pages_and_swap_cache(batch->pages, batch->nr); @@ -249,6 +252,14 @@ void tlb_flush_mmu(struct mmu_gather *tlb) tlb->active = &tlb->local; } +void tlb_flush_mmu(struct mmu_gather *tlb) +{ + if (!tlb->need_flush) + return; + tlb_flush_mmu_tlbonly(tlb); + tlb_flush_mmu_free(tlb); +} + /* tlb_finish_mmu * Called at the end of the shootdown operation to free up any resources * that were required. @@ -257,8 +268,6 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e { struct mmu_gather_batch *batch, *next; - tlb->start = start; - tlb->end = end; tlb_flush_mmu(tlb); /* keep the page table cache within bounds */ @@ -283,11 +292,6 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) VM_BUG_ON(!tlb->need_flush); - if (tlb_fast_mode(tlb)) { - free_page_and_swap_cache(page); - return 1; /* avoid calling tlb_flush_mmu() */ - } - batch = tlb->active; batch->pages[batch->nr++] = page; if (batch->nr == batch->max) { @@ -295,7 +299,7 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) return 0; batch = tlb->active; } - VM_BUG_ON(batch->nr > batch->max); + VM_BUG_ON_PAGE(batch->nr > batch->max, page); return batch->max - batch->nr; } @@ -380,30 +384,6 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) #endif /* CONFIG_HAVE_RCU_TABLE_FREE */ /* - * If a p?d_bad entry is found while walking page tables, report - * the error, before resetting entry to p?d_none. Usually (but - * very seldom) called out from the p?d_none_or_clear_bad macros. - */ - -void pgd_clear_bad(pgd_t *pgd) -{ - pgd_ERROR(*pgd); - pgd_clear(pgd); -} - -void pud_clear_bad(pud_t *pud) -{ - pud_ERROR(*pud); - pud_clear(pud); -} - -void pmd_clear_bad(pmd_t *pmd) -{ - pmd_ERROR(*pmd); - pmd_clear(pmd); -} - -/* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ @@ -413,7 +393,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); - tlb->mm->nr_ptes--; + atomic_long_dec(&tlb->mm->nr_ptes); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, @@ -484,8 +464,6 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, /* * This function frees user-level page tables of a process. - * - * Must be called with pagetable lock held. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, @@ -583,6 +561,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pmd_t *pmd, unsigned long address) { + spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm, address); int wait_split_huge_page; if (!new) @@ -603,15 +582,15 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); wait_split_huge_page = 0; if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ - mm->nr_ptes++; + atomic_long_inc(&mm->nr_ptes); pmd_populate(mm, pmd, new); new = NULL; } else if (unlikely(pmd_trans_splitting(*pmd))) wait_split_huge_page = 1; - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); if (new) pte_free(mm, new); if (wait_split_huge_page) @@ -702,7 +681,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) - dump_page(page); + dump_page(page, "bad pte"); printk(KERN_ALERT "addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); @@ -710,18 +689,13 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y */ if (vma->vm_ops) - print_symbol(KERN_ALERT "vma->vm_ops->fault: %s\n", - (unsigned long)vma->vm_ops->fault); - if (vma->vm_file && vma->vm_file->f_op) - print_symbol(KERN_ALERT "vma->vm_file->f_op->mmap: %s\n", - (unsigned long)vma->vm_file->f_op->mmap); + printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n", + vma->vm_ops->fault); + if (vma->vm_file) + printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n", + vma->vm_file->f_op->mmap); dump_stack(); - add_taint(TAINT_BAD_PAGE); -} - -static inline bool is_cow_mapping(vm_flags_t flags) -{ - return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* @@ -777,7 +751,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn = pte_pfn(pte); if (HAVE_PTE_SPECIAL) { - if (likely(!pte_special(pte))) + if (likely(!pte_special(pte) || pte_numa(pte))) goto check_pfn; if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; @@ -803,14 +777,15 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, } } - if (is_zero_pfn(pfn)) - return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } + if (is_zero_pfn(pfn)) + return NULL; + /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. @@ -868,6 +843,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); set_pte_at(src_mm, addr, src_pte, pte); } } @@ -1146,25 +1123,31 @@ again: continue; if (unlikely(details) && details->nonlinear_vma && linear_page_index(details->nonlinear_vma, - addr) != page->index) - set_pte_at(mm, addr, pte, - pgoff_to_pte(page->index)); + addr) != page->index) { + pte_t ptfile = pgoff_to_pte(page->index); + if (pte_soft_dirty(ptent)) + pte_file_mksoft_dirty(ptfile); + set_pte_at(mm, addr, pte, ptfile); + } if (PageAnon(page)) rss[MM_ANONPAGES]--; else { - if (pte_dirty(ptent)) + if (pte_dirty(ptent)) { + force_flush = 1; set_page_dirty(page); + } if (pte_young(ptent) && - likely(!VM_SequentialReadHint(vma))) + likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); rss[MM_FILEPAGES]--; } page_remove_rmap(page); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); - force_flush = !__tlb_remove_page(tlb, page); - if (force_flush) + if (unlikely(!__tlb_remove_page(tlb, page))) { + force_flush = 1; break; + } continue; } /* @@ -1199,21 +1182,34 @@ again: add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); + + /* Do the actual TLB flush before dropping ptl */ + if (force_flush) { + unsigned long old_end; + + /* + * Flush the TLB just for the previous segment, + * then update the range to be the remaining + * TLB range. + */ + old_end = tlb->end; + tlb->end = addr; + tlb_flush_mmu_tlbonly(tlb); + tlb->start = addr; + tlb->end = old_end; + } pte_unmap_unlock(start_pte, ptl); /* - * mmu_gather ran out of room to batch pages, we break out of - * the PTE lock to avoid doing the potential expensive TLB invalidate - * and page-free while holding it. + * If we forced a TLB flush (either due to running out of + * batch buffers or because we needed to flush dirty TLB + * entries before releasing the ptl), free the batched + * memory too. Restart if we didn't do everything. */ if (force_flush) { force_flush = 0; + tlb_flush_mmu_free(tlb); -#ifdef HAVE_GENERIC_MMU_GATHER - tlb->start = addr; - tlb->end = end; -#endif - tlb_flush_mmu(tlb); if (addr != end) goto again; } @@ -1336,9 +1332,9 @@ static void unmap_single_vma(struct mmu_gather *tlb, * 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 + * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, - * do_mmap_pgoff() nullifies vma->vm_file + * mmap_region() 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. @@ -1400,7 +1396,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end = start + size; lru_add_drain(); - tlb_gather_mmu(&tlb, mm, 0); + tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(mm, start, end); for ( ; vma && vma->vm_start < end; vma = vma->vm_next) @@ -1426,7 +1422,7 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr unsigned long end = address + size; lru_add_drain(); - tlb_gather_mmu(&tlb, mm, 0); + tlb_gather_mmu(&tlb, mm, address, end); update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(mm, address, end); unmap_single_vma(&tlb, vma, address, end, details); @@ -1457,573 +1453,6 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(zap_vma_ptes); -/** - * follow_page - look up a page descriptor from a user-virtual address - * @vma: vm_area_struct mapping @address - * @address: virtual address to look up - * @flags: flags modifying lookup behaviour - * - * @flags can have FOLL_ flags set, defined in <linux/mm.h> - * - * Returns the mapped (struct page *), %NULL if no mapping exists, or - * an error pointer if there is a mapping to something not represented - * by a page descriptor (see also vm_normal_page()). - */ -struct page *follow_page(struct vm_area_struct *vma, unsigned long address, - unsigned int flags) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep, pte; - spinlock_t *ptl; - struct page *page; - struct mm_struct *mm = vma->vm_mm; - - page = follow_huge_addr(mm, address, flags & FOLL_WRITE); - if (!IS_ERR(page)) { - BUG_ON(flags & FOLL_GET); - goto out; - } - - page = NULL; - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto no_page_table; - - pud = pud_offset(pgd, address); - if (pud_none(*pud)) - goto no_page_table; - if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { - BUG_ON(flags & FOLL_GET); - page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); - goto out; - } - if (unlikely(pud_bad(*pud))) - goto no_page_table; - - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd)) - goto no_page_table; - if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { - BUG_ON(flags & FOLL_GET); - page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); - goto out; - } - if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) - goto no_page_table; - if (pmd_trans_huge(*pmd)) { - if (flags & FOLL_SPLIT) { - split_huge_page_pmd(vma, address, pmd); - goto split_fallthrough; - } - spin_lock(&mm->page_table_lock); - if (likely(pmd_trans_huge(*pmd))) { - if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&mm->page_table_lock); - wait_split_huge_page(vma->anon_vma, pmd); - } else { - page = follow_trans_huge_pmd(vma, address, - pmd, flags); - spin_unlock(&mm->page_table_lock); - goto out; - } - } else - spin_unlock(&mm->page_table_lock); - /* fall through */ - } -split_fallthrough: - if (unlikely(pmd_bad(*pmd))) - goto no_page_table; - - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); - - pte = *ptep; - if (!pte_present(pte)) - goto no_page; - if ((flags & FOLL_NUMA) && pte_numa(pte)) - goto no_page; - if ((flags & FOLL_WRITE) && !pte_write(pte)) - goto unlock; - - page = vm_normal_page(vma, address, pte); - if (unlikely(!page)) { - if ((flags & FOLL_DUMP) || - !is_zero_pfn(pte_pfn(pte))) - goto bad_page; - page = pte_page(pte); - } - - if (flags & FOLL_GET) - get_page_foll(page); - if (flags & FOLL_TOUCH) { - if ((flags & FOLL_WRITE) && - !pte_dirty(pte) && !PageDirty(page)) - set_page_dirty(page); - /* - * pte_mkyoung() would be more correct here, but atomic care - * is needed to avoid losing the dirty bit: it is easier to use - * mark_page_accessed(). - */ - mark_page_accessed(page); - } - if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { - /* - * The preliminary mapping check is mainly to avoid the - * pointless overhead of lock_page on the ZERO_PAGE - * which might bounce very badly if there is contention. - * - * If the page is already locked, we don't need to - * handle it now - vmscan will handle it later if and - * when it attempts to reclaim the page. - */ - if (page->mapping && trylock_page(page)) { - lru_add_drain(); /* push cached pages to LRU */ - /* - * Because we lock page here, and migration is - * blocked by the pte's page reference, and we - * know the page is still mapped, we don't even - * need to check for file-cache page truncation. - */ - mlock_vma_page(page); - unlock_page(page); - } - } -unlock: - pte_unmap_unlock(ptep, ptl); -out: - return page; - -bad_page: - pte_unmap_unlock(ptep, ptl); - return ERR_PTR(-EFAULT); - -no_page: - pte_unmap_unlock(ptep, ptl); - if (!pte_none(pte)) - return page; - -no_page_table: - /* - * When core dumping an enormous anonymous area that nobody - * has touched so far, we don't want to allocate unnecessary pages or - * page tables. Return error instead of NULL to skip handle_mm_fault, - * then get_dump_page() will return NULL to leave a hole in the dump. - * But we can only make this optimization where a hole would surely - * be zero-filled if handle_mm_fault() actually did handle it. - */ - if ((flags & FOLL_DUMP) && - (!vma->vm_ops || !vma->vm_ops->fault)) - return ERR_PTR(-EFAULT); - return page; -} - -static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) -{ - return stack_guard_page_start(vma, addr) || - stack_guard_page_end(vma, addr+PAGE_SIZE); -} - -/** - * __get_user_pages() - pin user pages in memory - * @tsk: task_struct of target task - * @mm: mm_struct of target mm - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. - * @nonblocking: whether waiting for disk IO or mmap_sem contention - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. Each page returned must be released - * with a put_page() call when it is finished with. vmas will only - * remain valid while mmap_sem is held. - * - * Must be called with mmap_sem held for read or write. - * - * __get_user_pages walks a process's page tables and takes a reference to - * each struct page that each user address corresponds to at a given - * instant. That is, it takes the page that would be accessed if a user - * thread accesses the given user virtual address at that instant. - * - * This does not guarantee that the page exists in the user mappings when - * __get_user_pages returns, and there may even be a completely different - * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page - * won't be freed completely. And mostly callers simply care that the page - * contains data that was valid *at some point in time*. Typically, an IO - * or similar operation cannot guarantee anything stronger anyway because - * locks can't be held over the syscall boundary. - * - * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If - * the page is written to, set_page_dirty (or set_page_dirty_lock, as - * appropriate) must be called after the page is finished with, and - * before put_page is called. - * - * If @nonblocking != NULL, __get_user_pages will not wait for disk IO - * or mmap_sem contention, and if waiting is needed to pin all pages, - * *@nonblocking will be set to 0. - * - * In most cases, get_user_pages or get_user_pages_fast should be used - * instead of __get_user_pages. __get_user_pages should be used only if - * you need some special @gup_flags. - */ -int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int nr_pages, unsigned int gup_flags, - struct page **pages, struct vm_area_struct **vmas, - int *nonblocking) -{ - int i; - unsigned long vm_flags; - - if (nr_pages <= 0) - return 0; - - VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); - - /* - * Require read or write permissions. - * If FOLL_FORCE is set, we only require the "MAY" flags. - */ - vm_flags = (gup_flags & FOLL_WRITE) ? - (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); - vm_flags &= (gup_flags & FOLL_FORCE) ? - (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); - - /* - * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault - * would be called on PROT_NONE ranges. We must never invoke - * handle_mm_fault on PROT_NONE ranges or the NUMA hinting - * page faults would unprotect the PROT_NONE ranges if - * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd - * bitflag. So to avoid that, don't set FOLL_NUMA if - * FOLL_FORCE is set. - */ - if (!(gup_flags & FOLL_FORCE)) - gup_flags |= FOLL_NUMA; - - i = 0; - - do { - struct vm_area_struct *vma; - - vma = find_extend_vma(mm, start); - if (!vma && in_gate_area(mm, start)) { - unsigned long pg = start & PAGE_MASK; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - /* user gate pages are read-only */ - if (gup_flags & FOLL_WRITE) - return i ? : -EFAULT; - if (pg > TASK_SIZE) - pgd = pgd_offset_k(pg); - else - pgd = pgd_offset_gate(mm, pg); - BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, pg); - BUG_ON(pud_none(*pud)); - pmd = pmd_offset(pud, pg); - if (pmd_none(*pmd)) - return i ? : -EFAULT; - VM_BUG_ON(pmd_trans_huge(*pmd)); - pte = pte_offset_map(pmd, pg); - if (pte_none(*pte)) { - pte_unmap(pte); - return i ? : -EFAULT; - } - vma = get_gate_vma(mm); - if (pages) { - struct page *page; - - page = vm_normal_page(vma, start, *pte); - if (!page) { - if (!(gup_flags & FOLL_DUMP) && - is_zero_pfn(pte_pfn(*pte))) - page = pte_page(*pte); - else { - pte_unmap(pte); - return i ? : -EFAULT; - } - } - pages[i] = page; - get_page(page); - } - pte_unmap(pte); - goto next_page; - } - - if (!vma || - (vma->vm_flags & (VM_IO | VM_PFNMAP)) || - !(vm_flags & vma->vm_flags)) - return i ? : -EFAULT; - - if (is_vm_hugetlb_page(vma)) { - i = follow_hugetlb_page(mm, vma, pages, vmas, - &start, &nr_pages, i, gup_flags); - continue; - } - - do { - struct page *page; - unsigned int foll_flags = gup_flags; - - /* - * If we have a pending SIGKILL, don't keep faulting - * pages and potentially allocating memory. - */ - if (unlikely(fatal_signal_pending(current))) - return i ? i : -ERESTARTSYS; - - cond_resched(); - while (!(page = follow_page(vma, start, foll_flags))) { - int ret; - unsigned int fault_flags = 0; - - /* For mlock, just skip the stack guard page. */ - if (foll_flags & FOLL_MLOCK) { - if (stack_guard_page(vma, start)) - goto next_page; - } - if (foll_flags & FOLL_WRITE) - fault_flags |= FAULT_FLAG_WRITE; - if (nonblocking) - fault_flags |= FAULT_FLAG_ALLOW_RETRY; - if (foll_flags & FOLL_NOWAIT) - fault_flags |= (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT); - - ret = handle_mm_fault(mm, vma, start, - fault_flags); - - if (ret & VM_FAULT_ERROR) { - if (ret & VM_FAULT_OOM) - return i ? i : -ENOMEM; - if (ret & (VM_FAULT_HWPOISON | - VM_FAULT_HWPOISON_LARGE)) { - if (i) - return i; - else if (gup_flags & FOLL_HWPOISON) - return -EHWPOISON; - else - return -EFAULT; - } - if (ret & VM_FAULT_SIGBUS) - return i ? i : -EFAULT; - BUG(); - } - - if (tsk) { - if (ret & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - } - - if (ret & VM_FAULT_RETRY) { - if (nonblocking) - *nonblocking = 0; - return i; - } - - /* - * The VM_FAULT_WRITE bit tells us that - * do_wp_page has broken COW when necessary, - * even if maybe_mkwrite decided not to set - * pte_write. We can thus safely do subsequent - * page lookups as if they were reads. But only - * do so when looping for pte_write is futile: - * in some cases userspace may also be wanting - * to write to the gotten user page, which a - * read fault here might prevent (a readonly - * page might get reCOWed by userspace write). - */ - if ((ret & VM_FAULT_WRITE) && - !(vma->vm_flags & VM_WRITE)) - foll_flags &= ~FOLL_WRITE; - - cond_resched(); - } - if (IS_ERR(page)) - return i ? i : PTR_ERR(page); - if (pages) { - pages[i] = page; - - flush_anon_page(vma, page, start); - flush_dcache_page(page); - } -next_page: - if (vmas) - vmas[i] = vma; - i++; - start += PAGE_SIZE; - nr_pages--; - } while (nr_pages && start < vma->vm_end); - } while (nr_pages); - return i; -} -EXPORT_SYMBOL(__get_user_pages); - -/* - * fixup_user_fault() - manually resolve a user page fault - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. - * @mm: mm_struct of target mm - * @address: user address - * @fault_flags:flags to pass down to handle_mm_fault() - * - * This is meant to be called in the specific scenario where for locking reasons - * we try to access user memory in atomic context (within a pagefault_disable() - * section), this returns -EFAULT, and we want to resolve the user fault before - * trying again. - * - * Typically this is meant to be used by the futex code. - * - * The main difference with get_user_pages() is that this function will - * unconditionally call handle_mm_fault() which will in turn perform all the - * necessary SW fixup of the dirty and young bits in the PTE, while - * handle_mm_fault() only guarantees to update these in the struct page. - * - * This is important for some architectures where those bits also gate the - * access permission to the page because they are maintained in software. On - * such architectures, gup() will not be enough to make a subsequent access - * succeed. - * - * This should be called with the mm_sem held for read. - */ -int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, - unsigned long address, unsigned int fault_flags) -{ - struct vm_area_struct *vma; - int ret; - - vma = find_extend_vma(mm, address); - if (!vma || address < vma->vm_start) - return -EFAULT; - - ret = handle_mm_fault(mm, vma, address, fault_flags); - if (ret & VM_FAULT_ERROR) { - if (ret & VM_FAULT_OOM) - return -ENOMEM; - if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) - return -EHWPOISON; - if (ret & VM_FAULT_SIGBUS) - return -EFAULT; - BUG(); - } - if (tsk) { - if (ret & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - } - return 0; -} - -/* - * get_user_pages() - pin user pages in memory - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. - * @mm: mm_struct of target mm - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @write: whether pages will be written to by the caller - * @force: whether to force write access even if user mapping is - * readonly. This will result in the page being COWed even - * in MAP_SHARED mappings. You do not want this. - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. Each page returned must be released - * with a put_page() call when it is finished with. vmas will only - * remain valid while mmap_sem is held. - * - * Must be called with mmap_sem held for read or write. - * - * get_user_pages walks a process's page tables and takes a reference to - * each struct page that each user address corresponds to at a given - * instant. That is, it takes the page that would be accessed if a user - * thread accesses the given user virtual address at that instant. - * - * This does not guarantee that the page exists in the user mappings when - * get_user_pages returns, and there may even be a completely different - * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page - * won't be freed completely. And mostly callers simply care that the page - * contains data that was valid *at some point in time*. Typically, an IO - * or similar operation cannot guarantee anything stronger anyway because - * locks can't be held over the syscall boundary. - * - * If write=0, the page must not be written to. If the page is written to, - * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called - * after the page is finished with, and before put_page is called. - * - * get_user_pages is typically used for fewer-copy IO operations, to get a - * handle on the memory by some means other than accesses via the user virtual - * addresses. The pages may be submitted for DMA to devices or accessed via - * their kernel linear mapping (via the kmap APIs). Care should be taken to - * use the correct cache flushing APIs. - * - * See also get_user_pages_fast, for performance critical applications. - */ -int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int nr_pages, int write, int force, - struct page **pages, struct vm_area_struct **vmas) -{ - int flags = FOLL_TOUCH; - - if (pages) - flags |= FOLL_GET; - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE; - - return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, - NULL); -} -EXPORT_SYMBOL(get_user_pages); - -/** - * get_dump_page() - pin user page in memory while writing it to core dump - * @addr: user address - * - * Returns struct page pointer of user page pinned for dump, - * to be freed afterwards by page_cache_release() or put_page(). - * - * Returns NULL on any kind of failure - a hole must then be inserted into - * the corefile, to preserve alignment with its headers; and also returns - * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - - * allowing a hole to be left in the corefile to save diskspace. - * - * Called without mmap_sem, but after all other threads have been killed. - */ -#ifdef CONFIG_ELF_CORE -struct page *get_dump_page(unsigned long addr) -{ - struct vm_area_struct *vma; - struct page *page; - - if (__get_user_pages(current, current->mm, addr, 1, - FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, - NULL) < 1) - return NULL; - flush_cache_page(vma, addr, page_to_pfn(page)); - return page; -} -#endif /* CONFIG_ELF_CORE */ - pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { @@ -2357,6 +1786,53 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(remap_pfn_range); +/** + * vm_iomap_memory - remap memory to userspace + * @vma: user vma to map to + * @start: start of area + * @len: size of area + * + * This is a simplified io_remap_pfn_range() for common driver use. The + * driver just needs to give us the physical memory range to be mapped, + * we'll figure out the rest from the vma information. + * + * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get + * whatever write-combining details or similar. + */ +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) +{ + unsigned long vm_len, pfn, pages; + + /* Check that the physical memory area passed in looks valid */ + if (start + len < start) + return -EINVAL; + /* + * You *really* shouldn't map things that aren't page-aligned, + * but we've historically allowed it because IO memory might + * just have smaller alignment. + */ + len += start & ~PAGE_MASK; + pfn = start >> PAGE_SHIFT; + pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; + if (pfn + pages < pfn) + return -EINVAL; + + /* We start the mapping 'vm_pgoff' pages into the area */ + if (vma->vm_pgoff > pages) + return -EINVAL; + pfn += vma->vm_pgoff; + pages -= vma->vm_pgoff; + + /* Can we fit all of the mapping? */ + vm_len = vma->vm_end - vma->vm_start; + if (vm_len >> PAGE_SHIFT > pages) + return -EINVAL; + + /* Ok, let it rip */ + return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_iomap_memory); + static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data) @@ -2485,6 +1961,8 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) { + debug_dma_assert_idle(src); + /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by @@ -2510,6 +1988,38 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo } /* + * Notify the address space that the page is about to become writable so that + * it can prohibit this or wait for the page to get into an appropriate state. + * + * We do this without the lock held, so that it can sleep if it needs to. + */ +static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page, + unsigned long address) +{ + struct vm_fault vmf; + int ret; + + vmf.virtual_address = (void __user *)(address & PAGE_MASK); + vmf.pgoff = page->index; + vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + vmf.page = page; + + ret = vma->vm_ops->page_mkwrite(vma, &vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) + return ret; + if (unlikely(!(ret & VM_FAULT_LOCKED))) { + lock_page(page); + if (!page->mapping) { + unlock_page(page); + return 0; /* retry */ + } + ret |= VM_FAULT_LOCKED; + } else + VM_BUG_ON_PAGE(!PageLocked(page), page); + return ret; +} + +/* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. @@ -2591,42 +2101,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * get_user_pages(.write=1, .force=1). */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { - struct vm_fault vmf; int tmp; - - vmf.virtual_address = (void __user *)(address & - PAGE_MASK); - vmf.pgoff = old_page->index; - vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; - vmf.page = old_page; - - /* - * Notify the address space that the page is about to - * become writable so that it can prohibit this or wait - * for the page to get into an appropriate state. - * - * We do this without the lock held, so that it can - * sleep if it needs to. - */ page_cache_get(old_page); pte_unmap_unlock(page_table, ptl); - - tmp = vma->vm_ops->page_mkwrite(vma, &vmf); - if (unlikely(tmp & - (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { - ret = tmp; - goto unwritable_page; + tmp = do_page_mkwrite(vma, old_page, address); + if (unlikely(!tmp || (tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + page_cache_release(old_page); + return tmp; } - if (unlikely(!(tmp & VM_FAULT_LOCKED))) { - lock_page(old_page); - if (!old_page->mapping) { - ret = 0; /* retry the fault */ - unlock_page(old_page); - goto unwritable_page; - } - } else - VM_BUG_ON(!PageLocked(old_page)); - /* * Since we dropped the lock we need to revalidate * the PTE as someone else may have changed it. If @@ -2646,6 +2129,14 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, get_page(dirty_page); reuse: + /* + * Clear the pages cpupid information as the existing + * information potentially belongs to a now completely + * unrelated process. + */ + if (old_page) + page_cpupid_xchg_last(old_page, (1 << LAST_CPUPID_SHIFT) - 1); + flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = pte_mkyoung(orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -2663,11 +2154,11 @@ reuse: * bit after it clear all dirty ptes, but before a racing * do_wp_page installs a dirty pte. * - * __do_fault is protected similarly. + * do_shared_fault is protected similarly. */ if (!page_mkwrite) { wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page, page_mkwrite); + set_page_dirty_balance(dirty_page); /* file_update_time outside page_lock */ if (vma->vm_file) file_update_time(vma->vm_file); @@ -2713,7 +2204,7 @@ gotten: } __SetPageUptodate(new_page); - if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) goto oom_free_new; mmun_start = address & PAGE_MASK; @@ -2807,10 +2298,6 @@ oom: if (old_page) page_cache_release(old_page); return VM_FAULT_OOM; - -unwritable_page: - page_cache_release(old_page); - return ret; } static void unmap_mapping_range_vma(struct vm_area_struct *vma, @@ -2830,7 +2317,7 @@ static inline void unmap_mapping_range_tree(struct rb_root *root, details->first_index, details->last_index) { vba = vma->vm_pgoff; - vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1; + vea = vba + vma_pages(vma) - 1; /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */ zba = details->first_index; if (zba < vba) @@ -2919,7 +2406,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned int flags, pte_t orig_pte) { spinlock_t *ptl; - struct page *page, *swapcache = NULL; + struct page *page, *swapcache; swp_entry_t entry; pte_t pte; int locked; @@ -2970,9 +2457,11 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, */ ret = VM_FAULT_HWPOISON; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + swapcache = page; goto out_release; } + swapcache = page; locked = lock_page_or_retry(page, mm, flags); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); @@ -2990,16 +2479,11 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val)) goto out_page; - if (ksm_might_need_to_copy(page, vma, address)) { - swapcache = page; - page = ksm_does_need_to_copy(page, vma, address); - - if (unlikely(!page)) { - ret = VM_FAULT_OOM; - page = swapcache; - swapcache = NULL; - goto out_page; - } + page = ksm_might_need_to_copy(page, vma, address); + if (unlikely(!page)) { + ret = VM_FAULT_OOM; + page = swapcache; + goto out_page; } if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) { @@ -3043,8 +2527,13 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, exclusive = 1; } flush_icache_page(vma, page); + if (pte_swp_soft_dirty(orig_pte)) + pte = pte_mksoft_dirty(pte); set_pte_at(mm, address, page_table, pte); - do_page_add_anon_rmap(page, vma, address, exclusive); + if (page == swapcache) + do_page_add_anon_rmap(page, vma, address, exclusive); + else /* ksm created a completely new copy */ + page_add_new_anon_rmap(page, vma, address); /* It's better to call commit-charge after rmap is established */ mem_cgroup_commit_charge_swapin(page, ptr); @@ -3052,7 +2541,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); - if (swapcache) { + if (page != swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check @@ -3085,7 +2574,7 @@ out_page: unlock_page(page); out_release: page_cache_release(page); - if (swapcache) { + if (page != swapcache) { unlock_page(swapcache); page_cache_release(swapcache); } @@ -3161,9 +2650,14 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, page = alloc_zeroed_user_highpage_movable(vma, address); if (!page) goto oom; + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceeding stores to the page contents become visible before + * the set_pte_at() write. + */ __SetPageUptodate(page); - if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) + if (mem_cgroup_charge_anon(page, mm, GFP_KERNEL)) goto oom_free_page; entry = mk_pte(page, vma->vm_page_prot); @@ -3194,53 +2688,11 @@ oom: return VM_FAULT_OOM; } -/* - * __do_fault() tries to create a new page mapping. It aggressively - * tries to share with existing pages, but makes a separate copy if - * the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid - * the next page fault. - * - * 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 neither mapped nor locked. - * We return with mmap_sem still held, but pte unmapped and unlocked. - */ -static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +static int __do_fault(struct vm_area_struct *vma, unsigned long address, + pgoff_t pgoff, unsigned int flags, struct page **page) { - pte_t *page_table; - spinlock_t *ptl; - struct page *page; - struct page *cow_page; - pte_t entry; - int anon = 0; - struct page *dirty_page = NULL; struct vm_fault vmf; int ret; - int page_mkwrite = 0; - - /* - * If we do COW later, allocate page befor taking lock_page() - * on the file cache page. This will reduce lock holding time. - */ - if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { - - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; - - cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (!cow_page) - return VM_FAULT_OOM; - - if (mem_cgroup_newpage_charge(cow_page, mm, GFP_KERNEL)) { - page_cache_release(cow_page); - return VM_FAULT_OOM; - } - } else - cow_page = NULL; vmf.virtual_address = (void __user *)(address & PAGE_MASK); vmf.pgoff = pgoff; @@ -3248,148 +2700,319 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, vmf.page = NULL; ret = vma->vm_ops->fault(vma, &vmf); - if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | - VM_FAULT_RETRY))) - goto uncharge_out; + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; if (unlikely(PageHWPoison(vmf.page))) { if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); - ret = VM_FAULT_HWPOISON; - goto uncharge_out; + page_cache_release(vmf.page); + return VM_FAULT_HWPOISON; } - /* - * For consistency in subsequent calls, make the faulted page always - * locked. - */ if (unlikely(!(ret & VM_FAULT_LOCKED))) lock_page(vmf.page); else - VM_BUG_ON(!PageLocked(vmf.page)); + VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page); + + *page = vmf.page; + return ret; +} + +/** + * do_set_pte - setup new PTE entry for given page and add reverse page mapping. + * + * @vma: virtual memory area + * @address: user virtual address + * @page: page to map + * @pte: pointer to target page table entry + * @write: true, if new entry is writable + * @anon: true, if it's anonymous page + * + * Caller must hold page table lock relevant for @pte. + * + * Target users are page handler itself and implementations of + * vm_ops->map_pages. + */ +void do_set_pte(struct vm_area_struct *vma, unsigned long address, + struct page *page, pte_t *pte, bool write, bool anon) +{ + pte_t entry; + + flush_icache_page(vma, page); + entry = mk_pte(page, vma->vm_page_prot); + if (write) + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + else if (pte_file(*pte) && pte_file_soft_dirty(*pte)) + pte_mksoft_dirty(entry); + if (anon) { + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, address); + } else { + inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES); + page_add_file_rmap(page); + } + set_pte_at(vma->vm_mm, address, pte, entry); + + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, address, pte); +} + +static unsigned long fault_around_bytes = rounddown_pow_of_two(65536); + +static inline unsigned long fault_around_pages(void) +{ + return fault_around_bytes >> PAGE_SHIFT; +} + +static inline unsigned long fault_around_mask(void) +{ + return ~(fault_around_bytes - 1) & PAGE_MASK; +} + +#ifdef CONFIG_DEBUG_FS +static int fault_around_bytes_get(void *data, u64 *val) +{ + *val = fault_around_bytes; + return 0; +} + +/* + * fault_around_pages() and fault_around_mask() expects fault_around_bytes + * rounded down to nearest page order. It's what do_fault_around() expects to + * see. + */ +static int fault_around_bytes_set(void *data, u64 val) +{ + if (val / PAGE_SIZE > PTRS_PER_PTE) + return -EINVAL; + if (val > PAGE_SIZE) + fault_around_bytes = rounddown_pow_of_two(val); + else + fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(fault_around_bytes_fops, + fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); + +static int __init fault_around_debugfs(void) +{ + void *ret; + + ret = debugfs_create_file("fault_around_bytes", 0644, NULL, NULL, + &fault_around_bytes_fops); + if (!ret) + pr_warn("Failed to create fault_around_bytes in debugfs"); + return 0; +} +late_initcall(fault_around_debugfs); +#endif + +/* + * do_fault_around() tries to map few pages around the fault address. The hope + * is that the pages will be needed soon and this will lower the number of + * faults to handle. + * + * It uses vm_ops->map_pages() to map the pages, which skips the page if it's + * not ready to be mapped: not up-to-date, locked, etc. + * + * This function is called with the page table lock taken. In the split ptlock + * case the page table lock only protects only those entries which belong to + * the page table corresponding to the fault address. + * + * This function doesn't cross the VMA boundaries, in order to call map_pages() + * only once. + * + * fault_around_pages() defines how many pages we'll try to map. + * do_fault_around() expects it to return a power of two less than or equal to + * PTRS_PER_PTE. + * + * The virtual address of the area that we map is naturally aligned to the + * fault_around_pages() value (and therefore to page order). This way it's + * easier to guarantee that we don't cross page table boundaries. + */ +static void do_fault_around(struct vm_area_struct *vma, unsigned long address, + pte_t *pte, pgoff_t pgoff, unsigned int flags) +{ + unsigned long start_addr; + pgoff_t max_pgoff; + struct vm_fault vmf; + int off; + + start_addr = max(address & fault_around_mask(), vma->vm_start); + off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + pte -= off; + pgoff -= off; /* - * Should we do an early C-O-W break? + * max_pgoff is either end of page table or end of vma + * or fault_around_pages() from pgoff, depending what is nearest. */ - page = vmf.page; - if (flags & FAULT_FLAG_WRITE) { - if (!(vma->vm_flags & VM_SHARED)) { - page = cow_page; - anon = 1; - copy_user_highpage(page, vmf.page, address, vma); - __SetPageUptodate(page); - } else { - /* - * If the page will be shareable, see if the backing - * address space wants to know that the page is about - * to become writable - */ - if (vma->vm_ops->page_mkwrite) { - int tmp; - - unlock_page(page); - vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; - tmp = vma->vm_ops->page_mkwrite(vma, &vmf); - if (unlikely(tmp & - (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { - ret = tmp; - goto unwritable_page; - } - if (unlikely(!(tmp & VM_FAULT_LOCKED))) { - lock_page(page); - if (!page->mapping) { - ret = 0; /* retry the fault */ - unlock_page(page); - goto unwritable_page; - } - } else - VM_BUG_ON(!PageLocked(page)); - page_mkwrite = 1; - } - } - + max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + + PTRS_PER_PTE - 1; + max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1, + pgoff + fault_around_pages() - 1); + + /* Check if it makes any sense to call ->map_pages */ + while (!pte_none(*pte)) { + if (++pgoff > max_pgoff) + return; + start_addr += PAGE_SIZE; + if (start_addr >= vma->vm_end) + return; + pte++; } - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + vmf.virtual_address = (void __user *) start_addr; + vmf.pte = pte; + vmf.pgoff = pgoff; + vmf.max_pgoff = max_pgoff; + vmf.flags = flags; + vma->vm_ops->map_pages(vma, &vmf); +} + +static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page; + spinlock_t *ptl; + pte_t *pte; + int ret = 0; /* - * This silly early PAGE_DIRTY setting removes a race - * due to the bad i386 page protection. But it's valid - * for other architectures too. - * - * Note that if FAULT_FLAG_WRITE is set, we either now have - * an exclusive copy of the page, or this is a shared mapping, - * so we can make it writable and dirty to avoid having to - * handle that later. + * Let's call ->map_pages() first and use ->fault() as fallback + * if page by the offset is not ready to be mapped (cold cache or + * something). */ - /* Only go through if we didn't race with anybody else... */ - if (likely(pte_same(*page_table, orig_pte))) { - flush_icache_page(vma, page); - entry = mk_pte(page, vma->vm_page_prot); - if (flags & FAULT_FLAG_WRITE) - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (anon) { - inc_mm_counter_fast(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, address); - } else { - inc_mm_counter_fast(mm, MM_FILEPAGES); - page_add_file_rmap(page); - if (flags & FAULT_FLAG_WRITE) { - dirty_page = page; - get_page(dirty_page); - } - } - set_pte_at(mm, address, page_table, entry); + if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) && + fault_around_pages() > 1) { + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + do_fault_around(vma, address, pte, pgoff, flags); + if (!pte_same(*pte, orig_pte)) + goto unlock_out; + pte_unmap_unlock(pte, ptl); + } - /* no need to invalidate: a not-present page won't be cached */ - update_mmu_cache(vma, address, page_table); - } else { - if (cow_page) - mem_cgroup_uncharge_page(cow_page); - if (anon) - page_cache_release(page); - else - anon = 1; /* no anon but release faulted_page */ + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + return ret; } + do_set_pte(vma, address, fault_page, pte, false, false); + unlock_page(fault_page); +unlock_out: + pte_unmap_unlock(pte, ptl); + return ret; +} - pte_unmap_unlock(page_table, ptl); +static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page, *new_page; + spinlock_t *ptl; + pte_t *pte; + int ret; - if (dirty_page) { - struct address_space *mapping = page->mapping; - int dirtied = 0; + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; - if (set_page_dirty(dirty_page)) - dirtied = 1; - unlock_page(dirty_page); - put_page(dirty_page); - if ((dirtied || page_mkwrite) && mapping) { - /* - * Some device drivers do not set page.mapping but still - * dirty their pages - */ - balance_dirty_pages_ratelimited(mapping); - } + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + if (!new_page) + return VM_FAULT_OOM; - /* file_update_time outside page_lock */ - if (vma->vm_file && !page_mkwrite) - file_update_time(vma->vm_file); - } else { - unlock_page(vmf.page); - if (anon) - page_cache_release(vmf.page); + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) { + page_cache_release(new_page); + return VM_FAULT_OOM; } - return ret; + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + goto uncharge_out; -unwritable_page: - page_cache_release(page); + copy_user_highpage(new_page, fault_page, address, vma); + __SetPageUptodate(new_page); + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + goto uncharge_out; + } + do_set_pte(vma, address, new_page, pte, true, true); + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); return ret; uncharge_out: - /* fs's fault handler get error */ - if (cow_page) { - mem_cgroup_uncharge_page(cow_page); - page_cache_release(cow_page); + mem_cgroup_uncharge_page(new_page); + page_cache_release(new_page); + return ret; +} + +static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page; + struct address_space *mapping; + spinlock_t *ptl; + pte_t *pte; + int dirtied = 0; + int ret, tmp; + + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + /* + * Check if the backing address space wants to know that the page is + * about to become writable + */ + if (vma->vm_ops->page_mkwrite) { + unlock_page(fault_page); + tmp = do_page_mkwrite(vma, fault_page, address); + if (unlikely(!tmp || + (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + page_cache_release(fault_page); + return tmp; + } + } + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + return ret; } + do_set_pte(vma, address, fault_page, pte, true, false); + pte_unmap_unlock(pte, ptl); + + if (set_page_dirty(fault_page)) + dirtied = 1; + mapping = fault_page->mapping; + unlock_page(fault_page); + if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) { + /* + * Some device drivers do not set page.mapping but still + * dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + + /* file_update_time outside page_lock */ + if (vma->vm_file && !vma->vm_ops->page_mkwrite) + file_update_time(vma->vm_file); + return ret; } @@ -3401,7 +3024,13 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; pte_unmap(page_table); - return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); + if (!(flags & FAULT_FLAG_WRITE)) + return do_read_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + if (!(vma->vm_flags & VM_SHARED)) + return do_cow_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } /* @@ -3433,29 +3062,40 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, } pgoff = pte_to_pgoff(orig_pte); - return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); + if (!(flags & FAULT_FLAG_WRITE)) + return do_read_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + if (!(vma->vm_flags & VM_SHARED)) + return do_cow_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } -int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, - unsigned long addr, int current_nid) +static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int page_nid, + int *flags) { get_page(page); count_vm_numa_event(NUMA_HINT_FAULTS); - if (current_nid == numa_node_id()) + if (page_nid == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + *flags |= TNF_FAULT_LOCAL; + } return mpol_misplaced(page, vma, addr); } -int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, +static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd) { struct page *page = NULL; spinlock_t *ptl; - int current_nid = -1; + int page_nid = -1; + int last_cpupid; int target_nid; bool migrated = false; + int flags = 0; /* * The "pte" at this point cannot be used safely without @@ -3482,123 +3122,44 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(ptep, ptl); return 0; } + BUG_ON(is_zero_pfn(page_to_pfn(page))); - current_nid = page_to_nid(page); - target_nid = numa_migrate_prep(page, vma, addr, current_nid); + /* + * Avoid grouping on DSO/COW pages in specific and RO pages + * in general, RO pages shouldn't hurt as much anyway since + * they can be in shared cache state. + */ + if (!pte_write(pte)) + flags |= TNF_NO_GROUP; + + /* + * Flag if the page is shared between multiple address spaces. This + * is later used when determining whether to group tasks together + */ + if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) + flags |= TNF_SHARED; + + last_cpupid = page_cpupid_last(page); + page_nid = page_to_nid(page); + target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags); pte_unmap_unlock(ptep, ptl); if (target_nid == -1) { - /* - * Account for the fault against the current node if it not - * being replaced regardless of where the page is located. - */ - current_nid = numa_node_id(); put_page(page); goto out; } /* Migrate to the requested node */ - migrated = migrate_misplaced_page(page, target_nid); - if (migrated) - current_nid = target_nid; - -out: - if (current_nid != -1) - task_numa_fault(current_nid, 1, migrated); - return 0; -} - -/* NUMA hinting page fault entry point for regular pmds */ -#ifdef CONFIG_NUMA_BALANCING -static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) -{ - pmd_t pmd; - pte_t *pte, *orig_pte; - unsigned long _addr = addr & PMD_MASK; - unsigned long offset; - spinlock_t *ptl; - bool numa = false; - int local_nid = numa_node_id(); - - spin_lock(&mm->page_table_lock); - pmd = *pmdp; - if (pmd_numa(pmd)) { - set_pmd_at(mm, _addr, pmdp, pmd_mknonnuma(pmd)); - numa = true; + migrated = migrate_misplaced_page(page, vma, target_nid); + if (migrated) { + page_nid = target_nid; + flags |= TNF_MIGRATED; } - spin_unlock(&mm->page_table_lock); - - if (!numa) - return 0; - - /* we're in a page fault so some vma must be in the range */ - BUG_ON(!vma); - BUG_ON(vma->vm_start >= _addr + PMD_SIZE); - offset = max(_addr, vma->vm_start) & ~PMD_MASK; - VM_BUG_ON(offset >= PMD_SIZE); - orig_pte = pte = pte_offset_map_lock(mm, pmdp, _addr, &ptl); - pte += offset >> PAGE_SHIFT; - for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) { - pte_t pteval = *pte; - struct page *page; - int curr_nid = local_nid; - int target_nid; - bool migrated; - if (!pte_present(pteval)) - continue; - if (!pte_numa(pteval)) - continue; - if (addr >= vma->vm_end) { - vma = find_vma(mm, addr); - /* there's a pte present so there must be a vma */ - BUG_ON(!vma); - BUG_ON(addr < vma->vm_start); - } - if (pte_numa(pteval)) { - pteval = pte_mknonnuma(pteval); - set_pte_at(mm, addr, pte, pteval); - } - page = vm_normal_page(vma, addr, pteval); - if (unlikely(!page)) - continue; - /* only check non-shared pages */ - if (unlikely(page_mapcount(page) != 1)) - continue; - - /* - * Note that the NUMA fault is later accounted to either - * the node that is currently running or where the page is - * migrated to. - */ - curr_nid = local_nid; - target_nid = numa_migrate_prep(page, vma, addr, - page_to_nid(page)); - if (target_nid == -1) { - put_page(page); - continue; - } - - /* Migrate to the requested node */ - pte_unmap_unlock(pte, ptl); - migrated = migrate_misplaced_page(page, target_nid); - if (migrated) - curr_nid = target_nid; - task_numa_fault(curr_nid, 1, migrated); - pte = pte_offset_map_lock(mm, pmdp, addr, &ptl); - } - pte_unmap_unlock(orig_pte, ptl); - - return 0; -} -#else -static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) -{ - BUG(); +out: + if (page_nid != -1) + task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } -#endif /* CONFIG_NUMA_BALANCING */ /* * These routines also need to handle stuff like marking pages dirty @@ -3613,7 +3174,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ -int handle_pte_fault(struct mm_struct *mm, +static int handle_pte_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *pte, pmd_t *pmd, unsigned int flags) { @@ -3672,26 +3233,17 @@ unlock: /* * By the time we get here, we already hold the mm semaphore */ -int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, unsigned int flags) +static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - __set_current_state(TASK_RUNNING); - - count_vm_event(PGFAULT); - mem_cgroup_count_vm_event(mm, PGFAULT); - - /* do counter updates before entering really critical section. */ - check_sync_rss_stat(current); - if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); -retry: pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); if (!pud) @@ -3700,9 +3252,12 @@ retry: if (!pmd) return VM_FAULT_OOM; if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) { + int ret = VM_FAULT_FALLBACK; if (!vma->vm_ops) - return do_huge_pmd_anonymous_page(mm, vma, address, - pmd, flags); + ret = do_huge_pmd_anonymous_page(mm, vma, address, + pmd, flags); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { pmd_t orig_pmd = *pmd; int ret; @@ -3726,26 +3281,16 @@ retry: if (dirty && !pmd_write(orig_pmd)) { ret = do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd); - /* - * If COW results in an oom, the huge pmd will - * have been split, so retry the fault on the - * pte for a smaller charge. - */ - if (unlikely(ret & VM_FAULT_OOM)) - goto retry; - return ret; + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { huge_pmd_set_accessed(mm, vma, address, pmd, orig_pmd, dirty); + return 0; } - - return 0; } } - if (pmd_numa(*pmd)) - return do_pmd_numa_page(mm, vma, address, pmd); - /* * Use __pte_alloc instead of pte_alloc_map, because we can't * run pte_offset_map on the pmd, if an huge pmd could @@ -3768,6 +3313,43 @@ retry: return handle_pte_fault(mm, vma, address, pte, pmd, flags); } +int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) +{ + int ret; + + __set_current_state(TASK_RUNNING); + + count_vm_event(PGFAULT); + mem_cgroup_count_vm_event(mm, PGFAULT); + + /* do counter updates before entering really critical section. */ + check_sync_rss_stat(current); + + /* + * Enable the memcg OOM handling for faults triggered in user + * space. Kernel faults are handled more gracefully. + */ + if (flags & FAULT_FLAG_USER) + mem_cgroup_oom_enable(); + + ret = __handle_mm_fault(mm, vma, address, flags); + + if (flags & FAULT_FLAG_USER) { + mem_cgroup_oom_disable(); + /* + * The task may have entered a memcg OOM situation but + * if the allocation error was handled gracefully (no + * VM_FAULT_OOM), there is no need to kill anything. + * Just clean up the OOM state peacefully. + */ + if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) + mem_cgroup_oom_synchronize(false); + } + + return ret; +} + #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. @@ -3821,30 +3403,6 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } #endif /* __PAGETABLE_PMD_FOLDED */ -int make_pages_present(unsigned long addr, unsigned long end) -{ - int ret, len, write; - struct vm_area_struct * vma; - - vma = find_vma(current->mm, addr); - if (!vma) - return -ENOMEM; - /* - * We want to touch writable mappings with a write fault in order - * to break COW, except for shared mappings because these don't COW - * and we would not want to dirty them for nothing. - */ - write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE; - BUG_ON(addr >= end); - BUG_ON(end > vma->vm_end); - len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE; - ret = get_user_pages(current, current->mm, addr, - len, write, 0, NULL, NULL); - if (ret < 0) - return ret; - return ret == len ? 0 : -EFAULT; -} - #if !defined(__HAVE_ARCH_GATE_AREA) #if defined(AT_SYSINFO_EHDR) @@ -4010,6 +3568,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, return len; } +EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* @@ -4146,7 +3705,7 @@ void print_vma_addr(char *prefix, unsigned long ip) up_read(&mm->mmap_sem); } -#ifdef CONFIG_PROVE_LOCKING +#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void might_fault(void) { /* @@ -4158,13 +3717,17 @@ void might_fault(void) if (segment_eq(get_fs(), KERNEL_DS)) return; - might_sleep(); /* * it would be nicer only to annotate paths which are not under * pagefault_disable, however that requires a larger audit and * providing helpers like get_user_atomic. */ - if (!in_atomic() && current->mm) + if (in_atomic()) + return; + + __might_sleep(__FILE__, __LINE__, 0); + + if (current->mm) might_lock_read(¤t->mm->mmap_sem); } EXPORT_SYMBOL(might_fault); @@ -4240,3 +3803,30 @@ void copy_user_huge_page(struct page *dst, struct page *src, } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + +#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS + +static struct kmem_cache *page_ptl_cachep; + +void __init ptlock_cache_init(void) +{ + page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, + SLAB_PANIC, NULL); +} + +bool ptlock_alloc(struct page *page) +{ + spinlock_t *ptl; + + ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); + if (!ptl) + return false; + page->ptl = ptl; + return true; +} + +void ptlock_free(struct page *page) +{ + kmem_cache_free(page_ptl_cachep, page->ptl); +} +#endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index d04ed87bfac..469bbf505f8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -9,7 +9,6 @@ #include <linux/swap.h> #include <linux/interrupt.h> #include <linux/pagemap.h> -#include <linux/bootmem.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/pagevec.h> @@ -29,6 +28,9 @@ #include <linux/suspend.h> #include <linux/mm_inline.h> #include <linux/firmware-map.h> +#include <linux/stop_machine.h> +#include <linux/hugetlb.h> +#include <linux/memblock.h> #include <asm/tlbflush.h> @@ -44,23 +46,84 @@ static void generic_online_page(struct page *page); static online_page_callback_t online_page_callback = generic_online_page; +static DEFINE_MUTEX(online_page_callback_lock); -DEFINE_MUTEX(mem_hotplug_mutex); +/* The same as the cpu_hotplug lock, but for memory hotplug. */ +static struct { + struct task_struct *active_writer; + struct mutex lock; /* Synchronizes accesses to refcount, */ + /* + * Also blocks the new readers during + * an ongoing mem hotplug operation. + */ + int refcount; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} mem_hotplug = { + .active_writer = NULL, + .lock = __MUTEX_INITIALIZER(mem_hotplug.lock), + .refcount = 0, +#ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "mem_hotplug.lock" }, +#endif +}; + +/* Lockdep annotations for get/put_online_mems() and mem_hotplug_begin/end() */ +#define memhp_lock_acquire_read() lock_map_acquire_read(&mem_hotplug.dep_map) +#define memhp_lock_acquire() lock_map_acquire(&mem_hotplug.dep_map) +#define memhp_lock_release() lock_map_release(&mem_hotplug.dep_map) -void lock_memory_hotplug(void) +void get_online_mems(void) { - mutex_lock(&mem_hotplug_mutex); + might_sleep(); + if (mem_hotplug.active_writer == current) + return; + memhp_lock_acquire_read(); + mutex_lock(&mem_hotplug.lock); + mem_hotplug.refcount++; + mutex_unlock(&mem_hotplug.lock); + +} + +void put_online_mems(void) +{ + if (mem_hotplug.active_writer == current) + return; + mutex_lock(&mem_hotplug.lock); + + if (WARN_ON(!mem_hotplug.refcount)) + mem_hotplug.refcount++; /* try to fix things up */ + + if (!--mem_hotplug.refcount && unlikely(mem_hotplug.active_writer)) + wake_up_process(mem_hotplug.active_writer); + mutex_unlock(&mem_hotplug.lock); + memhp_lock_release(); - /* for exclusive hibernation if CONFIG_HIBERNATION=y */ - lock_system_sleep(); } -void unlock_memory_hotplug(void) +static void mem_hotplug_begin(void) { - unlock_system_sleep(); - mutex_unlock(&mem_hotplug_mutex); + mem_hotplug.active_writer = current; + + memhp_lock_acquire(); + for (;;) { + mutex_lock(&mem_hotplug.lock); + if (likely(!mem_hotplug.refcount)) + break; + __set_current_state(TASK_UNINTERRUPTIBLE); + mutex_unlock(&mem_hotplug.lock); + schedule(); + } } +static void mem_hotplug_done(void) +{ + mem_hotplug.active_writer = NULL; + mutex_unlock(&mem_hotplug.lock); + memhp_lock_release(); +} /* add this memory to iomem resource */ static struct resource *register_memory_resource(u64 start, u64 size) @@ -74,7 +137,7 @@ static struct resource *register_memory_resource(u64 start, u64 size) res->end = start + size - 1; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; if (request_resource(&iomem_resource, res) < 0) { - printk("System RAM resource %pR cannot be added\n", res); + pr_debug("System RAM resource %pR cannot be added\n", res); kfree(res); res = NULL; } @@ -91,9 +154,8 @@ static void release_memory_resource(struct resource *res) } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE -#ifndef CONFIG_SPARSEMEM_VMEMMAP -static void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type) +void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) { page->lru.next = (struct list_head *) type; SetPagePrivate(page); @@ -101,12 +163,9 @@ static void get_page_bootmem(unsigned long info, struct page *page, atomic_inc(&page->_count); } -/* reference to __meminit __free_pages_bootmem is valid - * so use __ref to tell modpost not to generate a warning */ -void __ref put_page_bootmem(struct page *page) +void put_page_bootmem(struct page *page) { unsigned long type; - static DEFINE_MUTEX(ppb_lock); type = (unsigned long) page->lru.next; BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || @@ -116,18 +175,12 @@ void __ref put_page_bootmem(struct page *page) ClearPagePrivate(page); set_page_private(page, 0); INIT_LIST_HEAD(&page->lru); - - /* - * Please refer to comment for __free_pages_bootmem() - * for why we serialize here. - */ - mutex_lock(&ppb_lock); - __free_pages_bootmem(page, 0); - mutex_unlock(&ppb_lock); + free_reserved_page(page); } - } +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE +#ifndef CONFIG_SPARSEMEM_VMEMMAP static void register_page_bootmem_info_section(unsigned long start_pfn) { unsigned long *usemap, mapsize, section_nr, i; @@ -161,6 +214,32 @@ static void register_page_bootmem_info_section(unsigned long start_pfn) get_page_bootmem(section_nr, page, MIX_SECTION_INFO); } +#else /* CONFIG_SPARSEMEM_VMEMMAP */ +static void register_page_bootmem_info_section(unsigned long start_pfn) +{ + unsigned long *usemap, mapsize, section_nr, i; + struct mem_section *ms; + struct page *page, *memmap; + + if (!pfn_valid(start_pfn)) + return; + + section_nr = pfn_to_section_nr(start_pfn); + ms = __nr_to_section(section_nr); + + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + + register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION); + + usemap = __nr_to_section(section_nr)->pageblock_flags; + page = virt_to_page(usemap); + + mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT; + + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, MIX_SECTION_INFO); +} +#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ void register_page_bootmem_info_node(struct pglist_data *pgdat) { @@ -177,7 +256,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) zone = &pgdat->node_zones[0]; for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) { - if (zone->wait_table) { + if (zone_is_initialized(zone)) { nr_pages = zone->wait_table_hash_nr_entries * sizeof(wait_queue_head_t); nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT; @@ -189,21 +268,21 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) } pfn = pgdat->node_start_pfn; - end_pfn = pfn + pgdat->node_spanned_pages; + end_pfn = pgdat_end_pfn(pgdat); - /* register_section info */ + /* register section info */ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { /* * Some platforms can assign the same pfn to multiple nodes - on * node0 as well as nodeN. To avoid registering a pfn against * multiple nodes we check that this pfn does not already - * reside in some other node. + * reside in some other nodes. */ if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node)) register_page_bootmem_info_section(pfn); } } -#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ +#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */ static void grow_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) @@ -212,8 +291,8 @@ static void grow_zone_span(struct zone *zone, unsigned long start_pfn, zone_span_writelock(zone); - old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; - if (!zone->spanned_pages || start_pfn < zone->zone_start_pfn) + old_zone_end_pfn = zone_end_pfn(zone); + if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn) zone->zone_start_pfn = start_pfn; zone->spanned_pages = max(old_zone_end_pfn, end_pfn) - @@ -253,6 +332,17 @@ static void fix_zone_id(struct zone *zone, unsigned long start_pfn, set_page_links(pfn_to_page(pfn), zid, nid, pfn); } +/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or + * alloc_bootmem_node_nopanic()/memblock_virt_alloc_node_nopanic() */ +static int __ref ensure_zone_is_initialized(struct zone *zone, + unsigned long start_pfn, unsigned long num_pages) +{ + if (!zone_is_initialized(zone)) + return init_currently_empty_zone(zone, start_pfn, num_pages, + MEMMAP_HOTPLUG); + return 0; +} + static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2, unsigned long start_pfn, unsigned long end_pfn) { @@ -260,19 +350,16 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2, unsigned long flags; unsigned long z1_start_pfn; - if (!z1->wait_table) { - ret = init_currently_empty_zone(z1, start_pfn, - end_pfn - start_pfn, MEMMAP_HOTPLUG); - if (ret) - return ret; - } + ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn); + if (ret) + return ret; pgdat_resize_lock(z1->zone_pgdat, &flags); /* can't move pfns which are higher than @z2 */ - if (end_pfn > z2->zone_start_pfn + z2->spanned_pages) + if (end_pfn > zone_end_pfn(z2)) goto out_fail; - /* the move out part mast at the left most of @z2 */ + /* the move out part must be at the left most of @z2 */ if (start_pfn > z2->zone_start_pfn) goto out_fail; /* must included/overlap */ @@ -280,13 +367,13 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2, goto out_fail; /* use start_pfn for z1's start_pfn if z1 is empty */ - if (z1->spanned_pages) + if (!zone_is_empty(z1)) z1_start_pfn = z1->zone_start_pfn; else z1_start_pfn = start_pfn; resize_zone(z1, z1_start_pfn, end_pfn); - resize_zone(z2, end_pfn, z2->zone_start_pfn + z2->spanned_pages); + resize_zone(z2, end_pfn, zone_end_pfn(z2)); pgdat_resize_unlock(z1->zone_pgdat, &flags); @@ -305,12 +392,9 @@ static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2, unsigned long flags; unsigned long z2_end_pfn; - if (!z2->wait_table) { - ret = init_currently_empty_zone(z2, start_pfn, - end_pfn - start_pfn, MEMMAP_HOTPLUG); - if (ret) - return ret; - } + ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn); + if (ret) + return ret; pgdat_resize_lock(z1->zone_pgdat, &flags); @@ -318,15 +402,15 @@ static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2, if (z1->zone_start_pfn > start_pfn) goto out_fail; /* the move out part mast at the right most of @z1 */ - if (z1->zone_start_pfn + z1->spanned_pages > end_pfn) + if (zone_end_pfn(z1) > end_pfn) goto out_fail; /* must included/overlap */ - if (start_pfn >= z1->zone_start_pfn + z1->spanned_pages) + if (start_pfn >= zone_end_pfn(z1)) goto out_fail; /* use end_pfn for z2's end_pfn if z2 is empty */ - if (z2->spanned_pages) - z2_end_pfn = z2->zone_start_pfn + z2->spanned_pages; + if (!zone_is_empty(z2)) + z2_end_pfn = zone_end_pfn(z2); else z2_end_pfn = end_pfn; @@ -346,8 +430,7 @@ out_fail: static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long old_pgdat_end_pfn = - pgdat->node_start_pfn + pgdat->node_spanned_pages; + unsigned long old_pgdat_end_pfn = pgdat_end_pfn(pgdat); if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn) pgdat->node_start_pfn = start_pfn; @@ -363,16 +446,13 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) int nid = pgdat->node_id; int zone_type; unsigned long flags; + int ret; zone_type = zone - pgdat->node_zones; - if (!zone->wait_table) { - int ret; + ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages); + if (ret) + return ret; - ret = init_currently_empty_zone(zone, phys_start_pfn, - nr_pages, MEMMAP_HOTPLUG); - if (ret) - return ret; - } pgdat_resize_lock(zone->zone_pgdat, &flags); grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages); grow_pgdat_span(zone->zone_pgdat, phys_start_pfn, @@ -386,13 +466,12 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) static int __meminit __add_section(int nid, struct zone *zone, unsigned long phys_start_pfn) { - int nr_pages = PAGES_PER_SECTION; int ret; if (pfn_valid(phys_start_pfn)) return -EEXIST; - ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages); + ret = sparse_add_one_section(zone, phys_start_pfn); if (ret < 0) return ret; @@ -405,36 +484,6 @@ static int __meminit __add_section(int nid, struct zone *zone, return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); } -#ifdef CONFIG_SPARSEMEM_VMEMMAP -static int __remove_section(struct zone *zone, struct mem_section *ms) -{ - /* - * XXX: Freeing memmap with vmemmap is not implement yet. - * This should be removed later. - */ - return -EBUSY; -} -#else -static int __remove_section(struct zone *zone, struct mem_section *ms) -{ - unsigned long flags; - struct pglist_data *pgdat = zone->zone_pgdat; - int ret = -EINVAL; - - if (!valid_section(ms)) - return ret; - - ret = unregister_memory_section(ms); - if (ret) - return ret; - - pgdat_resize_lock(pgdat, &flags); - sparse_remove_one_section(zone, ms); - pgdat_resize_unlock(pgdat, &flags); - return 0; -} -#endif - /* * Reasonably generic function for adding memory. It is * expected that archs that support memory hotplug will @@ -468,6 +517,230 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, } EXPORT_SYMBOL_GPL(__add_pages); +#ifdef CONFIG_MEMORY_HOTREMOVE +/* find the smallest valid pfn in the range [start_pfn, end_pfn) */ +static int find_smallest_section_pfn(int nid, struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn) +{ + struct mem_section *ms; + + for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) { + ms = __pfn_to_section(start_pfn); + + if (unlikely(!valid_section(ms))) + continue; + + if (unlikely(pfn_to_nid(start_pfn) != nid)) + continue; + + if (zone && zone != page_zone(pfn_to_page(start_pfn))) + continue; + + return start_pfn; + } + + return 0; +} + +/* find the biggest valid pfn in the range [start_pfn, end_pfn). */ +static int find_biggest_section_pfn(int nid, struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn) +{ + struct mem_section *ms; + unsigned long pfn; + + /* pfn is the end pfn of a memory section. */ + pfn = end_pfn - 1; + for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) { + ms = __pfn_to_section(pfn); + + if (unlikely(!valid_section(ms))) + continue; + + if (unlikely(pfn_to_nid(pfn) != nid)) + continue; + + if (zone && zone != page_zone(pfn_to_page(pfn))) + continue; + + return pfn; + } + + return 0; +} + +static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, + unsigned long end_pfn) +{ + unsigned long zone_start_pfn = zone->zone_start_pfn; + unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */ + unsigned long zone_end_pfn = z; + unsigned long pfn; + struct mem_section *ms; + int nid = zone_to_nid(zone); + + zone_span_writelock(zone); + if (zone_start_pfn == start_pfn) { + /* + * If the section is smallest section in the zone, it need + * shrink zone->zone_start_pfn and zone->zone_spanned_pages. + * In this case, we find second smallest valid mem_section + * for shrinking zone. + */ + pfn = find_smallest_section_pfn(nid, zone, end_pfn, + zone_end_pfn); + if (pfn) { + zone->zone_start_pfn = pfn; + zone->spanned_pages = zone_end_pfn - pfn; + } + } else if (zone_end_pfn == end_pfn) { + /* + * If the section is biggest section in the zone, it need + * shrink zone->spanned_pages. + * In this case, we find second biggest valid mem_section for + * shrinking zone. + */ + pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn, + start_pfn); + if (pfn) + zone->spanned_pages = pfn - zone_start_pfn + 1; + } + + /* + * The section is not biggest or smallest mem_section in the zone, it + * only creates a hole in the zone. So in this case, we need not + * change the zone. But perhaps, the zone has only hole data. Thus + * it check the zone has only hole or not. + */ + pfn = zone_start_pfn; + for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) { + ms = __pfn_to_section(pfn); + + if (unlikely(!valid_section(ms))) + continue; + + if (page_zone(pfn_to_page(pfn)) != zone) + continue; + + /* If the section is current section, it continues the loop */ + if (start_pfn == pfn) + continue; + + /* If we find valid section, we have nothing to do */ + zone_span_writeunlock(zone); + return; + } + + /* The zone has no valid section */ + zone->zone_start_pfn = 0; + zone->spanned_pages = 0; + zone_span_writeunlock(zone); +} + +static void shrink_pgdat_span(struct pglist_data *pgdat, + unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long pgdat_start_pfn = pgdat->node_start_pfn; + unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */ + unsigned long pgdat_end_pfn = p; + unsigned long pfn; + struct mem_section *ms; + int nid = pgdat->node_id; + + if (pgdat_start_pfn == start_pfn) { + /* + * If the section is smallest section in the pgdat, it need + * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages. + * In this case, we find second smallest valid mem_section + * for shrinking zone. + */ + pfn = find_smallest_section_pfn(nid, NULL, end_pfn, + pgdat_end_pfn); + if (pfn) { + pgdat->node_start_pfn = pfn; + pgdat->node_spanned_pages = pgdat_end_pfn - pfn; + } + } else if (pgdat_end_pfn == end_pfn) { + /* + * If the section is biggest section in the pgdat, it need + * shrink pgdat->node_spanned_pages. + * In this case, we find second biggest valid mem_section for + * shrinking zone. + */ + pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn, + start_pfn); + if (pfn) + pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1; + } + + /* + * If the section is not biggest or smallest mem_section in the pgdat, + * it only creates a hole in the pgdat. So in this case, we need not + * change the pgdat. + * But perhaps, the pgdat has only hole data. Thus it check the pgdat + * has only hole or not. + */ + pfn = pgdat_start_pfn; + for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) { + ms = __pfn_to_section(pfn); + + if (unlikely(!valid_section(ms))) + continue; + + if (pfn_to_nid(pfn) != nid) + continue; + + /* If the section is current section, it continues the loop */ + if (start_pfn == pfn) + continue; + + /* If we find valid section, we have nothing to do */ + return; + } + + /* The pgdat has no valid section */ + pgdat->node_start_pfn = 0; + pgdat->node_spanned_pages = 0; +} + +static void __remove_zone(struct zone *zone, unsigned long start_pfn) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + int nr_pages = PAGES_PER_SECTION; + int zone_type; + unsigned long flags; + + zone_type = zone - pgdat->node_zones; + + pgdat_resize_lock(zone->zone_pgdat, &flags); + shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); + shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages); + pgdat_resize_unlock(zone->zone_pgdat, &flags); +} + +static int __remove_section(struct zone *zone, struct mem_section *ms) +{ + unsigned long start_pfn; + int scn_nr; + int ret = -EINVAL; + + if (!valid_section(ms)) + return ret; + + ret = unregister_memory_section(ms); + if (ret) + return ret; + + scn_nr = __section_nr(ms); + start_pfn = section_nr_to_pfn(scn_nr); + __remove_zone(zone, start_pfn); + + sparse_remove_one_section(zone, ms); + return 0; +} + /** * __remove_pages() - remove sections of pages from a zone * @zone: zone from which pages need to be removed @@ -482,8 +755,10 @@ EXPORT_SYMBOL_GPL(__add_pages); int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) { - unsigned long i, ret = 0; + unsigned long i; int sections_to_remove; + resource_size_t start, size; + int ret = 0; /* * We can only remove entire sections @@ -491,7 +766,15 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK); BUG_ON(nr_pages % PAGES_PER_SECTION); - release_mem_region(phys_start_pfn << PAGE_SHIFT, nr_pages * PAGE_SIZE); + start = phys_start_pfn << PAGE_SHIFT; + size = nr_pages * PAGE_SIZE; + ret = release_mem_region_adjustable(&iomem_resource, start, size); + if (ret) { + resource_size_t endres = start + size - 1; + + pr_warn("Unable to release resource <%pa-%pa> (%d)\n", + &start, &endres, ret); + } sections_to_remove = nr_pages / PAGES_PER_SECTION; for (i = 0; i < sections_to_remove; i++) { @@ -503,19 +786,22 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, return ret; } EXPORT_SYMBOL_GPL(__remove_pages); +#endif /* CONFIG_MEMORY_HOTREMOVE */ int set_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; - lock_memory_hotplug(); + get_online_mems(); + mutex_lock(&online_page_callback_lock); if (online_page_callback == generic_online_page) { online_page_callback = callback; rc = 0; } - unlock_memory_hotplug(); + mutex_unlock(&online_page_callback_lock); + put_online_mems(); return rc; } @@ -525,14 +811,16 @@ int restore_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; - lock_memory_hotplug(); + get_online_mems(); + mutex_lock(&online_page_callback_lock); if (online_page_callback == callback) { online_page_callback = generic_online_page; rc = 0; } - unlock_memory_hotplug(); + mutex_unlock(&online_page_callback_lock); + put_online_mems(); return rc; } @@ -540,29 +828,18 @@ EXPORT_SYMBOL_GPL(restore_online_page_callback); void __online_page_set_limits(struct page *page) { - unsigned long pfn = page_to_pfn(page); - - if (pfn >= num_physpages) - num_physpages = pfn + 1; } EXPORT_SYMBOL_GPL(__online_page_set_limits); void __online_page_increment_counters(struct page *page) { - totalram_pages++; - -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages++; -#endif + adjust_managed_page_count(page, 1); } EXPORT_SYMBOL_GPL(__online_page_increment_counters); void __online_page_free(struct page *page) { - ClearPageReserved(page); - init_page_count(page); - __free_page(page); + __free_reserved_page(page); } EXPORT_SYMBOL_GPL(__online_page_free); @@ -683,6 +960,7 @@ static void node_states_set_node(int node, struct memory_notify *arg) int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) { + unsigned long flags; unsigned long onlined_pages = 0; struct zone *zone; int need_zonelists_rebuild = 0; @@ -690,7 +968,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ int ret; struct memory_notify arg; - lock_memory_hotplug(); + mem_hotplug_begin(); /* * This doesn't need a lock to do pfn_to_page(). * The section can't be removed here because of the @@ -698,23 +976,18 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ */ zone = page_zone(pfn_to_page(pfn)); + ret = -EINVAL; if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) && - !can_online_high_movable(zone)) { - unlock_memory_hotplug(); - return -1; - } + !can_online_high_movable(zone)) + goto out; if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) { - if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) { - unlock_memory_hotplug(); - return -1; - } + if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) + goto out; } if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) { - if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) { - unlock_memory_hotplug(); - return -1; - } + if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) + goto out; } /* Previous code may changed the zone of the pfn range */ @@ -724,14 +997,13 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ arg.nr_pages = nr_pages; node_states_check_changes_online(nr_pages, zone, &arg); - nid = page_to_nid(pfn_to_page(pfn)); + nid = pfn_to_nid(pfn); ret = memory_notify(MEM_GOING_ONLINE, &arg); ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); - unlock_memory_hotplug(); - return ret; + goto out; } /* * If this zone is not populated, then it is not in zonelist. @@ -755,13 +1027,15 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); - unlock_memory_hotplug(); - return ret; + goto out; } - zone->managed_pages += onlined_pages; zone->present_pages += onlined_pages; + + pgdat_resize_lock(zone->zone_pgdat, &flags); zone->zone_pgdat->node_present_pages += onlined_pages; + pgdat_resize_unlock(zone->zone_pgdat, &flags); + if (onlined_pages) { node_states_set_node(zone_to_nid(zone), &arg); if (need_zonelists_rebuild) @@ -783,9 +1057,9 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) memory_notify(MEM_ONLINE, &arg); - unlock_memory_hotplug(); - - return 0; +out: + mem_hotplug_done(); + return ret; } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ @@ -795,13 +1069,16 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) struct pglist_data *pgdat; unsigned long zones_size[MAX_NR_ZONES] = {0}; unsigned long zholes_size[MAX_NR_ZONES] = {0}; - unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long start_pfn = PFN_DOWN(start); - pgdat = arch_alloc_nodedata(nid); - if (!pgdat) - return NULL; + pgdat = NODE_DATA(nid); + if (!pgdat) { + pgdat = arch_alloc_nodedata(nid); + if (!pgdat) + return NULL; - arch_refresh_nodedata(nid, pgdat); + arch_refresh_nodedata(nid, pgdat); + } /* we can use NODE_DATA(nid) from here */ @@ -827,17 +1104,23 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat) } -/* +/** + * try_online_node - online a node if offlined + * * called by cpu_up() to online a node without onlined memory. */ -int mem_online_node(int nid) +int try_online_node(int nid) { pg_data_t *pgdat; int ret; - lock_memory_hotplug(); + if (node_online(nid)) + return 0; + + mem_hotplug_begin(); pgdat = hotadd_new_pgdat(nid, 0); if (!pgdat) { + pr_err("Cannot online node %d due to NULL pgdat\n", nid); ret = -ENOMEM; goto out; } @@ -845,32 +1128,65 @@ int mem_online_node(int nid) ret = register_one_node(nid); BUG_ON(ret); + if (pgdat->node_zonelists->_zonerefs->zone == NULL) { + mutex_lock(&zonelists_mutex); + build_all_zonelists(NULL, NULL); + mutex_unlock(&zonelists_mutex); + } + out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } +static int check_hotplug_memory_range(u64 start, u64 size) +{ + u64 start_pfn = PFN_DOWN(start); + u64 nr_pages = size >> PAGE_SHIFT; + + /* Memory range must be aligned with section */ + if ((start_pfn & ~PAGE_SECTION_MASK) || + (nr_pages % PAGES_PER_SECTION) || (!nr_pages)) { + pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx\n", + (unsigned long long)start, + (unsigned long long)size); + return -EINVAL; + } + + return 0; +} + /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ int __ref add_memory(int nid, u64 start, u64 size) { pg_data_t *pgdat = NULL; - int new_pgdat = 0; + bool new_pgdat; + bool new_node; struct resource *res; int ret; - lock_memory_hotplug(); + ret = check_hotplug_memory_range(start, size); + if (ret) + return ret; res = register_memory_resource(start, size); ret = -EEXIST; if (!res) - goto out; + return ret; + + { /* Stupid hack to suppress address-never-null warning */ + void *p = NODE_DATA(nid); + new_pgdat = !p; + } - if (!node_online(nid)) { + mem_hotplug_begin(); + + new_node = !node_online(nid); + if (new_node) { pgdat = hotadd_new_pgdat(nid, start); ret = -ENOMEM; if (!pgdat) goto error; - new_pgdat = 1; } /* call arch's memory hotadd */ @@ -882,7 +1198,7 @@ int __ref add_memory(int nid, u64 start, u64 size) /* we online node here. we can't roll back from here. */ node_set_online(nid); - if (new_pgdat) { + if (new_node) { ret = register_one_node(nid); /* * If sysfs file of new node can't create, cpu on the node @@ -901,11 +1217,10 @@ error: /* rollback pgdat allocation and others */ if (new_pgdat) rollback_node_hotadd(nid, pgdat); - if (res) - release_memory_resource(res); + release_memory_resource(res); out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } EXPORT_SYMBOL_GPL(add_memory); @@ -985,10 +1300,12 @@ static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) } /* - * Scanning pfn is much easier than scanning lru list. - * Scan pfn from start to end and Find LRU page. + * Scan pfn range [start,end) to find movable/migratable pages (LRU pages + * and hugepages). We scan pfn because it's much easier than scanning over + * linked list. This function returns the pfn of the first found movable + * page if it's found, otherwise 0. */ -static unsigned long scan_lru_pages(unsigned long start, unsigned long end) +static unsigned long scan_movable_pages(unsigned long start, unsigned long end) { unsigned long pfn; struct page *page; @@ -997,6 +1314,13 @@ static unsigned long scan_lru_pages(unsigned long start, unsigned long end) page = pfn_to_page(pfn); if (PageLRU(page)) return pfn; + if (PageHuge(page)) { + if (is_hugepage_active(page)) + return pfn; + else + pfn = round_up(pfn + 1, + 1 << compound_order(page)) - 1; + } } } return 0; @@ -1017,6 +1341,19 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (!pfn_valid(pfn)) continue; page = pfn_to_page(pfn); + + if (PageHuge(page)) { + struct page *head = compound_head(page); + pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1; + if (compound_order(head) > PFN_SECTION_SHIFT) { + ret = -EBUSY; + break; + } + if (isolate_huge_page(page, &source)) + move_pages -= 1 << compound_order(head); + continue; + } + if (!get_page_unless_zero(page)) continue; /* @@ -1035,7 +1372,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) #ifdef CONFIG_DEBUG_VM printk(KERN_ALERT "removing pfn %lx from LRU failed\n", pfn); - dump_page(page); + dump_page(page, "failed to remove from LRU"); #endif put_page(page); /* Because we don't have big zone->lock. we should @@ -1049,7 +1386,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } if (!list_empty(&source)) { if (not_managed) { - putback_lru_pages(&source); + putback_movable_pages(&source); goto out; } @@ -1057,11 +1394,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * alloc_migrate_target should be improooooved!! * migrate_pages returns # of failed pages. */ - ret = migrate_pages(&source, alloc_migrate_target, 0, - true, MIGRATE_SYNC, - MR_MEMORY_HOTPLUG); + ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, + MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) - putback_lru_pages(&source); + putback_movable_pages(&source); } out: return ret; @@ -1149,6 +1485,37 @@ static bool can_offline_normal(struct zone *zone, unsigned long nr_pages) } #endif /* CONFIG_MOVABLE_NODE */ +static int __init cmdline_parse_movable_node(char *p) +{ +#ifdef CONFIG_MOVABLE_NODE + /* + * Memory used by the kernel cannot be hot-removed because Linux + * cannot migrate the kernel pages. When memory hotplug is + * enabled, we should prevent memblock from allocating memory + * for the kernel. + * + * ACPI SRAT records all hotpluggable memory ranges. But before + * SRAT is parsed, we don't know about it. + * + * The kernel image is loaded into memory at very early time. We + * cannot prevent this anyway. So on NUMA system, we set any + * node the kernel resides in as un-hotpluggable. + * + * Since on modern servers, one node could have double-digit + * gigabytes memory, we can assume the memory around the kernel + * image is also un-hotpluggable. So before SRAT is parsed, just + * allocate memory near the kernel image to try the best to keep + * the kernel away from hotpluggable memory. + */ + memblock_set_bottom_up(true); + movable_node_enabled = true; +#else + pr_warn("movable_node option not supported\n"); +#endif + return 0; +} +early_param("movable_node", cmdline_parse_movable_node); + /* check which state of node_states will be changed when offline memory */ static void node_states_check_changes_offline(unsigned long nr_pages, struct zone *zone, struct memory_notify *arg) @@ -1246,10 +1613,10 @@ static int __ref __offline_pages(unsigned long start_pfn, unsigned long pfn, nr_pages, expire; long offlined_pages; int ret, drain, retry_max, node; + unsigned long flags; struct zone *zone; struct memory_notify arg; - BUG_ON(start_pfn >= end_pfn); /* at least, alignment against pageblock is necessary */ if (!IS_ALIGNED(start_pfn, pageblock_nr_pages)) return -EINVAL; @@ -1260,7 +1627,7 @@ static int __ref __offline_pages(unsigned long start_pfn, if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; - lock_memory_hotplug(); + mem_hotplug_begin(); zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); @@ -1304,8 +1671,8 @@ repeat: drain_all_pages(); } - pfn = scan_lru_pages(start_pfn, end_pfn); - if (pfn) { /* We have page on LRU */ + pfn = scan_movable_pages(start_pfn, end_pfn); + if (pfn) { /* We have movable pages */ ret = do_migrate_range(pfn, end_pfn); if (!ret) { drain = 1; @@ -1324,6 +1691,11 @@ repeat: yield(); /* drain pcp pages, this is synchronous. */ drain_all_pages(); + /* + * dissolve free hugepages in the memory block before doing offlining + * actually in order to make hugetlbfs's object counting consistent. + */ + dissolve_free_huge_pages(start_pfn, end_pfn); /* check again */ offlined_pages = check_pages_isolated(start_pfn, end_pfn); if (offlined_pages < 0) { @@ -1337,10 +1709,12 @@ repeat: /* reset pagetype flags and makes migrate type to be MOVABLE */ undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); /* removal success */ - zone->managed_pages -= offlined_pages; + adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages); zone->present_pages -= offlined_pages; + + pgdat_resize_lock(zone->zone_pgdat, &flags); zone->zone_pgdat->node_present_pages -= offlined_pages; - totalram_pages -= offlined_pages; + pgdat_resize_unlock(zone->zone_pgdat, &flags); init_per_zone_wmark_min(); @@ -1360,7 +1734,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); - unlock_memory_hotplug(); + mem_hotplug_done(); return 0; failed_removal: @@ -1372,7 +1746,7 @@ failed_removal: undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } @@ -1380,18 +1754,28 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); } +#endif /* CONFIG_MEMORY_HOTREMOVE */ -int remove_memory(u64 start, u64 size) +/** + * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn) + * @start_pfn: start pfn of the memory range + * @end_pfn: end pfn of the memory range + * @arg: argument passed to func + * @func: callback for each memory section walked + * + * This function walks through all present mem sections in range + * [start_pfn, end_pfn) and call func on each mem section. + * + * Returns the return value of func. + */ +int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, + void *arg, int (*func)(struct memory_block *, void *)) { struct memory_block *mem = NULL; struct mem_section *section; - unsigned long start_pfn, end_pfn; unsigned long pfn, section_nr; int ret; - start_pfn = PFN_DOWN(start); - end_pfn = start_pfn + PFN_DOWN(size); - for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { section_nr = pfn_to_section_nr(pfn); if (!present_section_nr(section_nr)) @@ -1408,7 +1792,7 @@ int remove_memory(u64 start, u64 size) if (!mem) continue; - ret = offline_memory_block(mem); + ret = func(mem, arg); if (ret) { kobject_put(&mem->dev.kobj); return ret; @@ -1420,14 +1804,172 @@ int remove_memory(u64 start, u64 size) return 0; } -#else -int offline_pages(unsigned long start_pfn, unsigned long nr_pages) + +#ifdef CONFIG_MEMORY_HOTREMOVE +static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) { - return -EINVAL; + int ret = !is_memblock_offlined(mem); + + if (unlikely(ret)) { + phys_addr_t beginpa, endpa; + + beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)); + endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1; + pr_warn("removing memory fails, because memory " + "[%pa-%pa] is onlined\n", + &beginpa, &endpa); + } + + return ret; } -int remove_memory(u64 start, u64 size) + +static int check_cpu_on_node(pg_data_t *pgdat) { - return -EINVAL; + int cpu; + + for_each_present_cpu(cpu) { + if (cpu_to_node(cpu) == pgdat->node_id) + /* + * the cpu on this node isn't removed, and we can't + * offline this node. + */ + return -EBUSY; + } + + return 0; +} + +static void unmap_cpu_on_node(pg_data_t *pgdat) +{ +#ifdef CONFIG_ACPI_NUMA + int cpu; + + for_each_possible_cpu(cpu) + if (cpu_to_node(cpu) == pgdat->node_id) + numa_clear_node(cpu); +#endif +} + +static int check_and_unmap_cpu_on_node(pg_data_t *pgdat) +{ + int ret; + + ret = check_cpu_on_node(pgdat); + if (ret) + return ret; + + /* + * the node will be offlined when we come here, so we can clear + * the cpu_to_node() now. + */ + + unmap_cpu_on_node(pgdat); + return 0; +} + +/** + * try_offline_node + * + * Offline a node if all memory sections and cpus of the node are removed. + * + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations before this call. + */ +void try_offline_node(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + unsigned long start_pfn = pgdat->node_start_pfn; + unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; + unsigned long pfn; + struct page *pgdat_page = virt_to_page(pgdat); + int i; + + for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + unsigned long section_nr = pfn_to_section_nr(pfn); + + if (!present_section_nr(section_nr)) + continue; + + if (pfn_to_nid(pfn) != nid) + continue; + + /* + * some memory sections of this node are not removed, and we + * can't offline node now. + */ + return; + } + + if (check_and_unmap_cpu_on_node(pgdat)) + return; + + /* + * all memory/cpu of this node are removed, we can offline this + * node now. + */ + node_set_offline(nid); + unregister_one_node(nid); + + if (!PageSlab(pgdat_page) && !PageCompound(pgdat_page)) + /* node data is allocated from boot memory */ + return; + + /* free waittable in each zone */ + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + + /* + * wait_table may be allocated from boot memory, + * here only free if it's allocated by vmalloc. + */ + if (is_vmalloc_addr(zone->wait_table)) + vfree(zone->wait_table); + } + + /* + * Since there is no way to guarentee the address of pgdat/zone is not + * on stack of any kernel threads or used by other kernel objects + * without reference counting or other symchronizing method, do not + * reset node_data and free pgdat here. Just reset it to 0 and reuse + * the memory when the node is online again. + */ + memset(pgdat, 0, sizeof(*pgdat)); +} +EXPORT_SYMBOL(try_offline_node); + +/** + * remove_memory + * + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations before this call, as required by + * try_offline_node(). + */ +void __ref remove_memory(int nid, u64 start, u64 size) +{ + int ret; + + BUG_ON(check_hotplug_memory_range(start, size)); + + mem_hotplug_begin(); + + /* + * All memory blocks must be offlined before removing memory. Check + * whether all memory blocks in question are offline and trigger a BUG() + * if this is not the case. + */ + ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, + check_memblock_offlined_cb); + if (ret) + BUG(); + + /* remove memmap entry */ + firmware_map_remove(start, start + size, "System RAM"); + + arch_remove_memory(start, size); + + try_offline_node(nid); + + mem_hotplug_done(); } -#endif /* CONFIG_MEMORY_HOTREMOVE */ EXPORT_SYMBOL_GPL(remove_memory); +#endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e2df1c1fb41..8f5330d74f4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -26,7 +26,7 @@ * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. - * As a special case node -1 here means do the allocation + * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. @@ -65,6 +65,8 @@ kernel is not always grateful with that. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/highmem.h> @@ -91,6 +93,7 @@ #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> +#include <linux/printk.h> #include <asm/tlbflush.h> #include <asm/uaccess.h> @@ -123,16 +126,19 @@ static struct mempolicy preferred_node_policy[MAX_NUMNODES]; static struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; - int node; if (!pol) { - node = numa_node_id(); - if (node != -1) - pol = &preferred_node_policy[node]; + int node = numa_node_id(); - /* preferred_node_policy is not initialised early in boot */ - if (!pol->mode) - pol = NULL; + if (node != NUMA_NO_NODE) { + pol = &preferred_node_policy[node]; + /* + * preferred_node_policy is not initialised early in + * boot + */ + if (!pol->mode) + pol = NULL; + } } return pol; @@ -161,19 +167,7 @@ static const struct mempolicy_operations { /* Check that the nodemask contains at least one populated zone */ static int is_valid_nodemask(const nodemask_t *nodemask) { - int nd, k; - - for_each_node_mask(nd, *nodemask) { - struct zone *z; - - for (k = 0; k <= policy_zone; k++) { - z = &NODE_DATA(nd)->node_zones[k]; - if (z->present_pages > 0) - return 1; - } - } - - return 0; + return nodes_intersects(*nodemask, node_states[N_MEMORY]); } static inline int mpol_store_user_nodemask(const struct mempolicy *pol) @@ -270,7 +264,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, struct mempolicy *policy; pr_debug("setting mode %d flags %d nodes[0] %lx\n", - mode, flags, nodes ? nodes_addr(*nodes)[0] : -1); + mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) @@ -485,8 +479,11 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { static void migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); -/* Scan through pages checking if pages follow certain conditions. */ -static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, +/* + * Scan through pages checking if pages follow certain conditions, + * and move them to the pagelist if they do. + */ +static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -508,9 +505,8 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, /* * vm_normal_page() filters out zero pages, but there might * still be PageReserved pages to skip, perhaps in a VDSO. - * And we cannot move PageKsm pages sensibly or safely yet. */ - if (PageReserved(page) || PageKsm(page)) + if (PageReserved(page)) continue; nid = page_to_nid(page); if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) @@ -525,7 +521,36 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, return addr != end; } -static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, +static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma, + pmd_t *pmd, const nodemask_t *nodes, unsigned long flags, + void *private) +{ +#ifdef CONFIG_HUGETLB_PAGE + int nid; + struct page *page; + spinlock_t *ptl; + pte_t entry; + + ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd); + entry = huge_ptep_get((pte_t *)pmd); + if (!pte_present(entry)) + goto unlock; + page = pte_page(entry); + nid = page_to_nid(page); + if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) + goto unlock; + /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ + if (flags & (MPOL_MF_MOVE_ALL) || + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) + isolate_huge_page(page, private); +unlock: + spin_unlock(ptl); +#else + BUG(); +#endif +} + +static inline int queue_pages_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -536,17 +561,24 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + if (!pmd_present(*pmd)) + continue; + if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) { + queue_pages_hugetlb_pmd_range(vma, pmd, nodes, + flags, private); + continue; + } split_huge_page_pmd(vma, addr, pmd); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; - if (check_pte_range(vma, pmd, addr, next, nodes, + if (queue_pages_pte_range(vma, pmd, addr, next, nodes, flags, private)) return -EIO; } while (pmd++, addr = next, addr != end); return 0; } -static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline int queue_pages_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -557,16 +589,18 @@ static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd, pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); + if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) + continue; if (pud_none_or_clear_bad(pud)) continue; - if (check_pmd_range(vma, pud, addr, next, nodes, + if (queue_pages_pmd_range(vma, pud, addr, next, nodes, flags, private)) return -EIO; } while (pud++, addr = next, addr != end); return 0; } -static inline int check_pgd_range(struct vm_area_struct *vma, +static inline int queue_pages_pgd_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -579,14 +613,14 @@ static inline int check_pgd_range(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - if (check_pud_range(vma, pgd, addr, next, nodes, + if (queue_pages_pud_range(vma, pgd, addr, next, nodes, flags, private)) return -EIO; } while (pgd++, addr = next, addr != end); return 0; } -#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE +#ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these @@ -600,7 +634,6 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { int nr_updated; - BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE); nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1); if (nr_updated) @@ -614,26 +647,27 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, { return 0; } -#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ +#endif /* CONFIG_NUMA_BALANCING */ /* - * Check if all pages in a range are on a set of nodes. - * If pagelist != NULL then isolate pages from the LRU and - * put them on the pagelist. + * Walk through page tables and collect pages to be migrated. + * + * If pages found in a given range are on a set of nodes (determined by + * @nodes and @flags,) it's isolated and queued to the pagelist which is + * passed via @private.) */ -static struct vm_area_struct * -check_range(struct mm_struct *mm, unsigned long start, unsigned long end, +static int +queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) { - int err; - struct vm_area_struct *first, *vma, *prev; - + int err = 0; + struct vm_area_struct *vma, *prev; - first = find_vma(mm, start); - if (!first) - return ERR_PTR(-EFAULT); + vma = find_vma(mm, start); + if (!vma) + return -EFAULT; prev = NULL; - for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) { + for (; vma && vma->vm_start < end; vma = vma->vm_next) { unsigned long endvma = vma->vm_end; if (endvma > end) @@ -643,14 +677,11 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, if (!(flags & MPOL_MF_DISCONTIG_OK)) { if (!vma->vm_next && vma->vm_end < end) - return ERR_PTR(-EFAULT); + return -EFAULT; if (prev && prev->vm_end < vma->vm_start) - return ERR_PTR(-EFAULT); + return -EFAULT; } - if (is_vm_hugetlb_page(vma)) - goto next; - if (flags & MPOL_MF_LAZY) { change_prot_numa(vma, start, endvma); goto next; @@ -660,17 +691,15 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) && vma_migratable(vma))) { - err = check_pgd_range(vma, start, endvma, nodes, + err = queue_pages_pgd_range(vma, start, endvma, nodes, flags, private); - if (err) { - first = ERR_PTR(err); + if (err) break; - } } next: prev = vma; } - return first; + return err; } /* @@ -745,7 +774,10 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, if (prev) { vma = prev; next = vma->vm_next; - continue; + if (mpol_equal(vma_policy(vma), new_pol)) + continue; + /* vma_merge() joined vma && vma->next, case 8 */ + goto replace; } if (vma->vm_start != vmstart) { err = split_vma(vma->vm_mm, vma, vmstart, 1); @@ -757,6 +789,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, if (err) goto out; } + replace: err = vma_replace_policy(vma, new_pol); if (err) goto out; @@ -766,36 +799,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, return err; } -/* - * Update task->flags PF_MEMPOLICY bit: set iff non-default - * mempolicy. Allows more rapid checking of this (combined perhaps - * with other PF_* flag bits) on memory allocation hot code paths. - * - * If called from outside this file, the task 'p' should -only- be - * a newly forked child not yet visible on the task list, because - * manipulating the task flags of a visible task is not safe. - * - * The above limitation is why this routine has the funny name - * mpol_fix_fork_child_flag(). - * - * It is also safe to call this with a task pointer of current, - * which the static wrapper mpol_set_task_struct_flag() does, - * for use within this file. - */ - -void mpol_fix_fork_child_flag(struct task_struct *p) -{ - if (p->mempolicy) - p->flags |= PF_MEMPOLICY; - else - p->flags &= ~PF_MEMPOLICY; -} - -static void mpol_set_task_struct_flag(void) -{ - mpol_fix_fork_child_flag(current); -} - /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) @@ -832,7 +835,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, } old = current->mempolicy; current->mempolicy = new; - mpol_set_task_struct_flag(); if (new && new->mode == MPOL_INTERLEAVE && nodes_weight(new->v.nodes)) current->il_next = first_node(new->v.nodes); @@ -999,7 +1001,11 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, static struct page *new_node_page(struct page *page, unsigned long node, int **x) { - return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0); + if (PageHuge(page)) + return alloc_huge_page_node(page_hstate(compound_head(page)), + node); + else + return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0); } /* @@ -1022,15 +1028,14 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, * space range and MPOL_MF_DISCONTIG_OK, this call can not fail. */ VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); - check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, + queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, - false, MIGRATE_SYNC, - MR_SYSCALL); + err = migrate_pages(&pagelist, new_node_page, NULL, dest, + MIGRATE_SYNC, MR_SYSCALL); if (err) - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); } return err; @@ -1093,7 +1098,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, tmp = *from; while (!nodes_empty(tmp)) { int s,d; - int source = -1; + int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { @@ -1128,7 +1133,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, if (!node_isset(dest, tmp)) break; } - if (source == -1) + if (source == NUMA_NO_NODE) break; node_clear(source, tmp); @@ -1148,16 +1153,17 @@ out: /* * Allocate a new page for page migration based on vma policy. - * Start assuming that page is mapped by vma pointed to by @private. + * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { - struct vm_area_struct *vma = (struct vm_area_struct *)private; + struct vm_area_struct *vma; unsigned long uninitialized_var(address); + vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) @@ -1165,6 +1171,10 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int * vma = vma->vm_next; } + if (PageHuge(page)) { + BUG_ON(!vma); + return alloc_huge_page_noerr(vma, address, 1); + } /* * if !vma, alloc_page_vma() will use task or system default policy */ @@ -1183,7 +1193,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, return -ENOSYS; } -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { return NULL; } @@ -1193,7 +1203,6 @@ static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { - struct vm_area_struct *vma; struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; @@ -1235,7 +1244,7 @@ static long do_mbind(unsigned long start, unsigned long len, pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", start, start + len, mode, mode_flags, - nmask ? nodes_addr(*nmask)[0] : -1); + nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { @@ -1259,11 +1268,9 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - vma = check_range(mm, start, end, nmask, + err = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); - - err = PTR_ERR(vma); /* maybe ... */ - if (!IS_ERR(vma)) + if (!err) err = mbind_range(mm, start, end, new); if (!err) { @@ -1271,18 +1278,16 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, - false, MIGRATE_SYNC, - MR_MEMPOLICY_MBIND); + nr_failed = migrate_pages(&pagelist, new_page, NULL, + start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; } else - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); up_write(&mm->mmap_sem); mpol_out: @@ -1358,7 +1363,7 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, - unsigned long, mode, unsigned long __user *, nmask, + unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned, flags) { nodemask_t nodes; @@ -1379,7 +1384,7 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, } /* Set the process memory policy */ -SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask, +SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { int err; @@ -1521,10 +1526,10 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, #ifdef CONFIG_COMPAT -asmlinkage long compat_sys_get_mempolicy(int __user *policy, - compat_ulong_t __user *nmask, - compat_ulong_t maxnode, - compat_ulong_t addr, compat_ulong_t flags) +COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, + compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode, + compat_ulong_t, addr, compat_ulong_t, flags) { long err; unsigned long __user *nm = NULL; @@ -1551,8 +1556,8 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy, return err; } -asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, - compat_ulong_t maxnode) +COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode) { long err = 0; unsigned long __user *nm = NULL; @@ -1574,9 +1579,9 @@ asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, return sys_set_mempolicy(mode, nm, nr_bits+1); } -asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, - compat_ulong_t mode, compat_ulong_t __user *nmask, - compat_ulong_t maxnode, compat_ulong_t flags) +COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, + compat_ulong_t, mode, compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode, compat_ulong_t, flags) { long err = 0; unsigned long __user *nm = NULL; @@ -1602,9 +1607,9 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, /* * get_vma_policy(@task, @vma, @addr) - * @task - task for fallback if vma policy == default - * @vma - virtual memory area whose policy is sought - * @addr - address in @vma for shared policy lookup + * @task: task for fallback if vma policy == default + * @vma: virtual memory area whose policy is sought + * @addr: address in @vma for shared policy lookup * * Returns effective policy for a VMA at specified address. * Falls back to @task or system default policy, as necessary. @@ -1644,6 +1649,50 @@ struct mempolicy *get_vma_policy(struct task_struct *task, return pol; } +bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma) +{ + struct mempolicy *pol = get_task_policy(task); + if (vma) { + if (vma->vm_ops && vma->vm_ops->get_policy) { + bool ret = false; + + pol = vma->vm_ops->get_policy(vma, vma->vm_start); + if (pol && (pol->flags & MPOL_F_MOF)) + ret = true; + mpol_cond_put(pol); + + return ret; + } else if (vma->vm_policy) { + pol = vma->vm_policy; + } + } + + if (!pol) + return default_policy.flags & MPOL_F_MOF; + + return pol->flags & MPOL_F_MOF; +} + +static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) +{ + enum zone_type dynamic_policy_zone = policy_zone; + + BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); + + /* + * if policy->v.nodes has movable memory only, + * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. + * + * policy->v.nodes is intersect with node_states[N_MEMORY]. + * so if the following test faile, it implies + * policy->v.nodes has movable memory only. + */ + if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) + dynamic_policy_zone = ZONE_MOVABLE; + + return zone >= dynamic_policy_zone; +} + /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation @@ -1652,7 +1701,7 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) { /* Lower zones don't get a nodemask applied for MPOL_BIND */ if (unlikely(policy->mode == MPOL_BIND) && - gfp_zone(gfp) >= policy_zone && + apply_policy_zone(policy, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) return &policy->v.nodes; @@ -1703,21 +1752,18 @@ static unsigned interleave_nodes(struct mempolicy *policy) /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. - * @policy must be protected by freeing by the caller. If @policy is - * the current task's mempolicy, this protection is implicit, as only the - * task can change it's policy. The system default policy requires no - * such protection. */ -unsigned slab_node(void) +unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; + int node = numa_mem_id(); if (in_interrupt()) - return numa_node_id(); + return node; policy = current->mempolicy; if (!policy || policy->flags & MPOL_F_LOCAL) - return numa_node_id(); + return node; switch (policy->mode) { case MPOL_PREFERRED: @@ -1737,11 +1783,11 @@ unsigned slab_node(void) struct zonelist *zonelist; struct zone *zone; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); - zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0]; + zonelist = &NODE_DATA(node)->node_zonelists[0]; (void)first_zones_zonelist(zonelist, highest_zoneidx, &policy->v.nodes, &zone); - return zone ? zone->node : numa_node_id(); + return zone ? zone->node : node; } default: @@ -1756,7 +1802,7 @@ static unsigned offset_il_node(struct mempolicy *pol, unsigned nnodes = nodes_weight(pol->v.nodes); unsigned target; int c; - int nid = -1; + int nid = NUMA_NO_NODE; if (!nnodes) return numa_node_id(); @@ -1793,11 +1839,11 @@ static inline unsigned interleave_nid(struct mempolicy *pol, /* * Return the bit number of a random bit set in the nodemask. - * (returns -1 if nodemask is empty) + * (returns NUMA_NO_NODE if nodemask is empty) */ int node_random(const nodemask_t *maskp) { - int w, bit = -1; + int w, bit = NUMA_NO_NODE; w = nodes_weight(*maskp); if (w) @@ -1809,18 +1855,18 @@ int node_random(const nodemask_t *maskp) #ifdef CONFIG_HUGETLBFS /* * huge_zonelist(@vma, @addr, @gfp_flags, @mpol) - * @vma = virtual memory area whose policy is sought - * @addr = address in @vma for shared policy lookup and interleave policy - * @gfp_flags = for requested zone - * @mpol = pointer to mempolicy pointer for reference counted mempolicy - * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask + * @vma: virtual memory area whose policy is sought + * @addr: address in @vma for shared policy lookup and interleave policy + * @gfp_flags: for requested zone + * @mpol: pointer to mempolicy pointer for reference counted mempolicy + * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask * * Returns a zonelist suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * - * Must be protected by get_mems_allowed() + * Must be protected by read_mems_allowed_begin() */ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, @@ -1984,7 +2030,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, retry_cpuset: pol = get_vma_policy(current, vma, addr); - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; @@ -1992,7 +2038,7 @@ retry_cpuset: nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2002,7 +2048,7 @@ retry_cpuset: policy_nodemask(gfp, pol)); if (unlikely(mpol_needs_cond_ref(pol))) __mpol_put(pol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } @@ -2036,7 +2082,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) pol = &default_policy; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* * No reference counting needed for current->mempolicy @@ -2049,13 +2095,23 @@ retry_cpuset: policy_zonelist(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } EXPORT_SYMBOL(alloc_pages_current); +int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) +{ + struct mempolicy *pol = mpol_dup(vma_policy(src)); + + if (IS_ERR(pol)) + return PTR_ERR(pol); + dst->vm_policy = pol; + return 0; +} + /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() @@ -2083,7 +2139,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) } else *new = *old; - rcu_read_lock(); if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); if (new->flags & MPOL_F_REBINDING) @@ -2091,7 +2146,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) else mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE); } - rcu_read_unlock(); atomic_set(&new->refcnt, 1); return new; } @@ -2215,9 +2269,9 @@ static void sp_free(struct sp_node *n) /** * mpol_misplaced - check whether current page node is valid in policy * - * @page - page to be checked - * @vma - vm area where page mapped - * @addr - virtual address where page mapped + * @page: page to be checked + * @vma: vm area where page mapped + * @addr: virtual address where page mapped * * Lookup current policy node id for vma,addr and "compare to" page's * node id. @@ -2235,6 +2289,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long struct zone *zone; int curnid = page_to_nid(page); unsigned long pgoff; + int thiscpu = raw_smp_processor_id(); + int thisnid = cpu_to_node(thiscpu); int polnid = -1; int ret = -1; @@ -2283,33 +2339,9 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long /* Migrate the page towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { - int last_nid; - - polnid = numa_node_id(); + polnid = thisnid; - /* - * Multi-stage node selection is used in conjunction - * with a periodic migration fault to build a temporal - * task<->page relation. By using a two-stage filter we - * remove short/unlikely relations. - * - * Using P(p) ~ n_p / n_t as per frequentist - * probability, we can equate a task's usage of a - * particular page (n_p) per total usage of this - * page (n_t) (in a given time-span) to a probability. - * - * Our periodic faults will sample this probability and - * getting the same result twice in a row, given these - * samples are fully independent, is then given by - * P(n)^2, provided our sample period is sufficiently - * short compared to the usage pattern. - * - * This quadric squishes small probabilities, making - * it less likely we act on an unlikely task<->page - * relation. - */ - last_nid = page_xchg_last_nid(page, polnid); - if (last_nid != polnid) + if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) goto out; } @@ -2385,9 +2417,9 @@ restart: *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); - sp_node_init(n_new, n->end, end, mpol_new); - sp_insert(sp, n_new); + sp_node_init(n_new, end, n->end, mpol_new); n->end = start; + sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; @@ -2483,7 +2515,7 @@ int mpol_set_shared_policy(struct shared_policy *info, vma->vm_pgoff, sz, npol ? npol->mode : -1, npol ? npol->flags : -1, - npol ? nodes_addr(npol->v.nodes)[0] : -1); + npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); @@ -2515,7 +2547,7 @@ void mpol_free_shared_policy(struct shared_policy *p) } #ifdef CONFIG_NUMA_BALANCING -static bool __initdata numabalancing_override; +static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { @@ -2524,9 +2556,15 @@ static void __init check_numabalancing_enable(void) if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; + /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ + if (numabalancing_override) + set_numabalancing_state(numabalancing_override == 1); + if (nr_node_ids > 1 && !numabalancing_override) { - printk(KERN_INFO "Enabling automatic NUMA balancing. " - "Configure with numa_balancing= or sysctl"); + pr_info("%s automatic NUMA balancing. " + "Configure with numa_balancing= or the " + "kernel.numa_balancing sysctl", + numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } @@ -2536,18 +2574,17 @@ static int __init setup_numabalancing(char *str) int ret = 0; if (!str) goto out; - numabalancing_override = true; if (!strcmp(str, "enable")) { - set_numabalancing_state(true); + numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { - set_numabalancing_state(false); + numabalancing_override = -1; ret = 1; } out: if (!ret) - printk(KERN_WARNING "Unable to parse numa_balancing=\n"); + pr_warn("Unable to parse numa_balancing=\n"); return ret; } @@ -2607,7 +2644,7 @@ void __init numa_policy_init(void) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) - printk("numa_policy_init: interleaving failed\n"); + pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } @@ -2775,62 +2812,45 @@ out: * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * - * Convert a mempolicy into a string. - * Returns the number of characters in buffer (if positive) - * or an error (negative) + * Convert @pol into a string. If @buffer is too short, truncate the string. + * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the + * longest flag, "relative", and to display at least a few node ids. */ -int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) +void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; - int l; - nodemask_t nodes; - unsigned short mode; - unsigned short flags = pol ? pol->flags : 0; + nodemask_t nodes = NODE_MASK_NONE; + unsigned short mode = MPOL_DEFAULT; + unsigned short flags = 0; - /* - * Sanity check: room for longest mode, flag and some nodes - */ - VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16); - - if (!pol || pol == &default_policy) - mode = MPOL_DEFAULT; - else + if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) { mode = pol->mode; + flags = pol->flags; + } switch (mode) { case MPOL_DEFAULT: - nodes_clear(nodes); break; - case MPOL_PREFERRED: - nodes_clear(nodes); if (flags & MPOL_F_LOCAL) mode = MPOL_LOCAL; else node_set(pol->v.preferred_node, nodes); break; - case MPOL_BIND: - /* Fall through */ case MPOL_INTERLEAVE: nodes = pol->v.nodes; break; - default: - return -EINVAL; + WARN_ON_ONCE(1); + snprintf(p, maxlen, "unknown"); + return; } - l = strlen(policy_modes[mode]); - if (buffer + maxlen < p + l + 1) - return -ENOSPC; - - strcpy(p, policy_modes[mode]); - p += l; + p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { - if (buffer + maxlen < p + 2) - return -ENOSPC; - *p++ = '='; + p += snprintf(p, buffer + maxlen - p, "="); /* * Currently, the only defined flags are mutually exclusive @@ -2842,10 +2862,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) } if (!nodes_empty(nodes)) { - if (buffer + maxlen < p + 2) - return -ENOSPC; - *p++ = ':'; + p += snprintf(p, buffer + maxlen - p, ":"); p += nodelist_scnprintf(p, buffer + maxlen - p, nodes); } - return p - buffer; } diff --git a/mm/mempool.c b/mm/mempool.c index 54990476c04..e209c98c720 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/slab.h> +#include <linux/kmemleak.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/blkdev.h> @@ -73,7 +74,7 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, gfp_t gfp_mask, int node_id) { mempool_t *pool; - pool = kmalloc_node(sizeof(*pool), gfp_mask | __GFP_ZERO, node_id); + pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id); if (!pool) return NULL; pool->elements = kmalloc_node(min_nr * sizeof(void *), @@ -192,6 +193,7 @@ EXPORT_SYMBOL(mempool_resize); * returns NULL. Note that due to preallocation, this function * *never* fails when called from process contexts. (it might * fail if called from an IRQ context.) + * Note: using __GFP_ZERO is not supported. */ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask) { @@ -200,6 +202,7 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask) wait_queue_t wait; gfp_t gfp_temp; + VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); might_sleep_if(gfp_mask & __GFP_WAIT); gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ @@ -220,6 +223,11 @@ repeat_alloc: spin_unlock_irqrestore(&pool->lock, flags); /* paired with rmb in mempool_free(), read comment there */ smp_wmb(); + /* + * Update the allocation stack trace as this is more useful + * for debugging. + */ + kmemleak_update_trace(element); return element; } @@ -304,9 +312,9 @@ void mempool_free(void *element, mempool_t *pool) * ensures that there will be frees which return elements to the * pool waking up the waiters. */ - if (pool->curr_nr < pool->min_nr) { + if (unlikely(pool->curr_nr < pool->min_nr)) { spin_lock_irqsave(&pool->lock, flags); - if (pool->curr_nr < pool->min_nr) { + if (likely(pool->curr_nr < pool->min_nr)) { add_element(pool, element); spin_unlock_irqrestore(&pool->lock, flags); wake_up(&pool->wait); diff --git a/mm/migrate.c b/mm/migrate.c index c38778610aa..be6dbf995c0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -36,6 +36,7 @@ #include <linux/hugetlb_cgroup.h> #include <linux/gfp.h> #include <linux/balloon_compaction.h> +#include <linux/mmu_notifier.h> #include <asm/tlbflush.h> @@ -71,28 +72,12 @@ int migrate_prep_local(void) } /* - * Add isolated pages on the list back to the LRU under page lock - * to avoid leaking evictable pages back onto unevictable list. - */ -void putback_lru_pages(struct list_head *l) -{ - struct page *page; - struct page *page2; - - list_for_each_entry_safe(page, page2, l, lru) { - list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + - page_is_file_cache(page)); - putback_lru_page(page); - } -} - -/* * Put previously isolated pages back onto the appropriate lists * from where they were once taken off for compaction/migration. * - * This function shall be used instead of putback_lru_pages(), - * whenever the isolated pageset has been built by isolate_migratepages_range() + * This function shall be used whenever the isolated pageset has been + * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() + * and isolate_huge_page(). */ void putback_movable_pages(struct list_head *l) { @@ -100,10 +85,14 @@ void putback_movable_pages(struct list_head *l) struct page *page2; list_for_each_entry_safe(page, page2, l, lru) { + if (unlikely(PageHuge(page))) { + putback_active_hugepage(page); + continue; + } list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - if (unlikely(balloon_page_movable(page))) + if (unlikely(isolated_balloon_page(page))) balloon_page_putback(page); else putback_lru_page(page); @@ -126,13 +115,11 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, ptep = huge_pte_offset(mm, addr); if (!ptep) goto out; - ptl = &mm->page_table_lock; + ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep); } else { pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; ptep = pte_offset_map(pmd, addr); @@ -157,13 +144,17 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, get_page(new); pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); + if (pte_swp_soft_dirty(*ptep)) + pte = pte_mksoft_dirty(pte); if (is_write_migration_entry(entry)) pte = pte_mkwrite(pte); #ifdef CONFIG_HUGETLB_PAGE - if (PageHuge(new)) + if (PageHuge(new)) { pte = pte_mkhuge(pte); + pte = arch_make_huge_pte(pte, vma, new, 0); + } #endif - flush_cache_page(vma, addr, pte_pfn(pte)); + flush_dcache_page(new); set_pte_at(mm, addr, ptep, pte); if (PageHuge(new)) { @@ -185,12 +176,49 @@ out: } /* + * Congratulations to trinity for discovering this bug. + * mm/fremap.c's remap_file_pages() accepts any range within a single vma to + * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then + * replace the specified range by file ptes throughout (maybe populated after). + * If page migration finds a page within that range, while it's still located + * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem: + * zap_pte() clears the temporary migration entry before mmap_sem is dropped. + * But if the migrating page is in a part of the vma outside the range to be + * remapped, then it will not be cleared, and remove_migration_ptes() needs to + * deal with it. Fortunately, this part of the vma is of course still linear, + * so we just need to use linear location on the nonlinear list. + */ +static int remove_linear_migration_ptes_from_nonlinear(struct page *page, + struct address_space *mapping, void *arg) +{ + struct vm_area_struct *vma; + /* hugetlbfs does not support remap_pages, so no huge pgoff worries */ + pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + unsigned long addr; + + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { + + addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + if (addr >= vma->vm_start && addr < vma->vm_end) + remove_migration_pte(page, vma, addr, arg); + } + return SWAP_AGAIN; +} + +/* * Get rid of all migration entries and replace them by * references to the indicated page. */ static void remove_migration_ptes(struct page *old, struct page *new) { - rmap_walk(new, remove_migration_pte, old); + struct rmap_walk_control rwc = { + .rmap_one = remove_migration_pte, + .arg = old, + .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, + }; + + rmap_walk(new, &rwc); } /* @@ -198,15 +226,14 @@ static void remove_migration_ptes(struct page *old, struct page *new) * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ -void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, - unsigned long address) +static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) { - pte_t *ptep, pte; - spinlock_t *ptl; + pte_t pte; swp_entry_t entry; struct page *page; - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + spin_lock(ptl); pte = *ptep; if (!is_swap_pte(pte)) goto out; @@ -234,6 +261,21 @@ out: pte_unmap_unlock(ptep, ptl); } +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + spinlock_t *ptl = pte_lockptr(mm, pmd); + pte_t *ptep = pte_offset_map(pmd, address); + __migration_entry_wait(mm, ptep, ptl); +} + +void migration_entry_wait_huge(struct vm_area_struct *vma, + struct mm_struct *mm, pte_t *pte) +{ + spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte); + __migration_entry_wait(mm, pte, ptl); +} + #ifdef CONFIG_BLOCK /* Returns true if all buffers are successfully locked */ static bool buffer_migrate_lock_buffers(struct buffer_head *head, @@ -292,16 +334,17 @@ static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, * 2 for pages with a mapping * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ -static int migrate_page_move_mapping(struct address_space *mapping, +int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, - struct buffer_head *head, enum migrate_mode mode) + struct buffer_head *head, enum migrate_mode mode, + int extra_count) { - int expected_count = 0; + int expected_count = 1 + extra_count; void **pslot; if (!mapping) { /* Anonymous page without mapping */ - if (page_count(page) != 1) + if (page_count(page) != expected_count) return -EAGAIN; return MIGRATEPAGE_SUCCESS; } @@ -311,7 +354,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, pslot = radix_tree_lookup_slot(&mapping->page_tree, page_index(page)); - expected_count = 2 + page_has_private(page); + expected_count += 1 + page_has_private(page); if (page_count(page) != expected_count || radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { spin_unlock_irq(&mapping->tree_lock); @@ -420,10 +463,60 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, } /* + * Gigantic pages are so large that we do not guarantee that page++ pointer + * arithmetic will work across the entire page. We need something more + * specialized. + */ +static void __copy_gigantic_page(struct page *dst, struct page *src, + int nr_pages) +{ + int i; + struct page *dst_base = dst; + struct page *src_base = src; + + for (i = 0; i < nr_pages; ) { + cond_resched(); + copy_highpage(dst, src); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} + +static void copy_huge_page(struct page *dst, struct page *src) +{ + int i; + int nr_pages; + + if (PageHuge(src)) { + /* hugetlbfs page */ + struct hstate *h = page_hstate(src); + nr_pages = pages_per_huge_page(h); + + if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) { + __copy_gigantic_page(dst, src, nr_pages); + return; + } + } else { + /* thp page */ + BUG_ON(!PageTransHuge(src)); + nr_pages = hpage_nr_pages(src); + } + + for (i = 0; i < nr_pages; i++) { + cond_resched(); + copy_highpage(dst + i, src + i); + } +} + +/* * Copy the page to its new location */ void migrate_page_copy(struct page *newpage, struct page *page) { + int cpupid; + if (PageHuge(page) || PageTransHuge(page)) copy_huge_page(newpage, page); else @@ -436,7 +529,7 @@ void migrate_page_copy(struct page *newpage, struct page *page) if (PageUptodate(page)) SetPageUptodate(newpage); if (TestClearPageActive(page)) { - VM_BUG_ON(PageUnevictable(page)); + VM_BUG_ON_PAGE(PageUnevictable(page), page); SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); @@ -460,9 +553,19 @@ void migrate_page_copy(struct page *newpage, struct page *page) __set_page_dirty_nobuffers(newpage); } + /* + * Copy NUMA information to the new page, to prevent over-eager + * future migrations of this same page. + */ + cpupid = page_cpupid_xchg_last(page, -1); + page_cpupid_xchg_last(newpage, cpupid); + mlock_migrate_page(newpage, page); ksm_migrate_page(newpage, page); - + /* + * Please do not reorder this without considering how mm/ksm.c's + * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). + */ ClearPageSwapCache(page); ClearPagePrivate(page); set_page_private(page, 0); @@ -479,14 +582,6 @@ void migrate_page_copy(struct page *newpage, struct page *page) * Migration functions ***********************************************************/ -/* Always fail migration. Used for mappings that are not movable */ -int fail_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) -{ - return -EIO; -} -EXPORT_SYMBOL(fail_migrate_page); - /* * Common logic to directly migrate a single page suitable for * pages that do not use PagePrivate/PagePrivate2. @@ -501,7 +596,7 @@ int migrate_page(struct address_space *mapping, BUG_ON(PageWriteback(page)); /* Writeback must be complete */ - rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode); + rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0); if (rc != MIGRATEPAGE_SUCCESS) return rc; @@ -528,7 +623,7 @@ int buffer_migrate_page(struct address_space *mapping, head = page_buffers(page); - rc = migrate_page_move_mapping(mapping, newpage, page, head, mode); + rc = migrate_page_move_mapping(mapping, newpage, page, head, mode, 0); if (rc != MIGRATEPAGE_SUCCESS) return rc; @@ -696,7 +791,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, } static int __unmap_and_move(struct page *page, struct page *newpage, - int force, bool offlining, enum migrate_mode mode) + int force, enum migrate_mode mode) { int rc = -EAGAIN; int remap_swapcache = 1; @@ -726,26 +821,12 @@ static int __unmap_and_move(struct page *page, struct page *newpage, lock_page(page); } - /* - * Only memory hotplug's offline_pages() caller has locked out KSM, - * and can safely migrate a KSM page. The other cases have skipped - * PageKsm along with PageReserved - but it is only now when we have - * the page lock that we can be certain it will not go KSM beneath us - * (KSM will not upgrade a page from PageAnon to PageKsm when it sees - * its pagecount raised, but only here do we take the page lock which - * serializes that). - */ - if (PageKsm(page) && !offlining) { - rc = -EBUSY; - goto unlock; - } - /* charge against new page */ mem_cgroup_prepare_migration(page, newpage, &mem); if (PageWriteback(page)) { /* - * Only in the case of a full syncronous migration is it + * Only in the case of a full synchronous migration is it * necessary to wait for PageWriteback. In the async case, * the retry loop is too short and in the sync-light case, * the overhead of stalling is too much @@ -766,7 +847,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, * File Caches may use write_page() or lock_page() in migration, then, * just care Anon page here. */ - if (PageAnon(page)) { + if (PageAnon(page) && !PageKsm(page)) { /* * Only page_lock_anon_vma_read() understands the subtleties of * getting a hold on an anon_vma from outside one of its mms. @@ -820,7 +901,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, * free the metadata, so the page can be freed. */ if (!page->mapping) { - VM_BUG_ON(PageAnon(page)); + VM_BUG_ON_PAGE(PageAnon(page), page); if (page_has_private(page)) { try_to_free_buffers(page); goto uncharge; @@ -846,7 +927,6 @@ uncharge: mem_cgroup_end_migration(mem, page, newpage, (rc == MIGRATEPAGE_SUCCESS || rc == MIGRATEPAGE_BALLOON_SUCCESS)); -unlock: unlock_page(page); out: return rc; @@ -856,8 +936,8 @@ out: * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, bool offlining, +static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, + unsigned long private, struct page *page, int force, enum migrate_mode mode) { int rc = 0; @@ -876,7 +956,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, if (unlikely(split_huge_page(page))) goto out; - rc = __unmap_and_move(page, newpage, force, offlining, mode); + rc = __unmap_and_move(page, newpage, force, mode); if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) { /* @@ -902,11 +982,18 @@ out: page_is_file_cache(page)); putback_lru_page(page); } + /* - * Move the new page to the LRU. If migration was not successful - * then this will free the page. + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, putback_lru_page() will drop the reference grabbed + * during isolation. */ - putback_lru_page(newpage); + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) { + ClearPageSwapBacked(newpage); + put_new_page(newpage, private); + } else + putback_lru_page(newpage); + if (result) { if (rc) *result = rc; @@ -935,15 +1022,28 @@ out: * will wait in the page fault for migration to complete. */ static int unmap_and_move_huge_page(new_page_t get_new_page, - unsigned long private, struct page *hpage, - int force, bool offlining, + free_page_t put_new_page, unsigned long private, + struct page *hpage, int force, enum migrate_mode mode) { int rc = 0; int *result = NULL; - struct page *new_hpage = get_new_page(hpage, private, &result); + struct page *new_hpage; struct anon_vma *anon_vma = NULL; + /* + * Movability of hugepages depends on architectures and hugepage size. + * This check is necessary because some callers of hugepage migration + * like soft offline and memory hotremove don't walk through page + * tables or check whether the hugepage is pmd-based or not before + * kicking migration. + */ + if (!hugepage_migration_supported(page_hstate(hpage))) { + putback_active_hugepage(hpage); + return -ENOSYS; + } + + new_hpage = get_new_page(hpage, private, &result); if (!new_hpage) return -ENOMEM; @@ -963,18 +1063,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, 1, mode); - if (rc) + if (rc != MIGRATEPAGE_SUCCESS) remove_migration_ptes(hpage, hpage); if (anon_vma) put_anon_vma(anon_vma); - if (!rc) + if (rc == MIGRATEPAGE_SUCCESS) hugetlb_cgroup_migrate(hpage, new_hpage); unlock_page(hpage); out: - put_page(new_hpage); + if (rc != -EAGAIN) + putback_active_hugepage(hpage); + + /* + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, put_page() will drop the reference grabbed during + * isolation. + */ + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) + put_new_page(new_hpage, private); + else + put_page(new_hpage); + if (result) { if (rc) *result = rc; @@ -985,22 +1097,28 @@ out: } /* - * migrate_pages + * migrate_pages - migrate the pages specified in a list, to the free pages + * supplied as the target for the page migration * - * The function takes one list of pages to migrate and a function - * that determines from the page to be migrated and the private data - * the target of the move and allocates the page. + * @from: The list of pages to be migrated. + * @get_new_page: The function used to allocate free pages to be used + * as the target of the page migration. + * @put_new_page: The function used to free target pages if migration + * fails, or NULL if no special handling is necessary. + * @private: Private data to be passed on to get_new_page() + * @mode: The migration mode that specifies the constraints for + * page migration, if any. + * @reason: The reason for page migration. * - * The function returns after 10 attempts or if no pages - * are movable anymore because to has become empty - * or no retryable pages exist anymore. - * Caller should call putback_lru_pages to return pages to the LRU + * The function returns after 10 attempts or if no pages are movable any more + * because the list has become empty or no retryable pages exist any more. + * The caller should call putback_lru_pages() to return pages to the LRU * or free list only if ret != 0. * - * Return: Number of pages not migrated or error code. + * Returns the number of pages that were not migrated, or an error code. */ -int migrate_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private, bool offlining, +int migrate_pages(struct list_head *from, new_page_t get_new_page, + free_page_t put_new_page, unsigned long private, enum migrate_mode mode, int reason) { int retry = 1; @@ -1021,9 +1139,13 @@ int migrate_pages(struct list_head *from, list_for_each_entry_safe(page, page2, from, lru) { cond_resched(); - rc = unmap_and_move(get_new_page, private, - page, pass > 2, offlining, - mode); + if (PageHuge(page)) + rc = unmap_and_move_huge_page(get_new_page, + put_new_page, private, page, + pass > 2, mode); + else + rc = unmap_and_move(get_new_page, put_new_page, + private, page, pass > 2, mode); switch(rc) { case -ENOMEM: @@ -1035,7 +1157,12 @@ int migrate_pages(struct list_head *from, nr_succeeded++; break; default: - /* Permanent failure */ + /* + * Permanent failure (-EBUSY, -ENOSYS, etc.): + * unlike -EAGAIN case, the failed page is + * removed from migration page list and not + * retried in the next outer loop. + */ nr_failed++; break; } @@ -1055,34 +1182,6 @@ out: return rc; } -int migrate_huge_page(struct page *hpage, new_page_t get_new_page, - unsigned long private, bool offlining, - enum migrate_mode mode) -{ - int pass, rc; - - for (pass = 0; pass < 10; pass++) { - rc = unmap_and_move_huge_page(get_new_page, - private, hpage, pass > 2, offlining, - mode); - switch (rc) { - case -ENOMEM: - goto out; - case -EAGAIN: - /* try again */ - cond_resched(); - break; - case MIGRATEPAGE_SUCCESS: - goto out; - default: - rc = -EIO; - goto out; - } - } -out: - return rc; -} - #ifdef CONFIG_NUMA /* * Move a list of individual pages @@ -1107,8 +1206,12 @@ static struct page *new_page_node(struct page *p, unsigned long private, *result = &pm->status; - return alloc_pages_exact_node(pm->node, - GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0); + if (PageHuge(p)) + return alloc_huge_page_node(page_hstate(compound_head(p)), + pm->node); + else + return alloc_pages_exact_node(pm->node, + GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0); } /* @@ -1150,7 +1253,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm, goto set_status; /* Use PageReserved to check for zero page */ - if (PageReserved(page) || PageKsm(page)) + if (PageReserved(page)) goto put_and_set; pp->page = page; @@ -1167,6 +1270,11 @@ static int do_move_page_to_node_array(struct mm_struct *mm, !migrate_all) goto put_and_set; + if (PageHuge(page)) { + isolate_huge_page(page, &pagelist); + goto put_and_set; + } + err = isolate_lru_page(page); if (!err) { list_add_tail(&page->lru, &pagelist); @@ -1186,11 +1294,10 @@ set_status: err = 0; if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_page_node, - (unsigned long)pm, 0, MIGRATE_SYNC, - MR_SYSCALL); + err = migrate_pages(&pagelist, new_page_node, NULL, + (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); if (err) - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); } up_read(&mm->mmap_sem); @@ -1312,7 +1419,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, err = -ENOENT; /* Use PageReserved to check for zero page */ - if (!page || PageReserved(page) || PageKsm(page)) + if (!page || PageReserved(page)) goto set_status; err = page_to_nid(page); @@ -1459,7 +1566,7 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, * pages. Currently it only checks the watermarks which crude */ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, - int nr_migrate_pages) + unsigned long nr_migrate_pages) { int z; for (z = pgdat->nr_zones - 1; z >= 0; z--) { @@ -1468,7 +1575,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable) + if (!zone_reclaimable(zone)) continue; /* Avoid waking kswapd by allocating pages_to_migrate pages. */ @@ -1490,12 +1597,10 @@ static struct page *alloc_misplaced_dst_page(struct page *page, struct page *newpage; newpage = alloc_pages_exact_node(nid, - (GFP_HIGHUSER_MOVABLE | GFP_THISNODE | - __GFP_NOMEMALLOC | __GFP_NORETRY | - __GFP_NOWARN) & + (GFP_HIGHUSER_MOVABLE | + __GFP_THISNODE | __GFP_NOMEMALLOC | + __GFP_NORETRY | __GFP_NOWARN) & ~GFP_IOFS, 0); - if (newpage) - page_xchg_last_nid(newpage, page_last_nid(page)); return newpage; } @@ -1529,65 +1634,85 @@ bool migrate_ratelimited(int node) } /* Returns true if the node is migrate rate-limited after the update */ -bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages) +static bool numamigrate_update_ratelimit(pg_data_t *pgdat, + unsigned long nr_pages) { - bool rate_limited = false; - /* * Rate-limit the amount of data that is being migrated to a node. * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! */ - spin_lock(&pgdat->numabalancing_migrate_lock); if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) { + spin_lock(&pgdat->numabalancing_migrate_lock); pgdat->numabalancing_migrate_nr_pages = 0; pgdat->numabalancing_migrate_next_window = jiffies + msecs_to_jiffies(migrate_interval_millisecs); + spin_unlock(&pgdat->numabalancing_migrate_lock); } - if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) - rate_limited = true; - else - pgdat->numabalancing_migrate_nr_pages += nr_pages; - spin_unlock(&pgdat->numabalancing_migrate_lock); - - return rate_limited; + if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { + trace_mm_numa_migrate_ratelimit(current, pgdat->node_id, + nr_pages); + return true; + } + + /* + * This is an unlocked non-atomic update so errors are possible. + * The consequences are failing to migrate when we potentiall should + * have which is not severe enough to warrant locking. If it is ever + * a problem, it can be converted to a per-cpu counter. + */ + pgdat->numabalancing_migrate_nr_pages += nr_pages; + return false; } -int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) +static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { - int ret = 0; + int page_lru; + + VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); /* Avoid migrating to a node that is nearly full */ - if (migrate_balanced_pgdat(pgdat, 1)) { - int page_lru; + if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page))) + return 0; - if (isolate_lru_page(page)) { - put_page(page); - return 0; - } + if (isolate_lru_page(page)) + return 0; - /* Page is isolated */ - ret = 1; - page_lru = page_is_file_cache(page); - if (!PageTransHuge(page)) - inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru); - else - mod_zone_page_state(page_zone(page), - NR_ISOLATED_ANON + page_lru, - HPAGE_PMD_NR); + /* + * migrate_misplaced_transhuge_page() skips page migration's usual + * check on page_count(), so we must do it here, now that the page + * has been isolated: a GUP pin, or any other pin, prevents migration. + * The expected page count is 3: 1 for page's mapcount and 1 for the + * caller's pin and 1 for the reference taken by isolate_lru_page(). + */ + if (PageTransHuge(page) && page_count(page) != 3) { + putback_lru_page(page); + return 0; } + page_lru = page_is_file_cache(page); + mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, + hpage_nr_pages(page)); + /* - * Page is either isolated or there is not enough space on the target - * node. If isolated, then it has taken a reference count and the - * callers reference can be safely dropped without the page - * disappearing underneath us during migration. Otherwise the page is - * not to be migrated but the callers reference should still be - * dropped so it does not leak. + * Isolating the page has taken another reference, so the + * caller's reference can be safely dropped without the page + * disappearing underneath us during migration. */ put_page(page); + return 1; +} - return ret; +bool pmd_trans_migrating(pmd_t pmd) +{ + struct page *page = pmd_page(pmd); + return PageLocked(page); +} + +void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd) +{ + struct page *page = pmd_page(*pmd); + wait_on_page_locked(page); } /* @@ -1595,72 +1720,77 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) * node. Caller is expected to have an elevated reference count on * the page that will be dropped by this function before returning. */ -int migrate_misplaced_page(struct page *page, int node) +int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, + int node) { pg_data_t *pgdat = NODE_DATA(node); - int isolated = 0; + int isolated; int nr_remaining; LIST_HEAD(migratepages); /* - * Don't migrate pages that are mapped in multiple processes. - * TODO: Handle false sharing detection instead of this hammer + * Don't migrate file pages that are mapped in multiple processes + * with execute permissions as they are probably shared libraries. */ - if (page_mapcount(page) != 1) { - put_page(page); + if (page_mapcount(page) != 1 && page_is_file_cache(page) && + (vma->vm_flags & VM_EXEC)) goto out; - } /* * Rate-limit the amount of data that is being migrated to a node. * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! */ - if (numamigrate_update_ratelimit(pgdat, 1)) { - put_page(page); + if (numamigrate_update_ratelimit(pgdat, 1)) goto out; - } isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, - alloc_misplaced_dst_page, - node, false, MIGRATE_ASYNC, - MR_NUMA_MISPLACED); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); if (nr_remaining) { - putback_lru_pages(&migratepages); + if (!list_empty(&migratepages)) { + list_del(&page->lru); + dec_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + putback_lru_page(page); + } isolated = 0; } else count_vm_numa_event(NUMA_PAGE_MIGRATE); BUG_ON(!list_empty(&migratepages)); -out: return isolated; + +out: + put_page(page); + return 0; } #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +/* + * Migrates a THP to a given target node. page must be locked and is unlocked + * before returning. + */ int migrate_misplaced_transhuge_page(struct mm_struct *mm, struct vm_area_struct *vma, pmd_t *pmd, pmd_t entry, unsigned long address, struct page *page, int node) { - unsigned long haddr = address & HPAGE_PMD_MASK; + spinlock_t *ptl; pg_data_t *pgdat = NODE_DATA(node); int isolated = 0; struct page *new_page = NULL; struct mem_cgroup *memcg = NULL; int page_lru = page_is_file_cache(page); - - /* - * Don't migrate pages that are mapped in multiple processes. - * TODO: Handle false sharing detection instead of this hammer - */ - if (page_mapcount(page) != 1) - goto out_dropref; + unsigned long mmun_start = address & HPAGE_PMD_MASK; + unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; + pmd_t orig_entry; /* * Rate-limit the amount of data that is being migrated to a node. @@ -1671,32 +1801,20 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, goto out_dropref; new_page = alloc_pages_node(node, - (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER); - if (!new_page) { - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); - goto out_dropref; - } - page_xchg_last_nid(new_page, page_last_nid(page)); + (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT, + HPAGE_PMD_ORDER); + if (!new_page) + goto out_fail; isolated = numamigrate_isolate_page(pgdat, page); - - /* - * Failing to isolate or a GUP pin prevents migration. The expected - * page count is 2. 1 for anonymous pages without a mapping and 1 - * for the callers pin. If the page was isolated, the page will - * need to be put back on the LRU. - */ - if (!isolated || page_count(page) != 2) { - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); + if (!isolated) { put_page(new_page); - if (isolated) { - putback_lru_page(page); - isolated = 0; - goto out; - } - goto out_keep_locked; + goto out_fail; } + if (mm_tlb_flush_pending(mm)) + flush_tlb_range(vma, mmun_start, mmun_end); + /* Prepare a page as a migration target */ __set_page_locked(new_page); SetPageSwapBacked(new_page); @@ -1708,9 +1826,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, WARN_ON(PageLRU(new_page)); /* Recheck the target PMD */ - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(*pmd, entry))) { - spin_unlock(&mm->page_table_lock); + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + ptl = pmd_lock(mm, pmd); + if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) { +fail_putback: + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); /* Reverse changes made by migrate_page_copy() */ if (TestClearPageActive(new_page)) @@ -1722,11 +1843,13 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, unlock_page(new_page); put_page(new_page); /* Free it */ - unlock_page(page); + /* Retake the callers reference and putback on LRU */ + get_page(page); putback_lru_page(page); + mod_zone_page_state(page_zone(page), + NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); - goto out; + goto out_unlock; } /* @@ -1738,23 +1861,47 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, */ mem_cgroup_prepare_migration(page, new_page, &memcg); + orig_entry = *pmd; entry = mk_pmd(new_page, vma->vm_page_prot); - entry = pmd_mknonnuma(entry); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); entry = pmd_mkhuge(entry); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(new_page, vma, haddr); - - set_pmd_at(mm, haddr, pmd, entry); + /* + * Clear the old entry under pagetable lock and establish the new PTE. + * Any parallel GUP will either observe the old page blocking on the + * page lock, block on the page table lock or observe the new page. + * The SetPageUptodate on the new page and page_add_new_anon_rmap + * guarantee the copy is visible before the pagetable update. + */ + flush_cache_range(vma, mmun_start, mmun_end); + page_add_anon_rmap(new_page, vma, mmun_start); + pmdp_clear_flush(vma, mmun_start, pmd); + set_pmd_at(mm, mmun_start, pmd, entry); + flush_tlb_range(vma, mmun_start, mmun_end); update_mmu_cache_pmd(vma, address, &entry); + + if (page_count(page) != 2) { + set_pmd_at(mm, mmun_start, pmd, orig_entry); + flush_tlb_range(vma, mmun_start, mmun_end); + update_mmu_cache_pmd(vma, address, &entry); + page_remove_rmap(new_page); + goto fail_putback; + } + page_remove_rmap(page); + /* * Finish the charge transaction under the page table lock to * prevent split_huge_page() from dividing up the charge * before it's fully transferred to the new page. */ mem_cgroup_end_migration(memcg, page, new_page, true); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + + /* Take an "isolate" reference and put new page on the LRU. */ + get_page(new_page); + putback_lru_page(new_page); unlock_page(new_page); unlock_page(page); @@ -1764,15 +1911,25 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); -out: mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); return isolated; +out_fail: + count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); out_dropref: + ptl = pmd_lock(mm, pmd); + if (pmd_same(*pmd, entry)) { + entry = pmd_mknonnuma(entry); + set_pmd_at(mm, mmun_start, pmd, entry); + update_mmu_cache_pmd(vma, address, &entry); + } + spin_unlock(ptl); + +out_unlock: + unlock_page(page); put_page(page); -out_keep_locked: return 0; } #endif /* CONFIG_NUMA_BALANCING */ diff --git a/mm/mincore.c b/mm/mincore.c index 936b4cee8cb..725c8096104 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * any other file mapping (ie. marked !present and faulted in with * tmpfs's .fault). So swapped out tmpfs mappings are tested here. */ - page = find_get_page(mapping, pgoff); #ifdef CONFIG_SWAP - /* shmem/tmpfs may return swap: account for swapcache page too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - page = find_get_page(&swapper_space, swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + /* + * shmem/tmpfs may return swap: account for swapcache + * page too. + */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif if (page) { present = PageUptodate(page); @@ -135,7 +143,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } else { #ifdef CONFIG_SWAP pgoff = entry.val; - *vec = mincore_page(&swapper_space, pgoff); + *vec = mincore_page(swap_address_space(entry), + pgoff); #else WARN_ON(1); *vec = 1; @@ -224,13 +233,6 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v end = min(vma->vm_end, addr + (pages << PAGE_SHIFT)); - if (is_vm_hugetlb_page(vma)) { - mincore_hugetlb_page_range(vma, addr, end, vec); - return (end - addr) >> PAGE_SHIFT; - } - - end = pmd_addr_end(addr, end); - if (is_vm_hugetlb_page(vma)) mincore_hugetlb_page_range(vma, addr, end, vec); else diff --git a/mm/mlock.c b/mm/mlock.c index f0b9ce572fc..b1eb5363400 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -11,6 +11,7 @@ #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> +#include <linux/pagevec.h> #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> @@ -18,6 +19,8 @@ #include <linux/rmap.h> #include <linux/mmzone.h> #include <linux/hugetlb.h> +#include <linux/memcontrol.h> +#include <linux/mm_inline.h> #include "internal.h" @@ -76,6 +79,7 @@ void clear_page_mlock(struct page *page) */ void mlock_vma_page(struct page *page) { + /* Serialize with page migration */ BUG_ON(!PageLocked(page)); if (!TestSetPageMlocked(page)) { @@ -87,9 +91,73 @@ void mlock_vma_page(struct page *page) } } +/* + * Isolate a page from LRU with optional get_page() pin. + * Assumes lru_lock already held and page already pinned. + */ +static bool __munlock_isolate_lru_page(struct page *page, bool getpage) +{ + if (PageLRU(page)) { + struct lruvec *lruvec; + + lruvec = mem_cgroup_page_lruvec(page, page_zone(page)); + if (getpage) + get_page(page); + ClearPageLRU(page); + del_page_from_lru_list(page, lruvec, page_lru(page)); + return true; + } + + return false; +} + +/* + * Finish munlock after successful page isolation + * + * Page must be locked. This is a wrapper for try_to_munlock() + * and putback_lru_page() with munlock accounting. + */ +static void __munlock_isolated_page(struct page *page) +{ + int ret = SWAP_AGAIN; + + /* + * Optimization: if the page was mapped just once, that's our mapping + * and we don't need to check all the other vmas. + */ + if (page_mapcount(page) > 1) + ret = try_to_munlock(page); + + /* Did try_to_unlock() succeed or punt? */ + if (ret != SWAP_MLOCK) + count_vm_event(UNEVICTABLE_PGMUNLOCKED); + + putback_lru_page(page); +} + +/* + * Accounting for page isolation fail during munlock + * + * Performs accounting when page isolation fails in munlock. There is nothing + * else to do because it means some other task has already removed the page + * from the LRU. putback_lru_page() will take care of removing the page from + * the unevictable list, if necessary. vmscan [page_referenced()] will move + * the page back to the unevictable list if some other vma has it mlocked. + */ +static void __munlock_isolation_failed(struct page *page) +{ + if (PageUnevictable(page)) + __count_vm_event(UNEVICTABLE_PGSTRANDED); + else + __count_vm_event(UNEVICTABLE_PGMUNLOCKED); +} + /** * munlock_vma_page - munlock a vma page - * @page - page to be unlocked + * @page - page to be unlocked, either a normal page or THP page head + * + * returns the size of the page as a page mask (0 for normal page, + * HPAGE_PMD_NR - 1 for THP head page) * * called from munlock()/munmap() path with page supposedly on the LRU. * When we munlock a page, because the vma where we found the page is being @@ -102,45 +170,39 @@ void mlock_vma_page(struct page *page) * can't isolate the page, we leave it for putback_lru_page() and vmscan * [page_referenced()/try_to_unmap()] to deal with. */ -void munlock_vma_page(struct page *page) +unsigned int munlock_vma_page(struct page *page) { + unsigned int nr_pages; + struct zone *zone = page_zone(page); + + /* For try_to_munlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); - if (TestClearPageMlocked(page)) { - mod_zone_page_state(page_zone(page), NR_MLOCK, - -hpage_nr_pages(page)); - if (!isolate_lru_page(page)) { - int ret = SWAP_AGAIN; + /* + * Serialize with any parallel __split_huge_page_refcount() which + * might otherwise copy PageMlocked to part of the tail pages before + * we clear it in the head page. It also stabilizes hpage_nr_pages(). + */ + spin_lock_irq(&zone->lru_lock); - /* - * Optimization: if the page was mapped just once, - * that's our mapping and we don't need to check all the - * other vmas. - */ - if (page_mapcount(page) > 1) - ret = try_to_munlock(page); - /* - * did try_to_unlock() succeed or punt? - */ - if (ret != SWAP_MLOCK) - count_vm_event(UNEVICTABLE_PGMUNLOCKED); + nr_pages = hpage_nr_pages(page); + if (!TestClearPageMlocked(page)) + goto unlock_out; - putback_lru_page(page); - } else { - /* - * Some other task has removed the page from the LRU. - * putback_lru_page() will take care of removing the - * page from the unevictable list, if necessary. - * vmscan [page_referenced()] will move the page back - * to the unevictable list if some other vma has it - * mlocked. - */ - if (PageUnevictable(page)) - count_vm_event(UNEVICTABLE_PGSTRANDED); - else - count_vm_event(UNEVICTABLE_PGMUNLOCKED); - } + __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); + + if (__munlock_isolate_lru_page(page, true)) { + spin_unlock_irq(&zone->lru_lock); + __munlock_isolated_page(page); + goto out; } + __munlock_isolation_failed(page); + +unlock_out: + spin_unlock_irq(&zone->lru_lock); + +out: + return nr_pages - 1; } /** @@ -155,13 +217,11 @@ void munlock_vma_page(struct page *page) * * vma->vm_mm->mmap_sem must be held for at least read. */ -static long __mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - int *nonblocking) +long __mlock_vma_pages_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *nonblocking) { struct mm_struct *mm = vma->vm_mm; - unsigned long addr = start; - int nr_pages = (end - start) / PAGE_SIZE; + unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; VM_BUG_ON(start & ~PAGE_MASK); @@ -186,7 +246,11 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma, if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) gup_flags |= FOLL_FORCE; - return __get_user_pages(current, mm, addr, nr_pages, gup_flags, + /* + * We made sure addr is within a VMA, so the following will + * not result in a stack expansion that recurses back here. + */ + return __get_user_pages(current, mm, start, nr_pages, gup_flags, NULL, NULL, nonblocking); } @@ -202,54 +266,188 @@ static int __mlock_posix_error_return(long retval) return retval; } -/** - * mlock_vma_pages_range() - mlock pages in specified vma range. - * @vma - the vma containing the specfied address range - * @start - starting address in @vma to mlock - * @end - end address [+1] in @vma to mlock - * - * For mmap()/mremap()/expansion of mlocked vma. +/* + * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec() * - * return 0 on success for "normal" vmas. + * The fast path is available only for evictable pages with single mapping. + * Then we can bypass the per-cpu pvec and get better performance. + * when mapcount > 1 we need try_to_munlock() which can fail. + * when !page_evictable(), we need the full redo logic of putback_lru_page to + * avoid leaving evictable page in unevictable list. * - * return number of pages [> 0] to be removed from locked_vm on success - * of "special" vmas. + * In case of success, @page is added to @pvec and @pgrescued is incremented + * in case that the page was previously unevictable. @page is also unlocked. */ -long mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) +static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec, + int *pgrescued) { - int nr_pages = (end - start) / PAGE_SIZE; - BUG_ON(!(vma->vm_flags & VM_LOCKED)); + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + + if (page_mapcount(page) <= 1 && page_evictable(page)) { + pagevec_add(pvec, page); + if (TestClearPageUnevictable(page)) + (*pgrescued)++; + unlock_page(page); + return true; + } + + return false; +} +/* + * Putback multiple evictable pages to the LRU + * + * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of + * the pages might have meanwhile become unevictable but that is OK. + */ +static void __putback_lru_fast(struct pagevec *pvec, int pgrescued) +{ + count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec)); /* - * filter unlockable vmas + *__pagevec_lru_add() calls release_pages() so we don't call + * put_page() explicitly */ - if (vma->vm_flags & (VM_IO | VM_PFNMAP)) - goto no_mlock; + __pagevec_lru_add(pvec); + count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); +} - if (!((vma->vm_flags & VM_DONTEXPAND) || - is_vm_hugetlb_page(vma) || - vma == get_gate_vma(current->mm))) { +/* + * Munlock a batch of pages from the same zone + * + * The work is split to two main phases. First phase clears the Mlocked flag + * and attempts to isolate the pages, all under a single zone lru lock. + * The second phase finishes the munlock only for pages where isolation + * succeeded. + * + * Note that the pagevec may be modified during the process. + */ +static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) +{ + int i; + int nr = pagevec_count(pvec); + int delta_munlocked; + struct pagevec pvec_putback; + int pgrescued = 0; - __mlock_vma_pages_range(vma, start, end, NULL); + pagevec_init(&pvec_putback, 0); - /* Hide errors from mmap() and other callers */ - return 0; + /* Phase 1: page isolation */ + spin_lock_irq(&zone->lru_lock); + for (i = 0; i < nr; i++) { + struct page *page = pvec->pages[i]; + + if (TestClearPageMlocked(page)) { + /* + * We already have pin from follow_page_mask() + * so we can spare the get_page() here. + */ + if (__munlock_isolate_lru_page(page, false)) + continue; + else + __munlock_isolation_failed(page); + } + + /* + * We won't be munlocking this page in the next phase + * but we still need to release the follow_page_mask() + * pin. We cannot do it under lru_lock however. If it's + * the last pin, __page_cache_release() would deadlock. + */ + pagevec_add(&pvec_putback, pvec->pages[i]); + pvec->pages[i] = NULL; } + delta_munlocked = -nr + pagevec_count(&pvec_putback); + __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); + spin_unlock_irq(&zone->lru_lock); + + /* Now we can release pins of pages that we are not munlocking */ + pagevec_release(&pvec_putback); + + /* Phase 2: page munlock */ + for (i = 0; i < nr; i++) { + struct page *page = pvec->pages[i]; + + if (page) { + lock_page(page); + if (!__putback_lru_fast_prepare(page, &pvec_putback, + &pgrescued)) { + /* + * Slow path. We don't want to lose the last + * pin before unlock_page() + */ + get_page(page); /* for putback_lru_page() */ + __munlock_isolated_page(page); + unlock_page(page); + put_page(page); /* from follow_page_mask() */ + } + } + } + + /* + * Phase 3: page putback for pages that qualified for the fast path + * This will also call put_page() to return pin from follow_page_mask() + */ + if (pagevec_count(&pvec_putback)) + __putback_lru_fast(&pvec_putback, pgrescued); +} + +/* + * Fill up pagevec for __munlock_pagevec using pte walk + * + * The function expects that the struct page corresponding to @start address is + * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone. + * + * The rest of @pvec is filled by subsequent pages within the same pmd and same + * zone, as long as the pte's are present and vm_normal_page() succeeds. These + * pages also get pinned. + * + * Returns the address of the next page that should be scanned. This equals + * @start + PAGE_SIZE when no page could be added by the pte walk. + */ +static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, + struct vm_area_struct *vma, int zoneid, unsigned long start, + unsigned long end) +{ + pte_t *pte; + spinlock_t *ptl; /* - * User mapped kernel pages or huge pages: - * make these pages present to populate the ptes, but - * fall thru' to reset VM_LOCKED--no need to unlock, and - * return nr_pages so these don't get counted against task's - * locked limit. huge pages are already counted against - * locked vm limit. + * Initialize pte walk starting at the already pinned page where we + * are sure that there is a pte, as it was pinned under the same + * mmap_sem write op. */ - make_pages_present(start, end); + pte = get_locked_pte(vma->vm_mm, start, &ptl); + /* Make sure we do not cross the page table boundary */ + end = pgd_addr_end(start, end); + end = pud_addr_end(start, end); + end = pmd_addr_end(start, end); + + /* The page next to the pinned page is the first we will try to get */ + start += PAGE_SIZE; + while (start < end) { + struct page *page = NULL; + pte++; + if (pte_present(*pte)) + page = vm_normal_page(vma, start, *pte); + /* + * Break if page could not be obtained or the page's node+zone does not + * match + */ + if (!page || page_zone_id(page) != zoneid) + break; -no_mlock: - vma->vm_flags &= ~VM_LOCKED; /* and don't come back! */ - return nr_pages; /* error or pages NOT mlocked */ + get_page(page); + /* + * Increase the address that will be returned *before* the + * eventual break due to pvec becoming full by adding the page + */ + start += PAGE_SIZE; + if (pagevec_add(pvec, page) == 0) + break; + } + pte_unmap_unlock(pte, ptl); + return start; } /* @@ -273,13 +471,17 @@ no_mlock: void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - unsigned long addr; - - lru_add_drain(); vma->vm_flags &= ~VM_LOCKED; - for (addr = start; addr < end; addr += PAGE_SIZE) { - struct page *page; + while (start < end) { + struct page *page = NULL; + unsigned int page_mask; + unsigned long page_increm; + struct pagevec pvec; + struct zone *zone; + int zoneid; + + pagevec_init(&pvec, 0); /* * Although FOLL_DUMP is intended for get_dump_page(), * it just so happens that its special treatment of the @@ -287,13 +489,48 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, * suits munlock very well (and if somehow an abnormal page * has sneaked into the range, we won't oops here: great). */ - page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); + page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP, + &page_mask); + if (page && !IS_ERR(page)) { - lock_page(page); - munlock_vma_page(page); - unlock_page(page); - put_page(page); + if (PageTransHuge(page)) { + lock_page(page); + /* + * Any THP page found by follow_page_mask() may + * have gotten split before reaching + * munlock_vma_page(), so we need to recompute + * the page_mask here. + */ + page_mask = munlock_vma_page(page); + unlock_page(page); + put_page(page); /* follow_page_mask() */ + } else { + /* + * Non-huge pages are handled in batches via + * pagevec. The pin from follow_page_mask() + * prevents them from collapsing by THP. + */ + pagevec_add(&pvec, page); + zone = page_zone(page); + zoneid = page_zone_id(page); + + /* + * Try to fill the rest of pagevec using fast + * pte walk. This will also update start to + * the next page to process. Then munlock the + * pagevec. + */ + start = __munlock_pagevec_fill(&pvec, vma, + zoneid, start, end); + __munlock_pagevec(&pvec, zone); + goto next; + } } + /* It's a bug to munlock in the middle of a THP page */ + VM_BUG_ON((start >> PAGE_SHIFT) & page_mask); + page_increm = 1 + page_mask; + start += page_increm * PAGE_SIZE; +next: cond_resched(); } } @@ -303,7 +540,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, * * Filters out "special" vmas -- VM_LOCKED never gets set for these, and * munlock is a no-op. However, for some special vmas, we go ahead and - * populate the ptes via make_pages_present(). + * populate the ptes. * * For vmas that pass the filters, merge/split as appropriate. */ @@ -391,9 +628,9 @@ static int do_mlock(unsigned long start, size_t len, int on) /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ - newflags = vma->vm_flags | VM_LOCKED; - if (!on) - newflags &= ~VM_LOCKED; + newflags = vma->vm_flags & ~VM_LOCKED; + if (on) + newflags |= VM_LOCKED; tmp = vma->vm_end; if (tmp > end) @@ -416,13 +653,20 @@ static int do_mlock(unsigned long start, size_t len, int on) return error; } -static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors) +/* + * __mm_populate - populate and/or mlock pages within a range of address space. + * + * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap + * flags. VMAs must be already marked with the desired vm_flags, and + * mmap_sem must not be held. + */ +int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) { struct mm_struct *mm = current->mm; unsigned long end, nstart, nend; struct vm_area_struct *vma = NULL; int locked = 0; - int ret = 0; + long ret = 0; VM_BUG_ON(start & ~PAGE_MASK); VM_BUG_ON(len != PAGE_ALIGN(len)); @@ -483,22 +727,24 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) lru_add_drain_all(); /* flush pagevec */ - down_write(¤t->mm->mmap_sem); len = PAGE_ALIGN(len + (start & ~PAGE_MASK)); start &= PAGE_MASK; - locked = len >> PAGE_SHIFT; - locked += current->mm->locked_vm; - lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; + locked = len >> PAGE_SHIFT; + + down_write(¤t->mm->mmap_sem); + + locked += current->mm->locked_vm; /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = do_mlock(start, len, 1); + up_write(¤t->mm->mmap_sem); if (!error) - error = do_mlock_pages(start, len, 0); + error = __mm_populate(start, len, 0); return error; } @@ -506,34 +752,37 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; - down_write(¤t->mm->mmap_sem); len = PAGE_ALIGN(len + (start & ~PAGE_MASK)); start &= PAGE_MASK; + + down_write(¤t->mm->mmap_sem); ret = do_mlock(start, len, 0); up_write(¤t->mm->mmap_sem); + return ret; } static int do_mlockall(int flags) { struct vm_area_struct * vma, * prev = NULL; - unsigned int def_flags = 0; if (flags & MCL_FUTURE) - def_flags = VM_LOCKED; - current->mm->def_flags = def_flags; + current->mm->def_flags |= VM_LOCKED; + else + current->mm->def_flags &= ~VM_LOCKED; if (flags == MCL_FUTURE) goto out; for (vma = current->mm->mmap; vma ; vma = prev->vm_next) { vm_flags_t newflags; - newflags = vma->vm_flags | VM_LOCKED; - if (!(flags & MCL_CURRENT)) - newflags &= ~VM_LOCKED; + newflags = vma->vm_flags & ~VM_LOCKED; + if (flags & MCL_CURRENT) + newflags |= VM_LOCKED; /* Ignore errors */ mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); + cond_resched(); } out: return 0; @@ -554,20 +803,18 @@ SYSCALL_DEFINE1(mlockall, int, flags) if (flags & MCL_CURRENT) lru_add_drain_all(); /* flush pagevec */ - down_write(¤t->mm->mmap_sem); - lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; ret = -ENOMEM; + down_write(¤t->mm->mmap_sem); + if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = do_mlockall(flags); up_write(¤t->mm->mmap_sem); - if (!ret && (flags & MCL_CURRENT)) { - /* Ignore errors */ - do_mlock_pages(0, TASK_SIZE, 1); - } + if (!ret && (flags & MCL_CURRENT)) + mm_populate(0, TASK_SIZE); out: return ret; } diff --git a/mm/mm_init.c b/mm/mm_init.c index 1ffd97ae26d..4074caf9936 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -9,6 +9,8 @@ #include <linux/init.h> #include <linux/kobject.h> #include <linux/export.h> +#include <linux/memory.h> +#include <linux/notifier.h> #include "internal.h" #ifdef CONFIG_DEBUG_MEMORY_INIT @@ -69,34 +71,41 @@ void __init mminit_verify_pageflags_layout(void) unsigned long or_mask, add_mask; shift = 8 * sizeof(unsigned long); - width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH; + width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_CPUPID_SHIFT; mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths", - "Section %d Node %d Zone %d Flags %d\n", + "Section %d Node %d Zone %d Lastcpupid %d Flags %d\n", SECTIONS_WIDTH, NODES_WIDTH, ZONES_WIDTH, + LAST_CPUPID_WIDTH, NR_PAGEFLAGS); mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts", - "Section %d Node %d Zone %d\n", + "Section %d Node %d Zone %d Lastcpupid %d\n", SECTIONS_SHIFT, NODES_SHIFT, - ZONES_SHIFT); - mminit_dprintk(MMINIT_TRACE, "pageflags_layout_offsets", - "Section %lu Node %lu Zone %lu\n", + ZONES_SHIFT, + LAST_CPUPID_SHIFT); + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts", + "Section %lu Node %lu Zone %lu Lastcpupid %lu\n", (unsigned long)SECTIONS_PGSHIFT, (unsigned long)NODES_PGSHIFT, - (unsigned long)ZONES_PGSHIFT); - mminit_dprintk(MMINIT_TRACE, "pageflags_layout_zoneid", - "Zone ID: %lu -> %lu\n", - (unsigned long)ZONEID_PGOFF, - (unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT)); + (unsigned long)ZONES_PGSHIFT, + (unsigned long)LAST_CPUPID_PGSHIFT); + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid", + "Node/Zone ID: %lu -> %lu\n", + (unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT), + (unsigned long)ZONEID_PGOFF); mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage", - "location: %d -> %d unused %d -> %d flags %d -> %d\n", + "location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n", shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0); #ifdef NODE_NOT_IN_PAGE_FLAGS mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags", "Node not in page flags"); #endif +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags", + "Last cpupid not in page flags"); +#endif if (SECTIONS_WIDTH) { shift -= SECTIONS_WIDTH; @@ -140,6 +149,51 @@ early_param("mminit_loglevel", set_mminit_loglevel); struct kobject *mm_kobj; EXPORT_SYMBOL_GPL(mm_kobj); +#ifdef CONFIG_SMP +s32 vm_committed_as_batch = 32; + +static void __meminit mm_compute_batch(void) +{ + u64 memsized_batch; + s32 nr = num_present_cpus(); + s32 batch = max_t(s32, nr*2, 32); + + /* batch size set to 0.4% of (total memory/#cpus), or max int32 */ + memsized_batch = min_t(u64, (totalram_pages/nr)/256, 0x7fffffff); + + vm_committed_as_batch = max_t(s32, memsized_batch, batch); +} + +static int __meminit mm_compute_batch_notifier(struct notifier_block *self, + unsigned long action, void *arg) +{ + switch (action) { + case MEM_ONLINE: + case MEM_OFFLINE: + mm_compute_batch(); + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block compute_batch_nb __meminitdata = { + .notifier_call = mm_compute_batch_notifier, + .priority = IPC_CALLBACK_PRI, /* use lowest priority */ +}; + +static int __init mm_compute_batch_init(void) +{ + mm_compute_batch(); + register_hotmemory_notifier(&compute_batch_nb); + + return 0; +} + +__initcall(mm_compute_batch_init); + +#endif + static int __init mm_sysfs_init(void) { mm_kobj = kobject_create_and_add("mm", kernel_kobj); @@ -148,5 +202,4 @@ static int __init mm_sysfs_init(void) return 0; } - -__initcall(mm_sysfs_init); +postcore_initcall(mm_sysfs_init); diff --git a/mm/mmap.c b/mm/mmap.c index 35730ee9d51..129b847d30c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -6,9 +6,13 @@ * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> @@ -32,6 +36,10 @@ #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/rbtree_augmented.h> +#include <linux/sched/sysctl.h> +#include <linux/notifier.h> +#include <linux/memory.h> +#include <linux/printk.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -82,7 +90,10 @@ EXPORT_SYMBOL(vm_get_page_prot); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio __read_mostly = 50; /* default is 50% */ +unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; +unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ +unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ /* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. @@ -121,7 +132,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed; + unsigned long free, allowed, reserve; vm_acct_memory(pages); @@ -143,7 +154,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ free -= global_page_state(NR_SHMEM); - free += nr_swap_pages; + free += get_nr_swap_pages(); /* * Any slabs which are created with the @@ -162,10 +173,10 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) free -= totalreserve_pages; /* - * Leave the last 3% for root + * Reserve some for root */ if (!cap_sys_admin) - free -= free / 32; + free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); if (free > pages) return 0; @@ -173,19 +184,20 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) goto error; } - allowed = (totalram_pages - hugetlb_total_pages()) - * sysctl_overcommit_ratio / 100; + allowed = vm_commit_limit(); /* - * Leave the last 3% for root + * Reserve some for root */ if (!cap_sys_admin) - allowed -= allowed / 32; - allowed += total_swap_pages; + allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); - /* Don't let a single process grow too big: - leave 3% of the size of this process for other processes */ - if (mm) - allowed -= mm->total_vm / 32; + /* + * Don't let a single process grow so big a user can't recover + */ + if (mm) { + reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); + allowed -= min(mm->total_vm / 32, reserve); + } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; @@ -202,7 +214,7 @@ 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_path.dentry->d_inode->i_writecount); + atomic_inc(&file_inode(file)->i_writecount); if (vma->vm_flags & VM_SHARED) mapping->i_mmap_writable--; @@ -255,6 +267,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; unsigned long min_brk; + bool populate; down_write(&mm->mmap_sem); @@ -304,8 +317,15 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* Ok, looks good - let it rip. */ if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk) goto out; + set_brk: mm->brk = brk; + populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; + up_write(&mm->mmap_sem); + if (populate) + mm_populate(oldbrk, newbrk - oldbrk); + return brk; + out: retval = mm->brk; up_write(&mm->mmap_sem); @@ -344,20 +364,20 @@ static int browse_rb(struct rb_root *root) struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); if (vma->vm_start < prev) { - printk("vm_start %lx prev %lx\n", vma->vm_start, prev); + pr_info("vm_start %lx prev %lx\n", vma->vm_start, prev); bug = 1; } if (vma->vm_start < pend) { - printk("vm_start %lx pend %lx\n", vma->vm_start, pend); + pr_info("vm_start %lx pend %lx\n", vma->vm_start, pend); bug = 1; } if (vma->vm_start > vma->vm_end) { - printk("vm_end %lx < vm_start %lx\n", + pr_info("vm_end %lx < vm_start %lx\n", vma->vm_end, vma->vm_start); bug = 1; } if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) { - printk("free gap %lx, correct %lx\n", + pr_info("free gap %lx, correct %lx\n", vma->rb_subtree_gap, vma_compute_subtree_gap(vma)); bug = 1; @@ -371,7 +391,7 @@ static int browse_rb(struct rb_root *root) for (nd = pn; nd; nd = rb_prev(nd)) j++; if (i != j) { - printk("backwards %d, forwards %d\n", j, i); + pr_info("backwards %d, forwards %d\n", j, i); bug = 1; } return bug ? -1 : i; @@ -389,7 +409,7 @@ static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore) } } -void validate_mm(struct mm_struct *mm) +static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; @@ -406,17 +426,17 @@ void validate_mm(struct mm_struct *mm) i++; } if (i != mm->map_count) { - printk("map_count %d vm_next %d\n", mm->map_count, i); + pr_info("map_count %d vm_next %d\n", mm->map_count, i); bug = 1; } if (highest_address != mm->highest_vm_end) { - printk("mm->highest_vm_end %lx, found %lx\n", + pr_info("mm->highest_vm_end %lx, found %lx\n", mm->highest_vm_end, highest_address); bug = 1; } i = browse_rb(&mm->mm_rb); if (i != mm->map_count) { - printk("map_count %d rb %d\n", mm->map_count, i); + pr_info("map_count %d rb %d\n", mm->map_count, i); bug = 1; } BUG_ON(bug); @@ -534,6 +554,34 @@ static int find_vma_links(struct mm_struct *mm, unsigned long addr, return 0; } +static unsigned long count_vma_pages_range(struct mm_struct *mm, + unsigned long addr, unsigned long end) +{ + unsigned long nr_pages = 0; + struct vm_area_struct *vma; + + /* Find first overlaping mapping */ + vma = find_vma_intersection(mm, addr, end); + if (!vma) + return 0; + + nr_pages = (min(end, vma->vm_end) - + max(addr, vma->vm_start)) >> PAGE_SHIFT; + + /* Iterate over the rest of the overlaps */ + for (vma = vma->vm_next; vma; vma = vma->vm_next) { + unsigned long overlap_len; + + if (vma->vm_start > end) + break; + + overlap_len = min(end, vma->vm_end) - vma->vm_start; + nr_pages += overlap_len >> PAGE_SHIFT; + } + + return nr_pages; +} + void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, struct rb_node **rb_link, struct rb_node *rb_parent) { @@ -567,7 +615,7 @@ static 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_path.dentry->d_inode->i_writecount); + atomic_dec(&file_inode(file)->i_writecount); if (vma->vm_flags & VM_SHARED) mapping->i_mmap_writable++; @@ -595,11 +643,10 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, { struct address_space *mapping = NULL; - if (vma->vm_file) + if (vma->vm_file) { mapping = vma->vm_file->f_mapping; - - if (mapping) mutex_lock(&mapping->i_mmap_mutex); + } __vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); @@ -637,8 +684,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, prev->vm_next = next = vma->vm_next; if (next) next->vm_prev = prev; - if (mm->mmap_cache == vma) - mm->mmap_cache = prev; + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -800,7 +848,7 @@ again: remove_next = 1 + (end > next->vm_end); anon_vma_interval_tree_post_update_vma(vma); if (adjust_next) anon_vma_interval_tree_post_update_vma(next); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); } if (mapping) mutex_unlock(&mapping->i_mmap_mutex); @@ -850,7 +898,15 @@ again: remove_next = 1 + (end > next->vm_end); static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags) { - if (vma->vm_flags ^ vm_flags) + /* + * VM_SOFTDIRTY should not prevent from VMA merging, if we + * match the flags but dirty bit -- the caller should mark + * merged VMA as dirty. If dirty bit won't be excluded from + * comparison, we increase pressue on the memory system forcing + * the kernel to generate new VMAs when old one could be + * extended instead. + */ + if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) return 0; if (vma->vm_file != file) return 0; @@ -910,7 +966,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, if (is_mergeable_vma(vma, file, vm_flags) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; - vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + vm_pglen = vma_pages(vma); if (vma->vm_pgoff + vm_pglen == vm_pgoff) return 1; } @@ -1039,7 +1095,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && - !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) && + !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC|VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } @@ -1147,18 +1203,38 @@ static inline unsigned long round_hint_to_min(unsigned long hint) return hint; } +static inline int mlock_future_check(struct mm_struct *mm, + unsigned long flags, + unsigned long len) +{ + unsigned long locked, lock_limit; + + /* mlock MCL_FUTURE? */ + if (flags & VM_LOCKED) { + locked = len >> PAGE_SHIFT; + locked += mm->locked_vm; + lock_limit = rlimit(RLIMIT_MEMLOCK); + lock_limit >>= PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + return -EAGAIN; + } + return 0; +} + /* * The caller must hold down_write(¤t->mm->mmap_sem). */ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, - unsigned long flags, unsigned long pgoff) + unsigned long flags, unsigned long pgoff, + unsigned long *populate) { struct mm_struct * mm = current->mm; - struct inode *inode; vm_flags_t vm_flags; + *populate = 0; + /* * Does the application expect PROT_READ to imply PROT_EXEC? * @@ -1206,20 +1282,12 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (!can_do_mlock()) return -EPERM; - /* mlock MCL_FUTURE? */ - if (vm_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = len >> PAGE_SHIFT; - locked += mm->locked_vm; - lock_limit = rlimit(RLIMIT_MEMLOCK); - lock_limit >>= PAGE_SHIFT; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - return -EAGAIN; - } - - inode = file ? file->f_path.dentry->d_inode : NULL; + if (mlock_future_check(mm, vm_flags, len)) + return -EAGAIN; if (file) { + struct inode *inode = file_inode(file); + switch (flags & MAP_TYPE) { case MAP_SHARED: if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE)) @@ -1235,7 +1303,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, /* * Make sure there are no mandatory locks on the file. */ - if (locks_verify_locked(inode)) + if (locks_verify_locked(file)) return -EAGAIN; vm_flags |= VM_SHARED | VM_MAYSHARE; @@ -1252,8 +1320,10 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, vm_flags &= ~VM_MAYEXEC; } - if (!file->f_op || !file->f_op->mmap) + if (!file->f_op->mmap) return -ENODEV; + if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) + return -EINVAL; break; default: @@ -1262,6 +1332,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, } else { switch (flags & MAP_TYPE) { case MAP_SHARED: + if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) + return -EINVAL; /* * Ignore pgoff. */ @@ -1279,7 +1351,26 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, } } - return mmap_region(file, addr, len, flags, vm_flags, pgoff); + /* + * Set 'VM_NORESERVE' if we should not account for the + * memory use of this mapping. + */ + if (flags & MAP_NORESERVE) { + /* We honor MAP_NORESERVE if allowed to overcommit */ + if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) + vm_flags |= VM_NORESERVE; + + /* hugetlb applies strict overcommit unless MAP_NORESERVE */ + if (file && is_file_hugepages(file)) + vm_flags |= VM_NORESERVE; + } + + addr = mmap_region(file, addr, len, vm_flags, pgoff); + if (!IS_ERR_VALUE(addr) && + ((vm_flags & VM_LOCKED) || + (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) + *populate = len; + return addr; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, @@ -1291,20 +1382,30 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); - if (unlikely(flags & MAP_HUGETLB)) - return -EINVAL; file = fget(fd); if (!file) goto out; + if (is_file_hugepages(file)) + len = ALIGN(len, huge_page_size(hstate_file(file))); + retval = -EINVAL; + if (unlikely(flags & MAP_HUGETLB && !is_file_hugepages(file))) + goto out_fput; } else if (flags & MAP_HUGETLB) { struct user_struct *user = NULL; + struct hstate *hs; + + hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & SHM_HUGE_MASK); + if (!hs) + return -EINVAL; + + len = ALIGN(len, huge_page_size(hs)); /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called * A dummy user value is used because we are not locking * memory so no accounting is necessary */ - file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len, + file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, &user, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); @@ -1315,6 +1416,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); +out_fput: if (file) fput(file); out: @@ -1394,16 +1496,30 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) } unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff) + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - int correct_wcount = 0; int error; struct rb_node **rb_link, *rb_parent; unsigned long charged = 0; - struct inode *inode = file ? file->f_path.dentry->d_inode : NULL; + + /* Check against address space limit. */ + if (!may_expand_vm(mm, len >> PAGE_SHIFT)) { + unsigned long nr_pages; + + /* + * MAP_FIXED may remove pages of mappings that intersects with + * requested mapping. Account for the pages it would unmap. + */ + if (!(vm_flags & MAP_FIXED)) + return -ENOMEM; + + nr_pages = count_vma_pages_range(mm, addr, addr + len); + + if (!may_expand_vm(mm, (len >> PAGE_SHIFT) - nr_pages)) + return -ENOMEM; + } /* Clear old maps */ error = -ENOMEM; @@ -1414,24 +1530,6 @@ munmap_back: goto munmap_back; } - /* Check against address space limit. */ - if (!may_expand_vm(mm, len >> PAGE_SHIFT)) - return -ENOMEM; - - /* - * Set 'VM_NORESERVE' if we should not account for the - * memory use of this mapping. - */ - if ((flags & MAP_NORESERVE)) { - /* We honor MAP_NORESERVE if allowed to overcommit */ - if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) - vm_flags |= VM_NORESERVE; - - /* hugetlb applies strict overcommit unless MAP_NORESERVE */ - if (file && is_file_hugepages(file)) - vm_flags |= VM_NORESERVE; - } - /* * Private writable mapping: check memory availability */ @@ -1468,16 +1566,11 @@ munmap_back: vma->vm_pgoff = pgoff; INIT_LIST_HEAD(&vma->anon_vma_chain); - error = -EINVAL; /* when rejecting VM_GROWSDOWN|VM_GROWSUP */ - if (file) { - if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) - goto free_vma; if (vm_flags & VM_DENYWRITE) { error = deny_write_access(file); if (error) goto free_vma; - correct_wcount = 1; } vma->vm_file = get_file(file); error = file->f_op->mmap(file, vma); @@ -1494,11 +1587,8 @@ munmap_back: WARN_ON_ONCE(addr != vma->vm_start); addr = vma->vm_start; - pgoff = vma->vm_pgoff; vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { - if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP))) - goto free_vma; error = shmem_zero_setup(vma); if (error) goto free_vma; @@ -1520,29 +1610,39 @@ munmap_back: } vma_link(mm, vma, prev, rb_link, rb_parent); - file = vma->vm_file; - /* Once vma denies write, undo our temporary denial count */ - if (correct_wcount) - atomic_inc(&inode->i_writecount); + if (vm_flags & VM_DENYWRITE) + allow_write_access(file); + file = vma->vm_file; out: perf_event_mmap(vma); vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { - if (!mlock_vma_pages_range(vma, addr, addr + len)) + if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || + vma == get_gate_vma(current->mm))) mm->locked_vm += (len >> PAGE_SHIFT); - } else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) - make_pages_present(addr, addr + len); + else + vma->vm_flags &= ~VM_LOCKED; + } if (file) uprobe_mmap(vma); + /* + * New (or expanded) vma always get soft dirty status. + * Otherwise user-space soft-dirty page tracker won't + * be able to distinguish situation when vma area unmapped, + * then new mapped in-place (which must be aimed as + * a completely new data area). + */ + vma->vm_flags |= VM_SOFTDIRTY; + return addr; unmap_and_free_vma: - if (correct_wcount) - atomic_inc(&inode->i_writecount); + if (vm_flags & VM_DENYWRITE) + allow_write_access(file); vma->vm_file = NULL; fput(file); @@ -1777,7 +1877,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct vm_area_struct *vma; struct vm_unmapped_area_info info; - if (len > TASK_SIZE) + if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) @@ -1786,29 +1886,20 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vma->vm_start)) return addr; } info.flags = 0; info.length = len; - info.low_limit = TASK_UNMAPPED_BASE; + info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; info.align_mask = 0; return vm_unmapped_area(&info); } #endif -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the lowest possible address? - */ - if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) - mm->free_area_cache = addr; -} - /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): @@ -1825,7 +1916,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct vm_unmapped_area_info info; /* requested length too big for entire address space */ - if (len > TASK_SIZE) + if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) @@ -1835,14 +1926,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vma->vm_start)) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = PAGE_SIZE; + info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = mm->mmap_base; info.align_mask = 0; addr = vm_unmapped_area(&info); @@ -1865,19 +1956,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, } #endif -void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the highest possible address? - */ - if (addr > mm->free_area_cache) - mm->free_area_cache = addr; - - /* dont allow allocations above current base */ - if (mm->free_area_cache > mm->mmap_base) - mm->free_area_cache = mm->mmap_base; -} - unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -1894,7 +1972,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, return -ENOMEM; get_area = current->mm->get_unmapped_area; - if (file && file->f_op && file->f_op->get_unmapped_area) + if (file && file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) @@ -1915,37 +1993,33 @@ EXPORT_SYMBOL(get_unmapped_area); /* 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) { - struct vm_area_struct *vma = NULL; - - if (WARN_ON_ONCE(!mm)) /* Remove this in linux-3.6 */ - return NULL; + struct rb_node *rb_node; + struct vm_area_struct *vma; /* Check the cache first. */ - /* (Cache hit rate is typically around 35%.) */ - vma = mm->mmap_cache; - if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) { - struct rb_node *rb_node; + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; - rb_node = mm->mm_rb.rb_node; - vma = NULL; + rb_node = mm->mm_rb.rb_node; + vma = NULL; - while (rb_node) { - struct vm_area_struct *vma_tmp; - - vma_tmp = rb_entry(rb_node, - struct vm_area_struct, vm_rb); - - if (vma_tmp->vm_end > addr) { - vma = vma_tmp; - if (vma_tmp->vm_start <= addr) - break; - rb_node = rb_node->rb_left; - } else - rb_node = rb_node->rb_right; - } - if (vma) - mm->mmap_cache = vma; + while (rb_node) { + struct vm_area_struct *tmp; + + tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + + if (tmp->vm_end > addr) { + vma = tmp; + if (tmp->vm_start <= addr) + break; + rb_node = rb_node->rb_left; + } else + rb_node = rb_node->rb_right; } + + if (vma) + vmacache_update(addr, vma); return vma; } @@ -2169,9 +2243,28 @@ int expand_downwards(struct vm_area_struct *vma, return error; } +/* + * Note how expand_stack() refuses to expand the stack all the way to + * abut the next virtual mapping, *unless* that mapping itself is also + * a stack mapping. We want to leave room for a guard page, after all + * (the guard page itself is not added here, that is done by the + * actual page faulting logic) + * + * This matches the behavior of the guard page logic (see mm/memory.c: + * check_stack_guard_page()), which only allows the guard page to be + * removed under these circumstances. + */ #ifdef CONFIG_STACK_GROWSUP int expand_stack(struct vm_area_struct *vma, unsigned long address) { + struct vm_area_struct *next; + + address &= PAGE_MASK; + next = vma->vm_next; + if (next && next->vm_start == address + PAGE_SIZE) { + if (!(next->vm_flags & VM_GROWSUP)) + return -ENOMEM; + } return expand_upwards(vma, address); } @@ -2186,14 +2279,21 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!prev || expand_stack(prev, addr)) return NULL; - if (prev->vm_flags & VM_LOCKED) { - mlock_vma_pages_range(prev, addr, prev->vm_end); - } + if (prev->vm_flags & VM_LOCKED) + __mlock_vma_pages_range(prev, addr, prev->vm_end, NULL); return prev; } #else int expand_stack(struct vm_area_struct *vma, unsigned long address) { + struct vm_area_struct *prev; + + address &= PAGE_MASK; + prev = vma->vm_prev; + if (prev && prev->vm_end == address) { + if (!(prev->vm_flags & VM_GROWSDOWN)) + return -ENOMEM; + } return expand_downwards(vma, address); } @@ -2214,9 +2314,8 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr) start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; - if (vma->vm_flags & VM_LOCKED) { - mlock_vma_pages_range(vma, addr, start); - } + if (vma->vm_flags & VM_LOCKED) + __mlock_vma_pages_range(vma, addr, start, NULL); return vma; } #endif @@ -2258,11 +2357,11 @@ static void unmap_region(struct mm_struct *mm, struct mmu_gather tlb; lru_add_drain(); - tlb_gather_mmu(&tlb, mm, 0); + tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, - next ? next->vm_start : 0); + next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, start, end); } @@ -2276,7 +2375,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, { struct vm_area_struct **insertion_point; struct vm_area_struct *tail_vma = NULL; - unsigned long addr; insertion_point = (prev ? &prev->vm_next : &mm->mmap); vma->vm_prev = NULL; @@ -2293,12 +2391,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - if (mm->unmap_area == arch_unmap_area) - addr = prev ? prev->vm_end : mm->mmap_base; - else - addr = vma ? vma->vm_start : mm->mmap_base; - mm->unmap_area(mm, addr); - mm->mmap_cache = NULL; /* Kill the cache. */ + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -2308,7 +2403,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, unsigned long addr, int new_below) { - struct mempolicy *pol; struct vm_area_struct *new; int err = -ENOMEM; @@ -2332,12 +2426,9 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } - pol = mpol_dup(vma_policy(vma)); - if (IS_ERR(pol)) { - err = PTR_ERR(pol); + err = vma_dup_policy(vma, new); + if (err) goto out_free_vma; - } - vma_set_policy(new, pol); if (anon_vma_clone(new, vma)) goto out_free_mpol; @@ -2365,7 +2456,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, fput(new->vm_file); unlink_anon_vmas(new); out_free_mpol: - mpol_put(pol); + mpol_put(vma_policy(new)); out_free_vma: kmem_cache_free(vm_area_cachep, new); out_err: @@ -2524,18 +2615,9 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) if (error & ~PAGE_MASK) return error; - /* - * mlock MCL_FUTURE? - */ - if (mm->def_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = len >> PAGE_SHIFT; - locked += mm->locked_vm; - lock_limit = rlimit(RLIMIT_MEMLOCK); - lock_limit >>= PAGE_SHIFT; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - return -EAGAIN; - } + error = mlock_future_check(mm, mm->def_flags, len); + if (error) + return error; /* * mm->mmap_sem is required to protect against another thread @@ -2589,10 +2671,9 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; - if (flags & VM_LOCKED) { - if (!mlock_vma_pages_range(vma, addr, addr + len)) - mm->locked_vm += (len >> PAGE_SHIFT); - } + if (flags & VM_LOCKED) + mm->locked_vm += (len >> PAGE_SHIFT); + vma->vm_flags |= VM_SOFTDIRTY; return addr; } @@ -2600,10 +2681,14 @@ unsigned long vm_brk(unsigned long addr, unsigned long len) { struct mm_struct *mm = current->mm; unsigned long ret; + bool populate; down_write(&mm->mmap_sem); ret = do_brk(addr, len); + populate = ((mm->def_flags & VM_LOCKED) != 0); up_write(&mm->mmap_sem); + if (populate) + mm_populate(addr, len); return ret; } EXPORT_SYMBOL(vm_brk); @@ -2635,12 +2720,12 @@ void exit_mmap(struct mm_struct *mm) lru_add_drain(); flush_cache_mm(mm); - tlb_gather_mmu(&tlb, mm, 1); + tlb_gather_mmu(&tlb, mm, 0, -1); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); - free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); + free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); /* @@ -2654,7 +2739,8 @@ void exit_mmap(struct mm_struct *mm) } vm_unacct_memory(nr_accounted); - WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); + WARN_ON(atomic_long_read(&mm->nr_ptes) > + (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); } /* Insert vm structure into process list sorted by address @@ -2706,7 +2792,6 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; struct rb_node **rb_link, *rb_parent; - struct mempolicy *pol; bool faulted_in_anon_vma = true; /* @@ -2751,10 +2836,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; - pol = mpol_dup(vma_policy(vma)); - if (IS_ERR(pol)) + if (vma_dup_policy(vma, new_vma)) goto out_free_vma; - vma_set_policy(new_vma, pol); INIT_LIST_HEAD(&new_vma->anon_vma_chain); if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; @@ -2769,7 +2852,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_free_mempol: - mpol_put(pol); + mpol_put(vma_policy(new_vma)); out_free_vma: kmem_cache_free(vm_area_cachep, new_vma); return NULL; @@ -2791,6 +2874,31 @@ int may_expand_vm(struct mm_struct *mm, unsigned long npages) return 1; } +static int special_mapping_fault(struct vm_area_struct *vma, + struct vm_fault *vmf); + +/* + * Having a close hook prevents vma merging regardless of flags. + */ +static void special_mapping_close(struct vm_area_struct *vma) +{ +} + +static const char *special_mapping_name(struct vm_area_struct *vma) +{ + return ((struct vm_special_mapping *)vma->vm_private_data)->name; +} + +static const struct vm_operations_struct special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, + .name = special_mapping_name, +}; + +static const struct vm_operations_struct legacy_special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, +}; static int special_mapping_fault(struct vm_area_struct *vma, struct vm_fault *vmf) @@ -2806,7 +2914,13 @@ static int special_mapping_fault(struct vm_area_struct *vma, */ pgoff = vmf->pgoff - vma->vm_pgoff; - for (pages = vma->vm_private_data; pgoff && *pages; ++pages) + if (vma->vm_ops == &legacy_special_mapping_vmops) + pages = vma->vm_private_data; + else + pages = ((struct vm_special_mapping *)vma->vm_private_data)-> + pages; + + for (; pgoff && *pages; ++pages) pgoff--; if (*pages) { @@ -2819,48 +2933,29 @@ static int special_mapping_fault(struct vm_area_struct *vma, return VM_FAULT_SIGBUS; } -/* - * Having a close hook prevents vma merging regardless of flags. - */ -static void special_mapping_close(struct vm_area_struct *vma) -{ -} - -static const struct vm_operations_struct special_mapping_vmops = { - .close = special_mapping_close, - .fault = special_mapping_fault, -}; - -/* - * Called with mm->mmap_sem held for writing. - * Insert a new vma covering the given region, with the given flags. - * Its pages are supplied by the given array of struct page *. - * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. - * The region past the last page supplied will always produce SIGBUS. - * The array pointer and the pages it points to are assumed to stay alive - * for as long as this mapping might exist. - */ -int install_special_mapping(struct mm_struct *mm, - unsigned long addr, unsigned long len, - unsigned long vm_flags, struct page **pages) +static struct vm_area_struct *__install_special_mapping( + struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, const struct vm_operations_struct *ops, + void *priv) { int ret; struct vm_area_struct *vma; vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (unlikely(vma == NULL)) - return -ENOMEM; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; - vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND; + vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); - vma->vm_ops = &special_mapping_vmops; - vma->vm_private_data = pages; + vma->vm_ops = ops; + vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) @@ -2870,11 +2965,40 @@ int install_special_mapping(struct mm_struct *mm, perf_event_mmap(vma); - return 0; + return vma; out: kmem_cache_free(vm_area_cachep, vma); - return ret; + return ERR_PTR(ret); +} + +/* + * Called with mm->mmap_sem held for writing. + * Insert a new vma covering the given region, with the given flags. + * Its pages are supplied by the given array of struct page *. + * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. + * The region past the last page supplied will always produce SIGBUS. + * The array pointer and the pages it points to are assumed to stay alive + * for as long as this mapping might exist. + */ +struct vm_area_struct *_install_special_mapping( + struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, const struct vm_special_mapping *spec) +{ + return __install_special_mapping(mm, addr, len, vm_flags, + &special_mapping_vmops, (void *)spec); +} + +int install_special_mapping(struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, struct page **pages) +{ + struct vm_area_struct *vma = __install_special_mapping( + mm, addr, len, vm_flags, &legacy_special_mapping_vmops, + (void *)pages); + + return PTR_ERR_OR_ZERO(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); @@ -2943,7 +3067,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * vma in this mm is backed by the same anon_vma or address_space. * * We can take all the locks in random order because the VM code - * taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never + * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never * takes more than one of them in a row. Secondly we're protected * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex. * @@ -3001,7 +3125,7 @@ static void vm_unlock_anon_vma(struct anon_vma *anon_vma) if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_node)) BUG(); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); } } @@ -3052,3 +3176,115 @@ void __init mmap_init(void) ret = percpu_counter_init(&vm_committed_as, 0); VM_BUG_ON(ret); } + +/* + * Initialise sysctl_user_reserve_kbytes. + * + * This is intended to prevent a user from starting a single memory hogging + * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER + * mode. + * + * The default value is min(3% of free memory, 128MB) + * 128MB is enough to recover with sshd/login, bash, and top/kill. + */ +static int init_user_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); + return 0; +} +subsys_initcall(init_user_reserve); + +/* + * Initialise sysctl_admin_reserve_kbytes. + * + * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin + * to log in and kill a memory hogging process. + * + * Systems with more than 256MB will reserve 8MB, enough to recover + * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will + * only reserve 3% of free pages by default. + */ +static int init_admin_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); + return 0; +} +subsys_initcall(init_admin_reserve); + +/* + * Reinititalise user and admin reserves if memory is added or removed. + * + * The default user reserve max is 128MB, and the default max for the + * admin reserve is 8MB. These are usually, but not always, enough to + * enable recovery from a memory hogging process using login/sshd, a shell, + * and tools like top. It may make sense to increase or even disable the + * reserve depending on the existence of swap or variations in the recovery + * tools. So, the admin may have changed them. + * + * If memory is added and the reserves have been eliminated or increased above + * the default max, then we'll trust the admin. + * + * If memory is removed and there isn't enough free memory, then we + * need to reset the reserves. + * + * Otherwise keep the reserve set by the admin. + */ +static int reserve_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + unsigned long tmp, free_kbytes; + + switch (action) { + case MEM_ONLINE: + /* Default max is 128MB. Leave alone if modified by operator. */ + tmp = sysctl_user_reserve_kbytes; + if (0 < tmp && tmp < (1UL << 17)) + init_user_reserve(); + + /* Default max is 8MB. Leave alone if modified by operator. */ + tmp = sysctl_admin_reserve_kbytes; + if (0 < tmp && tmp < (1UL << 13)) + init_admin_reserve(); + + break; + case MEM_OFFLINE: + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + if (sysctl_user_reserve_kbytes > free_kbytes) { + init_user_reserve(); + pr_info("vm.user_reserve_kbytes reset to %lu\n", + sysctl_user_reserve_kbytes); + } + + if (sysctl_admin_reserve_kbytes > free_kbytes) { + init_admin_reserve(); + pr_info("vm.admin_reserve_kbytes reset to %lu\n", + sysctl_admin_reserve_kbytes); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block reserve_mem_nb = { + .notifier_call = reserve_mem_notifier, +}; + +static int __meminit init_reserve_notifier(void) +{ + if (register_hotmemory_notifier(&reserve_mem_nb)) + pr_err("Failed registering memory add/remove notifier for admin reserve\n"); + + return 0; +} +subsys_initcall(init_reserve_notifier); diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 3dcfaf4ed35..f802c2d216a 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -14,9 +14,6 @@ * use_mm * Makes the calling kernel thread take on the specified * mm context. - * Called by the retry thread execute retries within the - * iocb issuer's mm context, so that copy_from/to_user - * operations work seamlessly for aio. * (Note: this routine is intended to be called only * from a kernel thread context) */ @@ -34,6 +31,9 @@ void use_mm(struct mm_struct *mm) tsk->mm = mm; switch_mm(active_mm, mm, tsk); task_unlock(tsk); +#ifdef finish_arch_post_lock_switch + finish_arch_post_lock_switch(); +#endif if (active_mm != mm) mmdrop(active_mm); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 8a5ac8c686b..41cefdf0aad 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -37,7 +37,6 @@ static struct srcu_struct srcu; void __mmu_notifier_release(struct mm_struct *mm) { struct mmu_notifier *mn; - struct hlist_node *n; int id; /* @@ -45,13 +44,12 @@ void __mmu_notifier_release(struct mm_struct *mm) * ->release returns. */ id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) /* - * if ->release runs before mmu_notifier_unregister it - * must be handled as it's the only way for the driver - * to flush all existing sptes and stop the driver - * from establishing any more sptes before all the - * pages in the mm are freed. + * If ->release runs before mmu_notifier_unregister it must be + * handled, as it's the only way for the driver to flush all + * existing sptes and stop the driver from establishing any more + * sptes before all the pages in the mm are freed. */ if (mn->ops->release) mn->ops->release(mn, mm); @@ -64,22 +62,22 @@ void __mmu_notifier_release(struct mm_struct *mm) hlist); /* * We arrived before mmu_notifier_unregister so - * mmu_notifier_unregister will do nothing other than - * to wait ->release to finish and - * mmu_notifier_unregister to return. + * mmu_notifier_unregister will do nothing other than to wait + * for ->release to finish and for mmu_notifier_unregister to + * return. */ hlist_del_init_rcu(&mn->hlist); } spin_unlock(&mm->mmu_notifier_mm->lock); /* - * synchronize_srcu here prevents mmu_notifier_release to - * return to exit_mmap (which would proceed freeing all pages - * in the mm) until the ->release method returns, if it was - * invoked by mmu_notifier_unregister. + * synchronize_srcu here prevents mmu_notifier_release from returning to + * exit_mmap (which would proceed with freeing all pages in the mm) + * until the ->release method returns, if it was invoked by + * mmu_notifier_unregister. * - * The mmu_notifier_mm can't go away from under us because one - * mm_count is hold by exit_mmap. + * The mmu_notifier_mm can't go away from under us because one mm_count + * is held by exit_mmap. */ synchronize_srcu(&srcu); } @@ -93,11 +91,10 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long address) { struct mmu_notifier *mn; - struct hlist_node *n; int young = 0, id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->clear_flush_young) young |= mn->ops->clear_flush_young(mn, mm, address); } @@ -110,11 +107,10 @@ int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { struct mmu_notifier *mn; - struct hlist_node *n; int young = 0, id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->test_young) { young = mn->ops->test_young(mn, mm, address); if (young) @@ -130,11 +126,10 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { struct mmu_notifier *mn; - struct hlist_node *n; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->change_pte) mn->ops->change_pte(mn, mm, address, pte); } @@ -145,11 +140,10 @@ void __mmu_notifier_invalidate_page(struct mm_struct *mm, unsigned long address) { struct mmu_notifier *mn; - struct hlist_node *n; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->invalidate_page) mn->ops->invalidate_page(mn, mm, address); } @@ -160,31 +154,31 @@ void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *mn; - struct hlist_node *n; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->invalidate_range_start) mn->ops->invalidate_range_start(mn, mm, start, end); } srcu_read_unlock(&srcu, id); } +EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_start); void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *mn; - struct hlist_node *n; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->invalidate_range_end) mn->ops->invalidate_range_end(mn, mm, start, end); } srcu_read_unlock(&srcu, id); } +EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end); static int do_mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm, @@ -296,29 +290,32 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) if (!hlist_unhashed(&mn->hlist)) { /* - * SRCU here will force exit_mmap to wait ->release to finish - * before freeing the pages. + * SRCU here will force exit_mmap to wait for ->release to + * finish before freeing the pages. */ int id; id = srcu_read_lock(&srcu); /* - * exit_mmap will block in mmu_notifier_release to - * guarantee ->release is called before freeing the - * pages. + * exit_mmap will block in mmu_notifier_release to guarantee + * that ->release is called before freeing the pages. */ if (mn->ops->release) mn->ops->release(mn, mm); srcu_read_unlock(&srcu, id); spin_lock(&mm->mmu_notifier_mm->lock); - hlist_del_rcu(&mn->hlist); + /* + * Can not use list_del_rcu() since __mmu_notifier_release + * can delete it before we hold the lock. + */ + hlist_del_init_rcu(&mn->hlist); spin_unlock(&mm->mmu_notifier_mm->lock); } /* - * Wait any running method to finish, of course including - * ->release if it was run by mmu_notifier_relase instead of us. + * Wait for any running method to finish, of course including + * ->release if it was run by mmu_notifier_release instead of us. */ synchronize_srcu(&srcu); @@ -332,5 +329,4 @@ static int __init mmu_notifier_init(void) { return init_srcu_struct(&srcu); } - -module_init(mmu_notifier_init); +subsys_initcall(mmu_notifier_init); diff --git a/mm/mmzone.c b/mm/mmzone.c index 4596d81b89b..bf34fb8556d 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -1,7 +1,7 @@ /* * linux/mm/mmzone.c * - * management codes for pgdats and zones. + * management codes for pgdats, zones and page flags */ @@ -96,3 +96,21 @@ void lruvec_init(struct lruvec *lruvec) for_each_lru(lru) INIT_LIST_HEAD(&lruvec->lists[lru]); } + +#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) +int page_cpupid_xchg_last(struct page *page, int cpupid) +{ + unsigned long old_flags, flags; + int last_cpupid; + + do { + old_flags = flags = page->flags; + last_cpupid = page_cpupid_last(page); + + flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT); + flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT; + } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags)); + + return last_cpupid; +} +#endif diff --git a/mm/mprotect.c b/mm/mprotect.c index 94722a4d6b4..c43d557941f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -23,6 +23,7 @@ #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/perf_event.h> +#include <linux/ksm.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/cacheflush.h> @@ -35,18 +36,47 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) } #endif +/* + * For a prot_numa update we only hold mmap_sem for read so there is a + * potential race with faulting where a pmd was temporarily none. This + * function checks for a transhuge pmd under the appropriate lock. It + * returns a pte if it was successfully locked or NULL if it raced with + * a transhuge insertion. + */ +static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, int prot_numa, spinlock_t **ptl) +{ + pte_t *pte; + spinlock_t *pmdl; + + /* !prot_numa is protected by mmap_sem held for write */ + if (!prot_numa) + return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl); + + pmdl = pmd_lock(vma->vm_mm, pmd); + if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) { + spin_unlock(pmdl); + return NULL; + } + + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl); + spin_unlock(pmdl); + return pte; +} + static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, - int dirty_accountable, int prot_numa, bool *ret_all_same_node) + int dirty_accountable, int prot_numa) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, oldpte; spinlock_t *ptl; unsigned long pages = 0; - bool all_same_node = true; - int last_nid = -1; - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl); + if (!pte) + return 0; + arch_enter_lazy_mmu_mode(); do { oldpte = *pte; @@ -54,117 +84,111 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, pte_t ptent; bool updated = false; - ptent = ptep_modify_prot_start(mm, addr, pte); if (!prot_numa) { + ptent = ptep_modify_prot_start(mm, addr, pte); + if (pte_numa(ptent)) + ptent = pte_mknonnuma(ptent); ptent = pte_modify(ptent, newprot); + /* + * Avoid taking write faults for pages we + * know to be dirty. + */ + if (dirty_accountable && pte_dirty(ptent)) + ptent = pte_mkwrite(ptent); + ptep_modify_prot_commit(mm, addr, pte, ptent); updated = true; } else { struct page *page; page = vm_normal_page(vma, addr, oldpte); - if (page) { - int this_nid = page_to_nid(page); - if (last_nid == -1) - last_nid = this_nid; - if (last_nid != this_nid) - all_same_node = false; - - /* only check non-shared pages */ - if (!pte_numa(oldpte) && - page_mapcount(page) == 1) { - ptent = pte_mknuma(ptent); + if (page && !PageKsm(page)) { + if (!pte_numa(oldpte)) { + ptep_set_numa(mm, addr, pte); updated = true; } } } - - /* - * Avoid taking write faults for pages we know to be - * dirty. - */ - if (dirty_accountable && pte_dirty(ptent)) { - ptent = pte_mkwrite(ptent); - updated = true; - } - if (updated) pages++; - ptep_modify_prot_commit(mm, addr, pte, ptent); } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { + pte_t newpte; /* * A protection check is difficult so * just be safe and disable write */ make_migration_entry_read(&entry); - set_pte_at(mm, addr, pte, - swp_entry_to_pte(entry)); + newpte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(oldpte)) + newpte = pte_swp_mksoft_dirty(newpte); + set_pte_at(mm, addr, pte, newpte); + + pages++; } - pages++; } } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); - *ret_all_same_node = all_same_node; return pages; } -#ifdef CONFIG_NUMA_BALANCING -static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr, - pmd_t *pmd) -{ - spin_lock(&mm->page_table_lock); - set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd)); - spin_unlock(&mm->page_table_lock); -} -#else -static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr, - pmd_t *pmd) -{ - BUG(); -} -#endif /* CONFIG_NUMA_BALANCING */ - static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) { pmd_t *pmd; + struct mm_struct *mm = vma->vm_mm; unsigned long next; unsigned long pages = 0; - bool all_same_node; + unsigned long nr_huge_updates = 0; + unsigned long mni_start = 0; pmd = pmd_offset(pud, addr); do { + unsigned long this_pages; + next = pmd_addr_end(addr, end); + if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd)) + continue; + + /* invoke the mmu notifier if the pmd is populated */ + if (!mni_start) { + mni_start = addr; + mmu_notifier_invalidate_range_start(mm, mni_start, end); + } + if (pmd_trans_huge(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) split_huge_page_pmd(vma, addr, pmd); - else if (change_huge_pmd(vma, pmd, addr, newprot, - prot_numa)) { - pages += HPAGE_PMD_NR; - continue; + else { + int nr_ptes = change_huge_pmd(vma, pmd, addr, + newprot, prot_numa); + + if (nr_ptes) { + if (nr_ptes == HPAGE_PMD_NR) { + pages += HPAGE_PMD_NR; + nr_huge_updates++; + } + + /* huge pmd was handled */ + continue; + } } - /* fall through */ + /* fall through, the trans huge pmd just split */ } - if (pmd_none_or_clear_bad(pmd)) - continue; - pages += change_pte_range(vma, pmd, addr, next, newprot, - dirty_accountable, prot_numa, &all_same_node); - - /* - * If we are changing protections for NUMA hinting faults then - * set pmd_numa if the examined pages were all on the same - * node. This allows a regular PMD to be handled as one fault - * and effectively batches the taking of the PTL - */ - if (prot_numa && all_same_node) - change_pmd_protnuma(vma->vm_mm, addr, pmd); + this_pages = change_pte_range(vma, pmd, addr, next, newprot, + dirty_accountable, prot_numa); + pages += this_pages; } while (pmd++, addr = next, addr != end); + if (mni_start) + mmu_notifier_invalidate_range_end(mm, mni_start, end); + + if (nr_huge_updates) + count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates); return pages; } @@ -201,6 +225,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); + set_tlb_flush_pending(mm); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) @@ -212,6 +237,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, /* Only flush the TLB if we actually modified any entries: */ if (pages) flush_tlb_range(vma, start, end); + clear_tlb_flush_pending(mm); return pages; } @@ -220,15 +246,12 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) { - struct mm_struct *mm = vma->vm_mm; unsigned long pages; - mmu_notifier_invalidate_range_start(mm, start, end); if (is_vm_hugetlb_page(vma)) pages = hugetlb_change_protection(vma, start, end, newprot); else pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa); - mmu_notifier_invalidate_range_end(mm, start, end); return pages; } diff --git a/mm/mremap.c b/mm/mremap.c index e1031e1f6a6..05f1180e9f2 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -15,10 +15,12 @@ #include <linux/swap.h> #include <linux/capability.h> #include <linux/fs.h> +#include <linux/swapops.h> #include <linux/highmem.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/mmu_notifier.h> +#include <linux/sched/sysctl.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -68,6 +70,23 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, return pmd; } +static pte_t move_soft_dirty_pte(pte_t pte) +{ + /* + * Set soft dirty bit so we can notice + * in userspace the ptes were moved. + */ +#ifdef CONFIG_MEM_SOFT_DIRTY + if (pte_present(pte)) + pte = pte_mksoft_dirty(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_mksoft_dirty(pte); + else if (pte_file(pte)) + pte = pte_file_mksoft_dirty(pte); +#endif + return pte; +} + static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, unsigned long old_addr, unsigned long old_end, struct vm_area_struct *new_vma, pmd_t *new_pmd, @@ -125,6 +144,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, continue; pte = ptep_get_and_clear(mm, old_addr, old_pte); pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); + pte = move_soft_dirty_pte(pte); set_pte_at(mm, new_addr, new_pte, pte); } @@ -134,7 +154,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, pte_unmap(new_pte - 1); pte_unmap_unlock(old_pte - 1, old_ptl); if (anon_vma) - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); if (mapping) mutex_unlock(&mapping->i_mmap_mutex); } @@ -174,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma, break; if (pmd_trans_huge(*old_pmd)) { int err = 0; - if (extent == HPAGE_PMD_SIZE) + if (extent == HPAGE_PMD_SIZE) { + VM_BUG_ON(vma->vm_file || !vma->anon_vma); + /* See comment in move_ptes() */ + if (need_rmap_locks) + anon_vma_lock_write(vma->anon_vma); err = move_huge_pmd(vma, new_vma, old_addr, new_addr, old_end, old_pmd, new_pmd); + if (need_rmap_locks) + anon_vma_unlock_write(vma->anon_vma); + } if (err > 0) { need_flush = true; continue; @@ -208,7 +235,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma, static unsigned long move_vma(struct vm_area_struct *vma, unsigned long old_addr, unsigned long old_len, - unsigned long new_len, unsigned long new_addr) + unsigned long new_len, unsigned long new_addr, bool *locked) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma; @@ -299,9 +326,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (vm_flags & VM_LOCKED) { mm->locked_vm += new_len >> PAGE_SHIFT; - if (new_len > old_len) - mlock_vma_pages_range(new_vma, new_addr + old_len, - new_addr + new_len); + *locked = true; } return new_addr; @@ -366,9 +391,8 @@ Eagain: return ERR_PTR(-EAGAIN); } -static unsigned long mremap_to(unsigned long addr, - unsigned long old_len, unsigned long new_addr, - unsigned long new_len) +static unsigned long mremap_to(unsigned long addr, unsigned long old_len, + unsigned long new_addr, unsigned long new_len, bool *locked) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -418,7 +442,7 @@ static unsigned long mremap_to(unsigned long addr, if (ret & ~PAGE_MASK) goto out1; - ret = move_vma(vma, addr, old_len, new_len, new_addr); + ret = move_vma(vma, addr, old_len, new_len, new_addr, locked); if (!(ret & ~PAGE_MASK)) goto out; out1: @@ -456,14 +480,16 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, struct vm_area_struct *vma; unsigned long ret = -EINVAL; unsigned long charged = 0; - - down_write(¤t->mm->mmap_sem); + bool locked = false; if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE)) - goto out; + return ret; + + if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE)) + return ret; if (addr & ~PAGE_MASK) - goto out; + return ret; old_len = PAGE_ALIGN(old_len); new_len = PAGE_ALIGN(new_len); @@ -474,11 +500,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, * a zero new-len is nonsensical. */ if (!new_len) - goto out; + return ret; + + down_write(¤t->mm->mmap_sem); if (flags & MREMAP_FIXED) { - if (flags & MREMAP_MAYMOVE) - ret = mremap_to(addr, old_len, new_addr, new_len); + ret = mremap_to(addr, old_len, new_addr, new_len, + &locked); goto out; } @@ -520,8 +548,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); if (vma->vm_flags & VM_LOCKED) { mm->locked_vm += pages; - mlock_vma_pages_range(vma, addr + old_len, - addr + new_len); + locked = true; + new_addr = addr; } ret = addr; goto out; @@ -547,11 +575,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, goto out; } - ret = move_vma(vma, addr, old_len, new_len, new_addr); + ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked); } out: if (ret & ~PAGE_MASK) vm_unacct_memory(charged); up_write(¤t->mm->mmap_sem); + if (locked && new_len > old_len) + mm_populate(new_addr + old_len, new_len - old_len); return ret; } diff --git a/mm/msync.c b/mm/msync.c index 632df4527c0..992a1673d48 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -58,6 +58,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) vma = find_vma(mm, start); for (;;) { struct file *file; + loff_t fstart, fend; /* Still start < end. */ error = -ENOMEM; @@ -77,12 +78,18 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) goto out_unlock; } file = vma->vm_file; + fstart = (start - vma->vm_start) + + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + fend = fstart + (min(end, vma->vm_end) - start) - 1; start = vma->vm_end; if ((flags & MS_SYNC) && file && (vma->vm_flags & VM_SHARED)) { get_file(file); up_read(&mm->mmap_sem); - error = vfs_fsync(file, 0); + if (vma->vm_flags & VM_NONLINEAR) + error = vfs_fsync(file, 1); + else + error = vfs_fsync_range(file, fstart, fend, 1); fput(file); if (error || start >= end) goto out; diff --git a/mm/nobootmem.c b/mm/nobootmem.c index b8294fc03df..7ed58602e71 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -41,13 +41,15 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, if (limit > memblock.current_limit) limit = memblock.current_limit; - addr = memblock_find_in_range_node(goal, limit, size, align, nid); + addr = memblock_find_in_range_node(size, align, goal, limit, nid); if (!addr) return NULL; + if (memblock_reserve(addr, size)) + return NULL; + ptr = phys_to_virt(addr); memset(ptr, 0, size); - memblock_reserve(addr, size); /* * The min_count is set to 0 so that bootmem allocated blocks * are never reported as leaks. @@ -82,27 +84,18 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size) static void __init __free_pages_memory(unsigned long start, unsigned long end) { - unsigned long i, start_aligned, end_aligned; - int order = ilog2(BITS_PER_LONG); + int order; - start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1); - end_aligned = end & ~(BITS_PER_LONG - 1); + while (start < end) { + order = min(MAX_ORDER - 1UL, __ffs(start)); - if (end_aligned <= start_aligned) { - for (i = start; i < end; i++) - __free_pages_bootmem(pfn_to_page(i), 0); + while (start + (1UL << order) > end) + order--; - return; - } + __free_pages_bootmem(pfn_to_page(start), order); - for (i = start; i < start_aligned; i++) - __free_pages_bootmem(pfn_to_page(i), 0); - - for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG) - __free_pages_bootmem(pfn_to_page(i), order); - - for (i = end_aligned; i < end; i++) - __free_pages_bootmem(pfn_to_page(i), 0); + start += (1UL << order); + } } static unsigned long __init __free_memory_core(phys_addr_t start, @@ -120,52 +113,53 @@ static unsigned long __init __free_memory_core(phys_addr_t start, return end_pfn - start_pfn; } -unsigned long __init free_low_memory_core_early(int nodeid) +static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; - phys_addr_t start, end, size; + phys_addr_t start, end; u64 i; - for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) + for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) count += __free_memory_core(start, end); - /* free range that is used for reserved array if we allocate it */ - size = get_allocated_memblock_reserved_regions_info(&start); - if (size) - count += __free_memory_core(start, start + size); +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK + { + phys_addr_t size; + + /* Free memblock.reserved array if it was allocated */ + size = get_allocated_memblock_reserved_regions_info(&start); + if (size) + count += __free_memory_core(start, start + size); + + /* Free memblock.memory array if it was allocated */ + size = get_allocated_memblock_memory_regions_info(&start); + if (size) + count += __free_memory_core(start, start + size); + } +#endif return count; } -static void reset_node_lowmem_managed_pages(pg_data_t *pgdat) +static int reset_managed_pages_done __initdata; + +static inline void __init reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; - /* - * In free_area_init_core(), highmem zone's managed_pages is set to - * present_pages, and bootmem allocator doesn't allocate from highmem - * zones. So there's no need to recalculate managed_pages because all - * highmem pages will be managed by the buddy system. Here highmem - * zone also includes highmem movable zone. - */ + if (reset_managed_pages_done) + return; for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) - if (!is_highmem(z)) - z->managed_pages = 0; + z->managed_pages = 0; } -/** - * free_all_bootmem_node - release a node's free pages to the buddy allocator - * @pgdat: node to be released - * - * Returns the number of pages actually released. - */ -unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) +void __init reset_all_zones_managed_pages(void) { - register_page_bootmem_info_node(pgdat); - reset_node_lowmem_managed_pages(pgdat); + struct pglist_data *pgdat; - /* free_low_memory_core_early(MAX_NUMNODES) will be called later */ - return 0; + for_each_online_pgdat(pgdat) + reset_node_managed_pages(pgdat); + reset_managed_pages_done = 1; } /** @@ -175,17 +169,19 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) */ unsigned long __init free_all_bootmem(void) { - struct pglist_data *pgdat; + unsigned long pages; - for_each_online_pgdat(pgdat) - reset_node_lowmem_managed_pages(pgdat); + reset_all_zones_managed_pages(); /* - * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id + * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ - return free_low_memory_core_early(MAX_NUMNODES); + pages = free_low_memory_core_early(); + totalram_pages += pages; + + return pages; } /** @@ -201,7 +197,6 @@ unsigned long __init free_all_bootmem(void) void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size) { - kmemleak_free_part(__va(physaddr), size); memblock_free(physaddr, size); } @@ -216,7 +211,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, */ void __init free_bootmem(unsigned long addr, unsigned long size) { - kmemleak_free_part(__va(addr), size); memblock_free(addr, size); } @@ -232,7 +226,7 @@ static void * __init ___alloc_bootmem_nopanic(unsigned long size, restart: - ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit); + ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit); if (ptr) return ptr; @@ -316,7 +310,7 @@ again: if (ptr) return ptr; - ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, + ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit); if (ptr) return ptr; @@ -338,7 +332,7 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); } -void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, +static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { @@ -406,6 +400,14 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); } +void * __init __alloc_bootmem_low_nopanic(unsigned long size, + unsigned long align, + unsigned long goal) +{ + return ___alloc_bootmem_nopanic(size, align, goal, + ARCH_LOW_ADDRESS_LIMIT); +} + /** * __alloc_bootmem_low_node - allocate low boot memory from a specific node * @pgdat: node to allocate from diff --git a/mm/nommu.c b/mm/nommu.c index 79c3cac87af..4a852f6c570 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -13,8 +13,11 @@ * Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/export.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/file.h> @@ -24,11 +27,14 @@ #include <linux/vmalloc.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> +#include <linux/compiler.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> +#include <linux/sched/sysctl.h> +#include <linux/printk.h> #include <asm/uaccess.h> #include <asm/tlb.h> @@ -55,13 +61,15 @@ void *high_memory; struct page *mem_map; unsigned long max_mapnr; -unsigned long num_physpages; unsigned long highest_memmap_pfn; struct percpu_counter vm_committed_as; int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio = 50; /* default is 50% */ +unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS; +unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ +unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ int heap_stack_gap = 0; atomic_long_t mmap_pages_allocated; @@ -82,7 +90,6 @@ unsigned long vm_memory_committed(void) EXPORT_SYMBOL_GPL(vm_memory_committed); EXPORT_SYMBOL(mem_map); -EXPORT_SYMBOL(num_physpages); /* list of mapped, potentially shareable regions */ static struct kmem_cache *vm_region_jar; @@ -139,10 +146,10 @@ unsigned int kobjsize(const void *objp) return PAGE_SIZE << compound_order(page); } -int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int nr_pages, unsigned int foll_flags, - struct page **pages, struct vm_area_struct **vmas, - int *retry) +long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int foll_flags, struct page **pages, + struct vm_area_struct **vmas, int *nonblocking) { struct vm_area_struct *vma; unsigned long vm_flags; @@ -189,9 +196,10 @@ finish_or_fault: * 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 nr_pages, int write, int force, - struct page **pages, struct vm_area_struct **vmas) +long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + struct vm_area_struct **vmas) { int flags = 0; @@ -226,8 +234,7 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL(follow_pfn); -DEFINE_RWLOCK(vmlist_lock); -struct vm_struct *vmlist; +LIST_HEAD(vmap_area_list); void vfree(const void *addr) { @@ -279,6 +286,10 @@ EXPORT_SYMBOL(vmalloc_to_pfn); long vread(char *buf, char *addr, unsigned long count) { + /* Don't allow overflow */ + if ((unsigned long) buf + count < count) + count = -(unsigned long) buf; + memcpy(buf, addr, count); return count; } @@ -290,7 +301,7 @@ long vwrite(char *buf, char *addr, unsigned long count) count = -(unsigned long) addr; memcpy(addr, buf, count); - return(count); + return count; } /* @@ -453,7 +464,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases); * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. */ -void __attribute__((weak)) vmalloc_sync_all(void) +void __weak vmalloc_sync_all(void) { } @@ -762,16 +773,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) */ static void delete_vma_from_mm(struct vm_area_struct *vma) { + int i; struct address_space *mapping; struct mm_struct *mm = vma->vm_mm; + struct task_struct *curr = current; kenter("%p", vma); protect_vma(vma, 0); mm->map_count--; - if (mm->mmap_cache == vma) - mm->mmap_cache = NULL; + for (i = 0; i < VMACACHE_SIZE; i++) { + /* if the vma is cached, invalidate the entire cache */ + if (curr->vmacache[i] == vma) { + vmacache_invalidate(mm); + break; + } + } /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -819,8 +837,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) struct vm_area_struct *vma; /* check the cache first */ - vma = mm->mmap_cache; - if (vma && vma->vm_start <= addr && vma->vm_end > addr) + vma = vmacache_find(mm, addr); + if (likely(vma)) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -829,7 +847,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) if (vma->vm_start > addr) return NULL; if (vma->vm_end > addr) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -868,8 +886,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, unsigned long end = addr + len; /* check the cache first */ - vma = mm->mmap_cache; - if (vma && vma->vm_start == addr && vma->vm_end == end) + vma = vmacache_find_exact(mm, addr, end); + if (vma) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -880,7 +898,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, if (vma->vm_start > addr) return NULL; if (vma->vm_end == end) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -932,7 +950,7 @@ static int validate_mmap_request(struct file *file, struct address_space *mapping; /* files must support mmap */ - if (!file->f_op || !file->f_op->mmap) + if (!file->f_op->mmap) return -ENODEV; /* work out if what we've got could possibly be shared @@ -941,7 +959,7 @@ static int validate_mmap_request(struct file *file, */ mapping = file->f_mapping; if (!mapping) - mapping = file->f_path.dentry->d_inode->i_mapping; + mapping = file_inode(file)->i_mapping; capabilities = 0; if (mapping && mapping->backing_dev_info) @@ -950,7 +968,7 @@ static int validate_mmap_request(struct file *file, if (!capabilities) { /* no explicit capabilities set, so assume some * defaults */ - switch (file->f_path.dentry->d_inode->i_mode & S_IFMT) { + switch (file_inode(file)->i_mode & S_IFMT) { case S_IFREG: case S_IFBLK: capabilities = BDI_CAP_MAP_COPY; @@ -985,11 +1003,11 @@ static int validate_mmap_request(struct file *file, !(file->f_mode & FMODE_WRITE)) return -EACCES; - if (IS_APPEND(file->f_path.dentry->d_inode) && + if (IS_APPEND(file_inode(file)) && (file->f_mode & FMODE_WRITE)) return -EACCES; - if (locks_verify_locked(file->f_path.dentry->d_inode)) + if (locks_verify_locked(file)) return -EAGAIN; if (!(capabilities & BDI_CAP_MAP_DIRECT)) @@ -997,8 +1015,7 @@ static int validate_mmap_request(struct file *file, /* we mustn't privatise shared mappings */ capabilities &= ~BDI_CAP_MAP_COPY; - } - else { + } else { /* we're going to read the file into private memory we * allocate */ if (!(capabilities & BDI_CAP_MAP_COPY)) @@ -1029,23 +1046,20 @@ static int validate_mmap_request(struct file *file, if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) { if (prot & PROT_EXEC) return -EPERM; - } - else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) { + } else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) { /* handle implication of PROT_EXEC by PROT_READ */ if (current->personality & READ_IMPLIES_EXEC) { if (capabilities & BDI_CAP_EXEC_MAP) prot |= PROT_EXEC; } - } - else if ((prot & PROT_READ) && + } else if ((prot & PROT_READ) && (prot & PROT_EXEC) && !(capabilities & BDI_CAP_EXEC_MAP) ) { /* backing file is not executable, try to copy */ capabilities &= ~BDI_CAP_MAP_DIRECT; } - } - else { + } else { /* anonymous mappings are always memory backed and can be * privately mapped */ @@ -1235,7 +1249,7 @@ error_free: return ret; enomem: - printk("Allocation of length %lu from process %d (%s) failed\n", + pr_err("Allocation of length %lu from process %d (%s) failed\n", len, current->pid, current->comm); show_free_areas(0); return -ENOMEM; @@ -1249,7 +1263,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff) + unsigned long pgoff, + unsigned long *populate) { struct vm_area_struct *vma; struct vm_region *region; @@ -1259,6 +1274,8 @@ unsigned long do_mmap_pgoff(struct file *file, kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff); + *populate = 0; + /* decide whether we should attempt the mapping, and if so what sort of * mapping */ ret = validate_mmap_request(file, addr, len, prot, flags, pgoff, @@ -1322,8 +1339,8 @@ unsigned long do_mmap_pgoff(struct file *file, continue; /* search for overlapping mappings on the same file */ - if (pregion->vm_file->f_path.dentry->d_inode != - file->f_path.dentry->d_inode) + if (file_inode(pregion->vm_file) != + file_inode(file)) continue; if (pregion->vm_pgoff >= pgend) @@ -1650,7 +1667,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) /* find the first potentially overlapping VMA */ vma = find_vma(mm, start); if (!vma) { - static int limit = 0; + static int limit; if (limit < 5) { printk(KERN_WARNING "munmap of memory not mmapped by process %d" @@ -1765,7 +1782,7 @@ unsigned long vm_brk(unsigned long addr, unsigned long len) * * MREMAP_FIXED is not supported under NOMMU conditions */ -unsigned long do_mremap(unsigned long addr, +static unsigned long do_mremap(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr) { @@ -1800,7 +1817,6 @@ unsigned long do_mremap(unsigned long addr, vma->vm_end = vma->vm_start + new_len; return vma->vm_start; } -EXPORT_SYMBOL(do_mremap); SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long, new_len, unsigned long, flags, @@ -1814,9 +1830,11 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, return ret; } -struct page *follow_page(struct vm_area_struct *vma, unsigned long address, - unsigned int foll_flags) +struct page *follow_page_mask(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned int *page_mask) { + *page_mask = 0; return NULL; } @@ -1831,6 +1849,16 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(remap_pfn_range); +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) +{ + unsigned long pfn = start >> PAGE_SHIFT; + unsigned long vm_len = vma->vm_end - vma->vm_start; + + pfn += vma->vm_pgoff; + return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_iomap_memory); + int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { @@ -1852,10 +1880,6 @@ unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; } -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ -} - void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) @@ -1881,7 +1905,7 @@ EXPORT_SYMBOL(unmap_mapping_range); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed; + unsigned long free, allowed, reserve; vm_acct_memory(pages); @@ -1903,7 +1927,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ free -= global_page_state(NR_SHMEM); - free += nr_swap_pages; + free += get_nr_swap_pages(); /* * Any slabs which are created with the @@ -1922,10 +1946,10 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) free -= totalreserve_pages; /* - * Leave the last 3% for root + * Reserve some for root */ if (!cap_sys_admin) - free -= free / 32; + free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); if (free > pages) return 0; @@ -1933,18 +1957,20 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) goto error; } - allowed = totalram_pages * sysctl_overcommit_ratio / 100; + allowed = vm_commit_limit(); /* - * Leave the last 3% for root + * Reserve some 3% for root */ if (!cap_sys_admin) - allowed -= allowed / 32; - allowed += total_swap_pages; + allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); - /* Don't let a single process grow too big: - leave 3% of the size of this process for other processes */ - if (mm) - allowed -= mm->total_vm / 32; + /* + * Don't let a single process grow so big a user can't recover + */ + if (mm) { + reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); + allowed -= min(mm->total_vm / 32, reserve); + } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; @@ -1967,6 +1993,12 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_fault); +void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + BUG(); +} +EXPORT_SYMBOL(filemap_map_pages); + int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, unsigned long size, pgoff_t pgoff) { @@ -2106,3 +2138,45 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, up_write(&nommu_region_sem); return 0; } + +/* + * Initialise sysctl_user_reserve_kbytes. + * + * This is intended to prevent a user from starting a single memory hogging + * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER + * mode. + * + * The default value is min(3% of free memory, 128MB) + * 128MB is enough to recover with sshd/login, bash, and top/kill. + */ +static int __meminit init_user_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); + return 0; +} +module_init(init_user_reserve) + +/* + * Initialise sysctl_admin_reserve_kbytes. + * + * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin + * to log in and kill a memory hogging process. + * + * Systems with more than 256MB will reserve 8MB, enough to recover + * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will + * only reserve 3% of free pages by default. + */ +static int __meminit init_admin_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); + return 0; +} +module_init(init_admin_reserve) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 0399f146ae4..3291e82d435 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -47,19 +47,21 @@ static DEFINE_SPINLOCK(zone_scan_lock); #ifdef CONFIG_NUMA /** * has_intersects_mems_allowed() - check task eligiblity for kill - * @tsk: task struct of which task to consider + * @start: task struct of which task to consider * @mask: nodemask passed to page allocator for mempolicy ooms * * Task eligibility is determined by whether or not a candidate task, @tsk, * shares the same mempolicy nodes as current if it is bound by such a policy * and whether or not it has the same set of allowed cpuset nodes. */ -static bool has_intersects_mems_allowed(struct task_struct *tsk, +static bool has_intersects_mems_allowed(struct task_struct *start, const nodemask_t *mask) { - struct task_struct *start = tsk; + struct task_struct *tsk; + bool ret = false; - do { + rcu_read_lock(); + for_each_thread(start, tsk) { if (mask) { /* * If this is a mempolicy constrained oom, tsk's @@ -67,19 +69,20 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk, * mempolicy intersects current, otherwise it may be * needlessly killed. */ - if (mempolicy_nodemask_intersects(tsk, mask)) - return true; + ret = mempolicy_nodemask_intersects(tsk, mask); } else { /* * This is not a mempolicy constrained oom, so only * check the mems of tsk's cpuset. */ - if (cpuset_mems_allowed_intersects(current, tsk)) - return true; + ret = cpuset_mems_allowed_intersects(current, tsk); } - } while_each_thread(start, tsk); + if (ret) + break; + } + rcu_read_unlock(); - return false; + return ret; } #else static bool has_intersects_mems_allowed(struct task_struct *tsk, @@ -97,16 +100,21 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk, */ struct task_struct *find_lock_task_mm(struct task_struct *p) { - struct task_struct *t = p; + struct task_struct *t; + + rcu_read_lock(); - do { + for_each_thread(p, t) { task_lock(t); if (likely(t->mm)) - return t; + goto found; task_unlock(t); - } while_each_thread(p, t); + } + t = NULL; +found: + rcu_read_unlock(); - return NULL; + return t; } /* return true if the task is not adequate as candidate victim task. */ @@ -161,7 +169,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + p->mm->nr_ptes + + points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) + get_mm_counter(p->mm, MM_SWAPENTS); task_unlock(p); @@ -170,7 +178,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * implementation used by LSMs. */ if (has_capability_noaudit(p, CAP_SYS_ADMIN)) - adj -= 30; + points -= (points * 3) / 100; /* Normalize to oom_score_adj units */ adj *= totalpages / 1000; @@ -288,7 +296,7 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task, /* * Simple selection loop. We chose the process with the highest - * number of 'points'. + * number of 'points'. Returns -1 on scan abort. * * (not docbooked, we don't want this one cluttering up the manual) */ @@ -301,7 +309,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, unsigned long chosen_points = 0; rcu_read_lock(); - do_each_thread(g, p) { + for_each_process_thread(g, p) { unsigned int points; switch (oom_scan_process_thread(p, totalpages, nodemask, @@ -314,16 +322,20 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, continue; case OOM_SCAN_ABORT: rcu_read_unlock(); - return ERR_PTR(-1UL); + return (struct task_struct *)(-1UL); case OOM_SCAN_OK: break; }; points = oom_badness(p, NULL, nodemask, totalpages); - if (points > chosen_points) { - chosen = p; - chosen_points = points; - } - } while_each_thread(g, p); + if (!points || points < chosen_points) + continue; + /* Prefer thread group leaders for display purposes */ + if (points == chosen_points && thread_group_leader(chosen)) + continue; + + chosen = p; + chosen_points = points; + } if (chosen) get_task_struct(chosen); rcu_read_unlock(); @@ -364,10 +376,10 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu %5hd %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), - task->mm->nr_ptes, + atomic_long_read(&task->mm->nr_ptes), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); @@ -386,8 +398,10 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); - mem_cgroup_print_oom_info(memcg, p); - show_mem(SHOW_MEM_FILTER_NODES); + if (memcg) + mem_cgroup_print_oom_info(memcg, p); + else + show_mem(SHOW_MEM_FILTER_NODES); if (sysctl_oom_dump_tasks) dump_tasks(memcg, nodemask); } @@ -404,7 +418,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, { struct task_struct *victim = p; struct task_struct *child; - struct task_struct *t = p; + struct task_struct *t; struct mm_struct *mm; unsigned int victim_points = 0; static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, @@ -435,7 +449,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * still freeing memory. */ read_lock(&tasklist_lock); - do { + for_each_thread(p, t) { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -453,13 +467,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, get_task_struct(victim); } } - } while_each_thread(p, t); + } read_unlock(&tasklist_lock); - rcu_read_lock(); p = find_lock_task_mm(victim); if (!p) { - rcu_read_unlock(); put_task_struct(victim); return; } else if (victim != p) { @@ -485,6 +497,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * That thread will now get access to memory reserves since it has a * pending fatal signal. */ + rcu_read_lock(); for_each_process(p) if (p->mm == mm && !same_thread_group(p, victim) && !(p->flags & PF_KTHREAD)) { @@ -655,7 +668,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, dump_header(NULL, gfp_mask, order, NULL, mpol_mask); panic("Out of memory and no killable processes...\n"); } - if (PTR_ERR(p) != -1UL) { + if (p != (void *)-1UL) { oom_kill_process(p, gfp_mask, order, points, totalpages, NULL, nodemask, "Out of memory"); killed = 1; @@ -676,9 +689,12 @@ out: */ void pagefault_out_of_memory(void) { - struct zonelist *zonelist = node_zonelist(first_online_node, - GFP_KERNEL); + struct zonelist *zonelist; + + if (mem_cgroup_oom_synchronize(true)) + return; + zonelist = node_zonelist(first_online_node, GFP_KERNEL); if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) { out_of_memory(NULL, 0, 0, NULL, false); clear_zonelist_oom(zonelist, GFP_KERNEL); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0713bfbf095..e0c943014eb 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -35,8 +35,12 @@ #include <linux/buffer_head.h> /* __set_page_dirty_buffers */ #include <linux/pagevec.h> #include <linux/timer.h> +#include <linux/sched/rt.h> +#include <linux/mm_inline.h> #include <trace/events/writeback.h> +#include "internal.h" + /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ @@ -152,24 +156,6 @@ static unsigned long writeout_period_time = 0; #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) /* - * Work out the current dirty-memory clamping and background writeout - * thresholds. - * - * The main aim here is to lower them aggressively if there is a lot of mapped - * memory around. To avoid stressing page reclaim with lots of unreclaimable - * pages. It is better to clamp down on writers than to start swapping, and - * performing lots of scanning. - * - * We only allow 1/2 of the currently-unmapped memory to be dirtied. - * - * We don't permit the clamping level to fall below 5% - that is getting rather - * excessive. - * - * We make sure that the background writeout level is below the adjusted - * clamping level. - */ - -/* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect @@ -187,6 +173,26 @@ static unsigned long writeout_period_time = 0; * global dirtyable memory first. */ +/** + * zone_dirtyable_memory - number of dirtyable pages in a zone + * @zone: the zone + * + * Returns the zone's number of pages potentially available for dirty + * page cache. This is the base value for the per-zone dirty limits. + */ +static unsigned long zone_dirtyable_memory(struct zone *zone) +{ + unsigned long nr_pages; + + nr_pages = zone_page_state(zone, NR_FREE_PAGES); + nr_pages -= min(nr_pages, zone->dirty_balance_reserve); + + nr_pages += zone_page_state(zone, NR_INACTIVE_FILE); + nr_pages += zone_page_state(zone, NR_ACTIVE_FILE); + + return nr_pages; +} + static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM @@ -194,11 +200,9 @@ static unsigned long highmem_dirtyable_memory(unsigned long total) unsigned long x = 0; for_each_node_state(node, N_HIGH_MEMORY) { - struct zone *z = - &NODE_DATA(node)->node_zones[ZONE_HIGHMEM]; + struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM]; - x += zone_page_state(z, NR_FREE_PAGES) + - zone_reclaimable_pages(z) - z->dirty_balance_reserve; + x += zone_dirtyable_memory(z); } /* * Unreclaimable memory (kernel memory or anonymous memory @@ -234,9 +238,12 @@ static unsigned long global_dirtyable_memory(void) { unsigned long x; - x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages(); + x = global_page_state(NR_FREE_PAGES); x -= min(x, dirty_balance_reserve); + x += global_page_state(NR_INACTIVE_FILE); + x += global_page_state(NR_ACTIVE_FILE); + if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); @@ -285,32 +292,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) } /** - * zone_dirtyable_memory - number of dirtyable pages in a zone - * @zone: the zone - * - * Returns the zone's number of pages potentially available for dirty - * page cache. This is the base value for the per-zone dirty limits. - */ -static unsigned long zone_dirtyable_memory(struct zone *zone) -{ - /* - * The effective global number of dirtyable pages may exclude - * highmem as a big-picture measure to keep the ratio between - * dirty memory and lowmem reasonable. - * - * But this function is purely about the individual zone and a - * highmem zone can hold its share of dirty pages, so we don't - * care about vm_highmem_is_dirtyable here. - */ - unsigned long nr_pages = zone_page_state(zone, NR_FREE_PAGES) + - zone_reclaimable_pages(zone); - - /* don't allow this to underflow */ - nr_pages -= min(nr_pages, zone->dirty_balance_reserve); - return nr_pages; -} - -/** * zone_dirty_limit - maximum number of dirty pages allowed in a zone * @zone: the zone * @@ -581,6 +562,37 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty) } /* + * setpoint - dirty 3 + * f(dirty) := 1.0 + (----------------) + * limit - setpoint + * + * it's a 3rd order polynomial that subjects to + * + * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast + * (2) f(setpoint) = 1.0 => the balance point + * (3) f(limit) = 0 => the hard limit + * (4) df/dx <= 0 => negative feedback control + * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) + * => fast response on large errors; small oscillation near setpoint + */ +static long long pos_ratio_polynom(unsigned long setpoint, + unsigned long dirty, + unsigned long limit) +{ + long long pos_ratio; + long x; + + x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, + limit - setpoint + 1); + pos_ratio = x; + pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; + pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; + pos_ratio += 1 << RATELIMIT_CALC_SHIFT; + + return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); +} + +/* * Dirty position control. * * (o) global/bdi setpoints @@ -678,26 +690,80 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, /* * global setpoint * - * setpoint - dirty 3 - * f(dirty) := 1.0 + (----------------) - * limit - setpoint + * See comment for pos_ratio_polynom(). + */ + setpoint = (freerun + limit) / 2; + pos_ratio = pos_ratio_polynom(setpoint, dirty, limit); + + /* + * The strictlimit feature is a tool preventing mistrusted filesystems + * from growing a large number of dirty pages before throttling. For + * such filesystems balance_dirty_pages always checks bdi counters + * against bdi limits. Even if global "nr_dirty" is under "freerun". + * This is especially important for fuse which sets bdi->max_ratio to + * 1% by default. Without strictlimit feature, fuse writeback may + * consume arbitrary amount of RAM because it is accounted in + * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * - * it's a 3rd order polynomial that subjects to + * Here, in bdi_position_ratio(), we calculate pos_ratio based on + * two values: bdi_dirty and bdi_thresh. Let's consider an example: + * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global + * limits are set by default to 10% and 20% (background and throttle). + * Then bdi_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. + * bdi_dirty_limit(bdi, bg_thresh) is about ~4K pages. bdi_setpoint is + * about ~6K pages (as the average of background and throttle bdi + * limits). The 3rd order polynomial will provide positive feedback if + * bdi_dirty is under bdi_setpoint and vice versa. * - * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast - * (2) f(setpoint) = 1.0 => the balance point - * (3) f(limit) = 0 => the hard limit - * (4) df/dx <= 0 => negative feedback control - * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) - * => fast response on large errors; small oscillation near setpoint + * Note, that we cannot use global counters in these calculations + * because we want to throttle process writing to a strictlimit BDI + * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB + * in the example above). */ - setpoint = (freerun + limit) / 2; - x = div_s64((setpoint - dirty) << RATELIMIT_CALC_SHIFT, - limit - setpoint + 1); - pos_ratio = x; - pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; - pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; - pos_ratio += 1 << RATELIMIT_CALC_SHIFT; + if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + long long bdi_pos_ratio; + unsigned long bdi_bg_thresh; + + if (bdi_dirty < 8) + return min_t(long long, pos_ratio * 2, + 2 << RATELIMIT_CALC_SHIFT); + + if (bdi_dirty >= bdi_thresh) + return 0; + + bdi_bg_thresh = div_u64((u64)bdi_thresh * bg_thresh, thresh); + bdi_setpoint = dirty_freerun_ceiling(bdi_thresh, + bdi_bg_thresh); + + if (bdi_setpoint == 0 || bdi_setpoint == bdi_thresh) + return 0; + + bdi_pos_ratio = pos_ratio_polynom(bdi_setpoint, bdi_dirty, + bdi_thresh); + + /* + * Typically, for strictlimit case, bdi_setpoint << setpoint + * and pos_ratio >> bdi_pos_ratio. In the other words global + * state ("dirty") is not limiting factor and we have to + * make decision based on bdi counters. But there is an + * important case when global pos_ratio should get precedence: + * global limits are exceeded (e.g. due to activities on other + * BDIs) while given strictlimit BDI is below limit. + * + * "pos_ratio * bdi_pos_ratio" would work for the case above, + * but it would look too non-natural for the case of all + * activity in the system coming from a single strictlimit BDI + * with bdi->max_ratio == 100%. + * + * Note that min() below somewhat changes the dynamics of the + * control system. Normally, pos_ratio value can be well over 3 + * (when globally we are at freerun and bdi is well below bdi + * setpoint). Now the maximum pos_ratio in the same situation + * is 2. We might want to tweak this if we observe the control + * system is too slow to adapt. + */ + return min(pos_ratio, bdi_pos_ratio); + } /* * We have computed basic pos_ratio above based on global situation. If @@ -758,7 +824,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, x_intercept = bdi_setpoint + span; if (bdi_dirty < x_intercept - span / 4) { - pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty), + pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty), x_intercept - bdi_setpoint + 1); } else pos_ratio /= 4; @@ -990,6 +1056,27 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, * keep that period small to reduce time lags). */ step = 0; + + /* + * For strictlimit case, calculations above were based on bdi counters + * and limits (starting from pos_ratio = bdi_position_ratio() and up to + * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). + * Hence, to calculate "step" properly, we have to use bdi_dirty as + * "dirty" and bdi_setpoint as "setpoint". + * + * We rampup dirty_ratelimit forcibly if bdi_dirty is low because + * it's possible that bdi_thresh is close to zero due to inactivity + * of backing device (see the implementation of bdi_dirty_limit()). + */ + if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + dirty = bdi_dirty; + if (bdi_dirty < 8) + setpoint = bdi_dirty + 1; + else + setpoint = (bdi_thresh + + bdi_dirty_limit(bdi, bg_thresh)) / 2; + } + if (dirty < setpoint) { x = min(bdi->balanced_dirty_ratelimit, min(balanced_dirty_ratelimit, task_ratelimit)); @@ -1100,11 +1187,11 @@ static unsigned long dirty_poll_interval(unsigned long dirty, return 1; } -static long bdi_max_pause(struct backing_dev_info *bdi, - unsigned long bdi_dirty) +static unsigned long bdi_max_pause(struct backing_dev_info *bdi, + unsigned long bdi_dirty) { - long bw = bdi->avg_write_bandwidth; - long t; + unsigned long bw = bdi->avg_write_bandwidth; + unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long @@ -1116,7 +1203,7 @@ static long bdi_max_pause(struct backing_dev_info *bdi, t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; - return min_t(long, t, MAX_PAUSE); + return min_t(unsigned long, t, MAX_PAUSE); } static long bdi_min_pause(struct backing_dev_info *bdi, @@ -1194,6 +1281,56 @@ static long bdi_min_pause(struct backing_dev_info *bdi, return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } +static inline void bdi_dirty_limits(struct backing_dev_info *bdi, + unsigned long dirty_thresh, + unsigned long background_thresh, + unsigned long *bdi_dirty, + unsigned long *bdi_thresh, + unsigned long *bdi_bg_thresh) +{ + unsigned long bdi_reclaimable; + + /* + * bdi_thresh is not treated as some limiting factor as + * dirty_thresh, due to reasons + * - in JBOD setup, bdi_thresh can fluctuate a lot + * - in a system with HDD and USB key, the USB key may somehow + * go into state (bdi_dirty >> bdi_thresh) either because + * bdi_dirty starts high, or because bdi_thresh drops low. + * In this case we don't want to hard throttle the USB key + * dirtiers for 100 seconds until bdi_dirty drops under + * bdi_thresh. Instead the auxiliary bdi control line in + * bdi_position_ratio() will let the dirtier task progress + * at some rate <= (write_bw / 2) for bringing down bdi_dirty. + */ + *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); + + if (bdi_bg_thresh) + *bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh * + background_thresh, + dirty_thresh) : 0; + + /* + * In order to avoid the stacked BDI deadlock we need + * to ensure we accurately count the 'dirty' pages when + * the threshold is low. + * + * Otherwise it would be possible to get thresh+n pages + * reported dirty, even though there are thresh-m pages + * actually dirty; with m+n sitting in the percpu + * deltas. + */ + if (*bdi_thresh < 2 * bdi_stat_error(bdi)) { + bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); + *bdi_dirty = bdi_reclaimable + + bdi_stat_sum(bdi, BDI_WRITEBACK); + } else { + bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); + *bdi_dirty = bdi_reclaimable + + bdi_stat(bdi, BDI_WRITEBACK); + } +} + /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force @@ -1205,13 +1342,9 @@ static void balance_dirty_pages(struct address_space *mapping, unsigned long pages_dirtied) { unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */ - unsigned long bdi_reclaimable; unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */ - unsigned long bdi_dirty; - unsigned long freerun; unsigned long background_thresh; unsigned long dirty_thresh; - unsigned long bdi_thresh; long period; long pause; long max_pause; @@ -1222,10 +1355,16 @@ static void balance_dirty_pages(struct address_space *mapping, unsigned long dirty_ratelimit; unsigned long pos_ratio; struct backing_dev_info *bdi = mapping->backing_dev_info; + bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; for (;;) { unsigned long now = jiffies; + unsigned long uninitialized_var(bdi_thresh); + unsigned long thresh; + unsigned long uninitialized_var(bdi_dirty); + unsigned long dirty; + unsigned long bg_thresh; /* * Unstable writes are a feature of certain networked @@ -1239,61 +1378,44 @@ static void balance_dirty_pages(struct address_space *mapping, global_dirty_limits(&background_thresh, &dirty_thresh); + if (unlikely(strictlimit)) { + bdi_dirty_limits(bdi, dirty_thresh, background_thresh, + &bdi_dirty, &bdi_thresh, &bg_thresh); + + dirty = bdi_dirty; + thresh = bdi_thresh; + } else { + dirty = nr_dirty; + thresh = dirty_thresh; + bg_thresh = background_thresh; + } + /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts - * when the bdi limits are ramping up. + * when the bdi limits are ramping up in case of !strictlimit. + * + * In strictlimit case make decision based on the bdi counters + * and limits. Small writeouts when the bdi limits are ramping + * up are the price we consciously pay for strictlimit-ing. */ - freerun = dirty_freerun_ceiling(dirty_thresh, - background_thresh); - if (nr_dirty <= freerun) { + if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh)) { current->dirty_paused_when = now; current->nr_dirtied = 0; current->nr_dirtied_pause = - dirty_poll_interval(nr_dirty, dirty_thresh); + dirty_poll_interval(dirty, thresh); break; } if (unlikely(!writeback_in_progress(bdi))) bdi_start_background_writeback(bdi); - /* - * bdi_thresh is not treated as some limiting factor as - * dirty_thresh, due to reasons - * - in JBOD setup, bdi_thresh can fluctuate a lot - * - in a system with HDD and USB key, the USB key may somehow - * go into state (bdi_dirty >> bdi_thresh) either because - * bdi_dirty starts high, or because bdi_thresh drops low. - * In this case we don't want to hard throttle the USB key - * dirtiers for 100 seconds until bdi_dirty drops under - * bdi_thresh. Instead the auxiliary bdi control line in - * bdi_position_ratio() will let the dirtier task progress - * at some rate <= (write_bw / 2) for bringing down bdi_dirty. - */ - bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); - - /* - * In order to avoid the stacked BDI deadlock we need - * to ensure we accurately count the 'dirty' pages when - * the threshold is low. - * - * Otherwise it would be possible to get thresh+n pages - * reported dirty, even though there are thresh-m pages - * actually dirty; with m+n sitting in the percpu - * deltas. - */ - if (bdi_thresh < 2 * bdi_stat_error(bdi)) { - bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); - bdi_dirty = bdi_reclaimable + - bdi_stat_sum(bdi, BDI_WRITEBACK); - } else { - bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); - bdi_dirty = bdi_reclaimable + - bdi_stat(bdi, BDI_WRITEBACK); - } + if (!strictlimit) + bdi_dirty_limits(bdi, dirty_thresh, background_thresh, + &bdi_dirty, &bdi_thresh, NULL); dirty_exceeded = (bdi_dirty > bdi_thresh) && - (nr_dirty > dirty_thresh); + ((nr_dirty > dirty_thresh) || strictlimit); if (dirty_exceeded && !bdi->dirty_exceeded) bdi->dirty_exceeded = 1; @@ -1422,9 +1544,9 @@ pause: bdi_start_background_writeback(bdi); } -void set_page_dirty_balance(struct page *page, int page_mkwrite) +void set_page_dirty_balance(struct page *page) { - if (set_page_dirty(page) || page_mkwrite) { + if (set_page_dirty(page)) { struct address_space *mapping = page_mapping(page); if (mapping) @@ -1483,7 +1605,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping) * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ - p = &__get_cpu_var(bdp_ratelimits); + p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { @@ -1495,7 +1617,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping) * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ - p = &__get_cpu_var(dirty_throttle_leaks); + p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); @@ -1542,7 +1664,7 @@ void throttle_vm_writeout(gfp_t gfp_mask) /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ -int dirty_writeback_centisecs_handler(ctl_table *table, int write, +int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); @@ -1615,7 +1737,7 @@ void writeback_set_ratelimit(void) ratelimit_pages = 16; } -static int __cpuinit +static int ratelimit_handler(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -1630,7 +1752,7 @@ ratelimit_handler(struct notifier_block *self, unsigned long action, } } -static struct notifier_block __cpuinitdata ratelimit_nb = { +static struct notifier_block ratelimit_nb = { .notifier_call = ratelimit_handler, .next = NULL, }; @@ -1982,6 +2104,8 @@ int __set_page_dirty_no_writeback(struct page *page) */ void account_page_dirtied(struct page *page, struct address_space *mapping) { + trace_writeback_dirty_page(page, mapping); + if (mapping_cap_account_dirty(mapping)) { __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_DIRTIED); @@ -1996,11 +2120,17 @@ EXPORT_SYMBOL(account_page_dirtied); /* * Helper function for set_page_writeback family. + * + * The caller must hold mem_cgroup_begin/end_update_page_stat() lock + * while calling this function. + * See test_set_page_writeback for example. + * * NOTE: Unlike account_page_dirtied this does not rely on being atomic * wrt interrupts. */ void account_page_writeback(struct page *page) { + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); inc_zone_page_state(page, NR_WRITEBACK); } EXPORT_SYMBOL(account_page_writeback); @@ -2025,11 +2155,12 @@ int __set_page_dirty_nobuffers(struct page *page) if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); struct address_space *mapping2; + unsigned long flags; if (!mapping) return 1; - spin_lock_irq(&mapping->tree_lock); + spin_lock_irqsave(&mapping->tree_lock, flags); mapping2 = page_mapping(page); if (mapping2) { /* Race with truncate? */ BUG_ON(mapping2 != mapping); @@ -2038,7 +2169,7 @@ int __set_page_dirty_nobuffers(struct page *page) radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); @@ -2217,7 +2348,10 @@ int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); int ret; + bool locked; + unsigned long memcg_flags; + mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2238,17 +2372,22 @@ int test_clear_page_writeback(struct page *page) ret = TestClearPageWriteback(page); } if (ret) { + mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); dec_zone_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_WRITTEN); } + mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags); return ret; } -int test_set_page_writeback(struct page *page) +int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); int ret; + bool locked; + unsigned long memcg_flags; + mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2266,19 +2405,21 @@ int test_set_page_writeback(struct page *page) radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_TOWRITE); + if (!keep_write) + radix_tree_tag_clear(&mapping->page_tree, + page_index(page), + PAGECACHE_TAG_TOWRITE); spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestSetPageWriteback(page); } if (!ret) account_page_writeback(page); + mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags); return ret; } -EXPORT_SYMBOL(test_set_page_writeback); +EXPORT_SYMBOL(__test_set_page_writeback); /* * Return true if any of the pages in the mapping are marked with the @@ -2289,3 +2430,23 @@ int mapping_tagged(struct address_space *mapping, int tag) return radix_tree_tagged(&mapping->page_tree, tag); } EXPORT_SYMBOL(mapping_tagged); + +/** + * wait_for_stable_page() - wait for writeback to finish, if necessary. + * @page: The page to wait on. + * + * This function determines if the given page is related to a backing device + * that requires page contents to be held stable during writeback. If so, then + * it will wait for any pending writeback to complete. + */ +void wait_for_stable_page(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + struct backing_dev_info *bdi = mapping->backing_dev_info; + + if (!bdi_cap_stable_pages_required(bdi)) + return; + + wait_on_page_writeback(page); +} +EXPORT_SYMBOL_GPL(wait_for_stable_page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index df2022ff0c8..ef44ad736ca 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -56,13 +56,21 @@ #include <linux/ftrace_event.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> +#include <linux/mm_inline.h> #include <linux/migrate.h> #include <linux/page-debug-flags.h> +#include <linux/hugetlb.h> +#include <linux/sched/rt.h> +#include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include "internal.h" +/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ +static DEFINE_MUTEX(pcp_batch_high_lock); +#define MIN_PERCPU_PAGELIST_FRACTION (8) + #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -98,6 +106,9 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = { }; EXPORT_SYMBOL(node_states); +/* Protect totalram_pages and zone->managed_pages */ +static DEFINE_SPINLOCK(managed_page_count_lock); + unsigned long totalram_pages __read_mostly; unsigned long totalreserve_pages __read_mostly; /* @@ -195,6 +206,7 @@ static char * const zone_names[MAX_NR_ZONES] = { }; int min_free_kbytes = 1024; +int user_min_free_kbytes = -1; static unsigned long __meminitdata nr_kernel_pages; static unsigned long __meminitdata nr_all_pages; @@ -223,8 +235,8 @@ int page_group_by_mobility_disabled __read_mostly; void set_pageblock_migratetype(struct page *page, int migratetype) { - - if (unlikely(page_group_by_mobility_disabled)) + if (unlikely(page_group_by_mobility_disabled && + migratetype < MIGRATE_PCPTYPES)) migratetype = MIGRATE_UNMOVABLE; set_pageblock_flags_group(page, (unsigned long)migratetype, @@ -239,15 +251,21 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page) int ret = 0; unsigned seq; unsigned long pfn = page_to_pfn(page); + unsigned long sp, start_pfn; do { seq = zone_span_seqbegin(zone); - if (pfn >= zone->zone_start_pfn + zone->spanned_pages) - ret = 1; - else if (pfn < zone->zone_start_pfn) + start_pfn = zone->zone_start_pfn; + sp = zone->spanned_pages; + if (!zone_spans_pfn(zone, pfn)) ret = 1; } while (zone_span_seqretry(zone, seq)); + if (ret) + pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n", + pfn, zone_to_nid(zone), zone->name, + start_pfn, start_pfn + sp); + return ret; } @@ -279,7 +297,8 @@ static inline int bad_range(struct zone *zone, struct page *page) } #endif -static void bad_page(struct page *page) +static void bad_page(struct page *page, const char *reason, + unsigned long bad_flags) { static unsigned long resume; static unsigned long nr_shown; @@ -287,7 +306,7 @@ static void bad_page(struct page *page) /* Don't complain about poisoned pages */ if (PageHWPoison(page)) { - reset_page_mapcount(page); /* remove PageBuddy */ + page_mapcount_reset(page); /* remove PageBuddy */ return; } @@ -313,14 +332,14 @@ static void bad_page(struct page *page) printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); - dump_page(page); + dump_page_badflags(page, reason, bad_flags); print_modules(); dump_stack(); out: /* Leave bad fields for debug, except PageBuddy could make trouble */ - reset_page_mapcount(page); /* remove PageBuddy */ - add_taint(TAINT_BAD_PAGE); + page_mapcount_reset(page); /* remove PageBuddy */ + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* @@ -353,9 +372,11 @@ void prep_compound_page(struct page *page, unsigned long order) __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - __SetPageTail(p); set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } @@ -367,7 +388,7 @@ static int destroy_compound_page(struct page *page, unsigned long order) int bad = 0; if (unlikely(compound_order(page) != order)) { - bad_page(page); + bad_page(page, "wrong compound order", 0); bad++; } @@ -376,8 +397,11 @@ static int destroy_compound_page(struct page *page, unsigned long order) for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - if (unlikely(!PageTail(p) || (p->first_page != page))) { - bad_page(page); + if (unlikely(!PageTail(p))) { + bad_page(page, "PageTail not set", 0); + bad++; + } else if (unlikely(p->first_page != page)) { + bad_page(page, "first_page not consistent", 0); bad++; } __ClearPageTail(p); @@ -386,7 +410,8 @@ static int destroy_compound_page(struct page *page, unsigned long order) return bad; } -static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) +static inline void prep_zero_page(struct page *page, unsigned int order, + gfp_t gfp_flags) { int i; @@ -430,7 +455,7 @@ static inline void set_page_guard_flag(struct page *page) { } static inline void clear_page_guard_flag(struct page *page) { } #endif -static inline void set_page_order(struct page *page, int order) +static inline void set_page_order(struct page *page, unsigned int order) { set_page_private(page, order); __SetPageBuddy(page); @@ -473,27 +498,39 @@ __find_buddy_index(unsigned long page_idx, unsigned int order) * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * - * For recording whether a page is in the buddy system, we set ->_mapcount -2. - * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock. + * For recording whether a page is in the buddy system, we set ->_mapcount + * PAGE_BUDDY_MAPCOUNT_VALUE. + * Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is + * serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline int page_is_buddy(struct page *page, struct page *buddy, - int order) + unsigned int order) { if (!pfn_valid_within(page_to_pfn(buddy))) return 0; - if (page_zone_id(page) != page_zone_id(buddy)) - return 0; - if (page_is_guard(buddy) && page_order(buddy) == order) { - VM_BUG_ON(page_count(buddy) != 0); + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { - VM_BUG_ON(page_count(buddy) != 0); + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + /* + * zone check is done late to avoid uselessly + * calculating zone/node ids for pages that could + * never merge. + */ + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } return 0; @@ -512,8 +549,9 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous - * free pages of length of (1 << order) and marked with _mapcount -2. Page's - * order is recorded in page_private(page) field. + * free pages of length of (1 << order) and marked with _mapcount + * PAGE_BUDDY_MAPCOUNT_VALUE. Page's order is recorded in page_private(page) + * field. * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were * free, the remainder of the region must be split into blocks. @@ -524,6 +562,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, */ static inline void __free_one_page(struct page *page, + unsigned long pfn, struct zone *zone, unsigned int order, int migratetype) { @@ -532,16 +571,18 @@ static inline void __free_one_page(struct page *page, unsigned long uninitialized_var(buddy_idx); struct page *buddy; + VM_BUG_ON(!zone_is_initialized(zone)); + if (unlikely(PageCompound(page))) if (unlikely(destroy_compound_page(page, order))) return; VM_BUG_ON(migratetype == -1); - page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); + page_idx = pfn & ((1 << MAX_ORDER) - 1); - VM_BUG_ON(page_idx & ((1 << order) - 1)); - VM_BUG_ON(bad_range(zone, page)); + VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page); + VM_BUG_ON_PAGE(bad_range(zone, page), page); while (order < MAX_ORDER-1) { buddy_idx = __find_buddy_index(page_idx, order); @@ -597,15 +638,26 @@ out: static inline int free_pages_check(struct page *page) { - if (unlikely(page_mapcount(page) | - (page->mapping != NULL) | - (atomic_read(&page->_count) != 0) | - (page->flags & PAGE_FLAGS_CHECK_AT_FREE) | - (mem_cgroup_bad_page_check(page)))) { - bad_page(page); + const char *bad_reason = NULL; + unsigned long bad_flags = 0; + + if (unlikely(page_mapcount(page))) + bad_reason = "nonzero mapcount"; + if (unlikely(page->mapping != NULL)) + bad_reason = "non-NULL mapping"; + if (unlikely(atomic_read(&page->_count) != 0)) + bad_reason = "nonzero _count"; + if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) { + bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; + bad_flags = PAGE_FLAGS_CHECK_AT_FREE; + } + if (unlikely(mem_cgroup_bad_page_check(page))) + bad_reason = "cgroup check failed"; + if (unlikely(bad_reason)) { + bad_page(page, bad_reason, bad_flags); return 1; } - reset_page_last_nid(page); + page_cpupid_reset_last(page); if (page->flags & PAGE_FLAGS_CHECK_AT_PREP) page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; return 0; @@ -630,7 +682,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, int to_free = count; spin_lock(&zone->lock); - zone->all_unreclaimable = 0; zone->pages_scanned = 0; while (to_free) { @@ -663,9 +714,9 @@ static void free_pcppages_bulk(struct zone *zone, int count, list_del(&page->lru); mt = get_freepage_migratetype(page); /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, mt); + __free_one_page(page, page_to_pfn(page), zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); - if (likely(get_pageblock_migratetype(page) != MIGRATE_ISOLATE)) { + if (likely(!is_migrate_isolate_page(page))) { __mod_zone_page_state(zone, NR_FREE_PAGES, 1); if (is_migrate_cma(mt)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); @@ -675,15 +726,16 @@ static void free_pcppages_bulk(struct zone *zone, int count, spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order, +static void free_one_page(struct zone *zone, + struct page *page, unsigned long pfn, + unsigned int order, int migratetype) { spin_lock(&zone->lock); - zone->all_unreclaimable = 0; zone->pages_scanned = 0; - __free_one_page(page, zone, order, migratetype); - if (unlikely(migratetype != MIGRATE_ISOLATE)) + __free_one_page(page, pfn, zone, order, migratetype); + if (unlikely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); spin_unlock(&zone->lock); } @@ -704,7 +756,8 @@ static bool free_pages_prepare(struct page *page, unsigned int order) return false; if (!PageHighMem(page)) { - debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order); + debug_check_no_locks_freed(page_address(page), + PAGE_SIZE << order); debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } @@ -718,47 +771,41 @@ static void __free_pages_ok(struct page *page, unsigned int order) { unsigned long flags; int migratetype; + unsigned long pfn = page_to_pfn(page); if (!free_pages_prepare(page, order)) return; + migratetype = get_pfnblock_migratetype(page, pfn); local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); - migratetype = get_pageblock_migratetype(page); set_freepage_migratetype(page, migratetype); - free_one_page(page_zone(page), page, order, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype); local_irq_restore(flags); } -/* - * Read access to zone->managed_pages is safe because it's unsigned long, - * but we still need to serialize writers. Currently all callers of - * __free_pages_bootmem() except put_page_bootmem() should only be used - * at boot time. So for shorter boot time, we shift the burden to - * put_page_bootmem() to serialize writers. - */ -void __meminit __free_pages_bootmem(struct page *page, unsigned int order) +void __init __free_pages_bootmem(struct page *page, unsigned int order) { unsigned int nr_pages = 1 << order; + struct page *p = page; unsigned int loop; - prefetchw(page); - for (loop = 0; loop < nr_pages; loop++) { - struct page *p = &page[loop]; - - if (loop + 1 < nr_pages) - prefetchw(p + 1); + prefetchw(p); + for (loop = 0; loop < (nr_pages - 1); loop++, p++) { + prefetchw(p + 1); __ClearPageReserved(p); set_page_count(p, 0); } + __ClearPageReserved(p); + set_page_count(p, 0); - page_zone(page)->managed_pages += 1 << order; + page_zone(page)->managed_pages += nr_pages; set_page_refcounted(page); __free_pages(page, order); } #ifdef CONFIG_CMA -/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */ +/* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void __init init_cma_reserved_pageblock(struct page *page) { unsigned i = pageblock_nr_pages; @@ -769,10 +816,22 @@ void __init init_cma_reserved_pageblock(struct page *page) set_page_count(p, 0); } while (++p, --i); - set_page_refcounted(page); set_pageblock_migratetype(page, MIGRATE_CMA); - __free_pages(page, pageblock_order); - totalram_pages += pageblock_nr_pages; + + if (pageblock_order >= MAX_ORDER) { + i = pageblock_nr_pages; + p = page; + do { + set_page_refcounted(p); + __free_pages(p, MAX_ORDER - 1); + p += MAX_ORDER_NR_PAGES; + } while (i -= MAX_ORDER_NR_PAGES); + } else { + set_page_refcounted(page); + __free_pages(page, pageblock_order); + } + + adjust_managed_page_count(page, pageblock_nr_pages); } #endif @@ -800,7 +859,7 @@ static inline void expand(struct zone *zone, struct page *page, area--; high--; size >>= 1; - VM_BUG_ON(bad_range(zone, &page[size])); + VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); #ifdef CONFIG_DEBUG_PAGEALLOC if (high < debug_guardpage_minorder()) { @@ -830,18 +889,29 @@ static inline void expand(struct zone *zone, struct page *page, */ static inline int check_new_page(struct page *page) { - if (unlikely(page_mapcount(page) | - (page->mapping != NULL) | - (atomic_read(&page->_count) != 0) | - (page->flags & PAGE_FLAGS_CHECK_AT_PREP) | - (mem_cgroup_bad_page_check(page)))) { - bad_page(page); + const char *bad_reason = NULL; + unsigned long bad_flags = 0; + + if (unlikely(page_mapcount(page))) + bad_reason = "nonzero mapcount"; + if (unlikely(page->mapping != NULL)) + bad_reason = "non-NULL mapping"; + if (unlikely(atomic_read(&page->_count) != 0)) + bad_reason = "nonzero _count"; + if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { + bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; + bad_flags = PAGE_FLAGS_CHECK_AT_PREP; + } + if (unlikely(mem_cgroup_bad_page_check(page))) + bad_reason = "cgroup check failed"; + if (unlikely(bad_reason)) { + bad_page(page, bad_reason, bad_flags); return 1; } return 0; } -static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) +static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) { int i; @@ -875,7 +945,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, int migratetype) { unsigned int current_order; - struct free_area * area; + struct free_area *area; struct page *page; /* Find a page of the appropriate size in the preferred list */ @@ -890,6 +960,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, rmv_page_order(page); area->nr_free--; expand(zone, page, order, current_order, area, migratetype); + set_freepage_migratetype(page, migratetype); return page; } @@ -911,7 +982,9 @@ static int fallbacks[MIGRATE_TYPES][4] = { [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, #endif [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ +#ifdef CONFIG_MEMORY_ISOLATION [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ +#endif }; /* @@ -940,7 +1013,7 @@ int move_freepages(struct zone *zone, for (page = start_page; page <= end_page;) { /* Make sure we are not inadvertently changing nodes */ - VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone)); + VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); if (!pfn_valid_within(page_to_pfn(page))) { page++; @@ -976,9 +1049,9 @@ int move_freepages_block(struct zone *zone, struct page *page, end_pfn = start_pfn + pageblock_nr_pages - 1; /* Do not cross zone boundaries */ - if (start_pfn < zone->zone_start_pfn) + if (!zone_spans_pfn(zone, start_pfn)) start_page = page; - if (end_pfn >= zone->zone_start_pfn + zone->spanned_pages) + if (!zone_spans_pfn(zone, end_pfn)) return 0; return move_freepages(zone, start_page, end_page, migratetype); @@ -995,18 +1068,71 @@ static void change_pageblock_range(struct page *pageblock_page, } } +/* + * If breaking a large block of pages, move all free pages to the preferred + * allocation list. If falling back for a reclaimable kernel allocation, be + * more aggressive about taking ownership of free pages. + * + * On the other hand, never change migration type of MIGRATE_CMA pageblocks + * nor move CMA pages to different free lists. We don't want unmovable pages + * to be allocated from MIGRATE_CMA areas. + * + * Returns the new migratetype of the pageblock (or the same old migratetype + * if it was unchanged). + */ +static int try_to_steal_freepages(struct zone *zone, struct page *page, + int start_type, int fallback_type) +{ + int current_order = page_order(page); + + /* + * When borrowing from MIGRATE_CMA, we need to release the excess + * buddy pages to CMA itself. We also ensure the freepage_migratetype + * is set to CMA so it is returned to the correct freelist in case + * the page ends up being not actually allocated from the pcp lists. + */ + if (is_migrate_cma(fallback_type)) + return fallback_type; + + /* Take ownership for orders >= pageblock_order */ + if (current_order >= pageblock_order) { + change_pageblock_range(page, current_order, start_type); + return start_type; + } + + if (current_order >= pageblock_order / 2 || + start_type == MIGRATE_RECLAIMABLE || + page_group_by_mobility_disabled) { + int pages; + + pages = move_freepages_block(zone, page, start_type); + + /* Claim the whole block if over half of it is free */ + if (pages >= (1 << (pageblock_order-1)) || + page_group_by_mobility_disabled) { + + set_pageblock_migratetype(page, start_type); + return start_type; + } + + } + + return fallback_type; +} + /* Remove an element from the buddy allocator from the fallback list */ static inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) +__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) { - struct free_area * area; - int current_order; + struct free_area *area; + unsigned int current_order; struct page *page; - int migratetype, i; + int migratetype, new_type, i; /* Find the largest possible block of pages in the other list */ - for (current_order = MAX_ORDER-1; current_order >= order; - --current_order) { + for (current_order = MAX_ORDER-1; + current_order >= order && current_order <= MAX_ORDER-1; + --current_order) { for (i = 0;; i++) { migratetype = fallbacks[start_migratetype][i]; @@ -1022,51 +1148,25 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) struct page, lru); area->nr_free--; - /* - * If breaking a large block of pages, move all free - * pages to the preferred allocation list. If falling - * back for a reclaimable kernel allocation, be more - * aggressive about taking ownership of free pages - * - * On the other hand, never change migration - * type of MIGRATE_CMA pageblocks nor move CMA - * pages on different free lists. We don't - * want unmovable pages to be allocated from - * MIGRATE_CMA areas. - */ - if (!is_migrate_cma(migratetype) && - (unlikely(current_order >= pageblock_order / 2) || - start_migratetype == MIGRATE_RECLAIMABLE || - page_group_by_mobility_disabled)) { - int pages; - pages = move_freepages_block(zone, page, - start_migratetype); - - /* Claim the whole block if over half of it is free */ - if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) - set_pageblock_migratetype(page, - start_migratetype); - - migratetype = start_migratetype; - } + new_type = try_to_steal_freepages(zone, page, + start_migratetype, + migratetype); /* Remove the page from the freelists */ list_del(&page->lru); rmv_page_order(page); - /* Take ownership for orders >= pageblock_order */ - if (current_order >= pageblock_order && - !is_migrate_cma(migratetype)) - change_pageblock_range(page, current_order, - start_migratetype); - expand(zone, page, order, current_order, area, - is_migrate_cma(migratetype) - ? migratetype : start_migratetype); + new_type); + /* The freepage_migratetype may differ from pageblock's + * migratetype depending on the decisions in + * try_to_steal_freepages. This is OK as long as it does + * not differ for MIGRATE_CMA type. + */ + set_freepage_migratetype(page, new_type); trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype); + start_migratetype, migratetype, new_type); return page; } @@ -1112,9 +1212,9 @@ retry_reserve: */ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, - int migratetype, int cold) + int migratetype, bool cold) { - int mt = migratetype, i; + int i; spin_lock(&zone->lock); for (i = 0; i < count; ++i) { @@ -1131,18 +1231,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * merge IO requests if the physical pages are ordered * properly. */ - if (likely(cold == 0)) + if (likely(!cold)) list_add(&page->lru, list); else list_add_tail(&page->lru, list); - if (IS_ENABLED(CONFIG_CMA)) { - mt = get_pageblock_migratetype(page); - if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE) - mt = migratetype; - } - set_freepage_migratetype(page, mt); list = &page->lru; - if (is_migrate_cma(mt)) + if (is_migrate_cma(get_freepage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, -(1 << order)); } @@ -1164,10 +1258,12 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { unsigned long flags; int to_drain; + unsigned long batch; local_irq_save(flags); - if (pcp->count >= pcp->batch) - to_drain = pcp->batch; + batch = ACCESS_ONCE(pcp->batch); + if (pcp->count >= batch) + to_drain = batch; else to_drain = pcp->count; if (to_drain > 0) { @@ -1264,15 +1360,15 @@ void mark_free_pages(struct zone *zone) { unsigned long pfn, max_zone_pfn; unsigned long flags; - int order, t; + unsigned int order, t; struct list_head *curr; - if (!zone->spanned_pages) + if (zone_is_empty(zone)) return; spin_lock_irqsave(&zone->lock, flags); - max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages; + max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (pfn_valid(pfn)) { struct page *page = pfn_to_page(pfn); @@ -1296,19 +1392,20 @@ void mark_free_pages(struct zone *zone) /* * Free a 0-order page - * cold == 1 ? free a cold page : free a hot page + * cold == true ? free a cold page : free a hot page */ -void free_hot_cold_page(struct page *page, int cold) +void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + unsigned long pfn = page_to_pfn(page); int migratetype; if (!free_pages_prepare(page, 0)) return; - migratetype = get_pageblock_migratetype(page); + migratetype = get_pfnblock_migratetype(page, pfn); set_freepage_migratetype(page, migratetype); local_irq_save(flags); __count_vm_event(PGFREE); @@ -1321,22 +1418,23 @@ void free_hot_cold_page(struct page *page, int cold) * excessively into the page allocator */ if (migratetype >= MIGRATE_PCPTYPES) { - if (unlikely(migratetype == MIGRATE_ISOLATE)) { - free_one_page(zone, page, 0, migratetype); + if (unlikely(is_migrate_isolate(migratetype))) { + free_one_page(zone, page, pfn, 0, migratetype); goto out; } migratetype = MIGRATE_MOVABLE; } pcp = &this_cpu_ptr(zone->pageset)->pcp; - if (cold) - list_add_tail(&page->lru, &pcp->lists[migratetype]); - else + if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); + else + list_add_tail(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { - free_pcppages_bulk(zone, pcp->batch, pcp); - pcp->count -= pcp->batch; + unsigned long batch = ACCESS_ONCE(pcp->batch); + free_pcppages_bulk(zone, batch, pcp); + pcp->count -= batch; } out: @@ -1346,7 +1444,7 @@ out: /* * Free a list of 0-order pages */ -void free_hot_cold_page_list(struct list_head *list, int cold) +void free_hot_cold_page_list(struct list_head *list, bool cold) { struct page *page, *next; @@ -1368,8 +1466,8 @@ void split_page(struct page *page, unsigned int order) { int i; - VM_BUG_ON(PageCompound(page)); - VM_BUG_ON(!page_count(page)); + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!page_count(page), page); #ifdef CONFIG_KMEMCHECK /* @@ -1383,6 +1481,7 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); } +EXPORT_SYMBOL_GPL(split_page); static int __isolate_free_page(struct page *page, unsigned int order) { @@ -1395,7 +1494,7 @@ static int __isolate_free_page(struct page *page, unsigned int order) zone = page_zone(page); mt = get_pageblock_migratetype(page); - if (mt != MIGRATE_ISOLATE) { + if (!is_migrate_isolate(mt)) { /* Obey watermarks as if the page was being allocated */ watermark = low_wmark_pages(zone) + (1 << order); if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) @@ -1414,7 +1513,7 @@ static int __isolate_free_page(struct page *page, unsigned int order) struct page *endpage = page + (1 << order) - 1; for (; page < endpage; page += pageblock_nr_pages) { int mt = get_pageblock_migratetype(page); - if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt)) + if (!is_migrate_isolate(mt) && !is_migrate_cma(mt)) set_pageblock_migratetype(page, MIGRATE_MOVABLE); } @@ -1457,12 +1556,12 @@ int split_free_page(struct page *page) */ static inline struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags, - int migratetype) + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype) { unsigned long flags; struct page *page; - int cold = !!(gfp_flags & __GFP_COLD); + bool cold = ((gfp_flags & __GFP_COLD) != 0); again: if (likely(order == 0)) { @@ -1507,14 +1606,16 @@ again: if (!page) goto failed; __mod_zone_freepage_state(zone, -(1 << order), - get_pageblock_migratetype(page)); + get_freepage_migratetype(page)); } + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); local_irq_restore(flags); - VM_BUG_ON(bad_range(zone, page)); + VM_BUG_ON_PAGE(bad_range(zone, page), page); if (prep_new_page(page, order, gfp_flags)) goto again; return page; @@ -1605,13 +1706,15 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ -static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags, long free_pages) +static bool __zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags, + long free_pages) { /* free_pages my go negative - that's OK */ long min = mark; long lowmem_reserve = z->lowmem_reserve[classzone_idx]; int o; + long free_cma = 0; free_pages -= (1 << order) - 1; if (alloc_flags & ALLOC_HIGH) @@ -1621,9 +1724,10 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, #ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ if (!(alloc_flags & ALLOC_CMA)) - free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES); + free_cma = zone_page_state(z, NR_FREE_CMA_PAGES); #endif - if (free_pages <= min + lowmem_reserve) + + if (free_pages - free_cma <= min + lowmem_reserve) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ @@ -1638,15 +1742,15 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, return true; } -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, +bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, int alloc_flags) { return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, zone_page_state(z, NR_FREE_PAGES)); } -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags) { long free_pages = zone_page_state(z, NR_FREE_PAGES); @@ -1665,7 +1769,7 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, * comments in mmzone.h. Reduces cache footprint of zonelist scans * that have to skip over a lot of full or unallowed zones. * - * If the zonelist cache is present in the passed in zonelist, then + * If the zonelist cache is present in the passed zonelist, then * returns a pointer to the allowed node mask (either the current * tasks mems_allowed, or node_states[N_MEMORY].) * @@ -1774,20 +1878,15 @@ static void zlc_clear_zones_full(struct zonelist *zonelist) bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); } -static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) +static bool zone_local(struct zone *local_zone, struct zone *zone) { - return node_isset(local_zone->node, zone->zone_pgdat->reclaim_nodes); + return local_zone->node == zone->node; } -static void __paginginit init_zone_allows_reclaim(int nid) +static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { - int i; - - for_each_online_node(i) - if (node_distance(nid, i) <= RECLAIM_DISTANCE) - node_set(i, NODE_DATA(nid)->reclaim_nodes); - else - zone_reclaim_mode = 1; + return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) < + RECLAIM_DISTANCE; } #else /* CONFIG_NUMA */ @@ -1811,14 +1910,16 @@ static void zlc_clear_zones_full(struct zonelist *zonelist) { } -static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) +static bool zone_local(struct zone *local_zone, struct zone *zone) { return true; } -static inline void init_zone_allows_reclaim(int nid) +static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { + return true; } + #endif /* CONFIG_NUMA */ /* @@ -1828,31 +1929,46 @@ static inline void init_zone_allows_reclaim(int nid) static struct page * get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, struct zonelist *zonelist, int high_zoneidx, int alloc_flags, - struct zone *preferred_zone, int migratetype) + struct zone *preferred_zone, int classzone_idx, int migratetype) { struct zoneref *z; struct page *page = NULL; - int classzone_idx; 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 */ + bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) && + (gfp_mask & __GFP_WRITE); - classzone_idx = zone_idx(preferred_zone); zonelist_scan: /* * Scan zonelist, looking for a zone with enough free. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, nodemask) { + unsigned long mark; + if (IS_ENABLED(CONFIG_NUMA) && zlc_active && !zlc_zone_worth_trying(zonelist, z, allowednodes)) continue; - if ((alloc_flags & ALLOC_CPUSET) && + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed_softwall(zone, gfp_mask)) continue; /* + * Distribute pages in proportion to the individual + * zone size to ensure fair page aging. The zone a + * page was allocated in should have no effect on the + * time the page has in memory before being reclaimed. + */ + if (alloc_flags & ALLOC_FAIR) { + if (!zone_local(preferred_zone, zone)) + continue; + if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) + continue; + } + /* * When allocating a page cache page for writing, we * want to get it from a zone that is within its dirty * limit, such that no single zone holds more than its @@ -1878,18 +1994,17 @@ zonelist_scan: * will require awareness of zones in the * dirty-throttling and the flusher threads. */ - if ((alloc_flags & ALLOC_WMARK_LOW) && - (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone)) - goto this_zone_full; + if (consider_zone_dirty && !zone_dirty_ok(zone)) + continue; - BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); - if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { - unsigned long mark; + mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; + if (!zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) { int ret; - mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; - if (zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) + /* Checked here to keep the fast path fast */ + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); + if (alloc_flags & ALLOC_NO_WATERMARKS) goto try_this_zone; if (IS_ENABLED(CONFIG_NUMA) && @@ -1926,9 +2041,24 @@ zonelist_scan: continue; default: /* did we reclaim enough */ - if (!zone_watermark_ok(zone, order, mark, + if (zone_watermark_ok(zone, order, mark, classzone_idx, alloc_flags)) + goto try_this_zone; + + /* + * Failed to reclaim enough to meet watermark. + * Only mark the zone full if checking the min + * watermark or if we failed to reclaim just + * 1<<order pages or else the page allocator + * fastpath will prematurely mark zones full + * when the watermark is between the low and + * min watermarks. + */ + if (((alloc_flags & ALLOC_WMARK_MASK) == ALLOC_WMARK_MIN) || + ret == ZONE_RECLAIM_SOME) goto this_zone_full; + + continue; } } @@ -1938,7 +2068,7 @@ try_this_zone: if (page) break; this_zone_full: - if (IS_ENABLED(CONFIG_NUMA)) + if (IS_ENABLED(CONFIG_NUMA) && zlc_active) zlc_mark_zone_full(zonelist, z); } @@ -2067,7 +2197,7 @@ static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; @@ -2085,7 +2215,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, ALLOC_WMARK_HIGH|ALLOC_CPUSET, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto out; @@ -2120,7 +2250,7 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, + int classzone_idx, int migratetype, enum migrate_mode mode, bool *contended_compaction, bool *deferred_compaction, unsigned long *did_some_progress) { @@ -2134,7 +2264,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, sync_migration, + nodemask, mode, contended_compaction); current->flags &= ~PF_MEMALLOC; @@ -2148,13 +2278,10 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) { preferred_zone->compact_blockskip_flush = false; - preferred_zone->compact_considered = 0; - preferred_zone->compact_defer_shift = 0; - if (order >= preferred_zone->compact_order_failed) - preferred_zone->compact_order_failed = order + 1; + compaction_defer_reset(preferred_zone, order, true); count_vm_event(COMPACTSUCCESS); return page; } @@ -2170,7 +2297,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * As async compaction considers a subset of pageblocks, only * defer if the failure was a sync compaction failure. */ - if (sync_migration) + if (mode != MIGRATE_ASYNC) defer_compaction(preferred_zone, order); cond_resched(); @@ -2183,9 +2310,9 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, - bool *contended_compaction, bool *deferred_compaction, - unsigned long *did_some_progress) + int classzone_idx, int migratetype, + enum migrate_mode mode, bool *contended_compaction, + bool *deferred_compaction, unsigned long *did_some_progress) { return NULL; } @@ -2224,7 +2351,7 @@ static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int classzone_idx, int migratetype, unsigned long *did_some_progress) { struct page *page = NULL; bool drained = false; @@ -2242,7 +2369,8 @@ retry: page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, + migratetype); /* * If an allocation failed after direct reclaim, it could be because @@ -2265,14 +2393,14 @@ static inline struct page * __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; do { page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); @@ -2281,23 +2409,45 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, return page; } -static inline -void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, - enum zone_type high_zoneidx, - enum zone_type classzone_idx) +static void reset_alloc_batches(struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) +{ + struct zoneref *z; + struct zone *zone; + + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + /* + * Only reset the batches of zones that were actually + * considered in the fairness pass, we don't want to + * trash fairness information for zones that are not + * actually part of this zonelist's round-robin cycle. + */ + if (!zone_local(preferred_zone, zone)) + continue; + mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); + } +} + +static void wake_all_kswapds(unsigned int order, + struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) { struct zoneref *z; struct zone *zone; for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - wakeup_kswapd(zone, order, classzone_idx); + wakeup_kswapd(zone, order, zone_idx(preferred_zone)); } static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const gfp_t wait = gfp_mask & __GFP_WAIT; + const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2306,20 +2456,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (!wait) { + if (atomic) { /* - * Not worth trying to allocate harder for - * __GFP_NOMEMALLOC even if it can't schedule. + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. */ - if (!(gfp_mask & __GFP_NOMEMALLOC)) + if (!(gfp_mask & __GFP_NOMEMALLOC)) alloc_flags |= ALLOC_HARDER; /* - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the + * comment for __cpuset_node_allowed_softwall(). */ alloc_flags &= ~ALLOC_CPUSET; } else if (unlikely(rt_task(current)) && !in_interrupt()) @@ -2351,14 +2501,14 @@ static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { const gfp_t wait = gfp_mask & __GFP_WAIT; struct page *page = NULL; int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - bool sync_migration = false; + enum migrate_mode migration_mode = MIGRATE_ASYNC; bool deferred_compaction = false; bool contended_compaction = false; @@ -2382,13 +2532,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, * over allocated. */ if (IS_ENABLED(CONFIG_NUMA) && - (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; restart: if (!(gfp_mask & __GFP_NO_KSWAPD)) - wake_all_kswapd(order, zonelist, high_zoneidx, - zone_idx(preferred_zone)); + wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone); /* * OK, we're below the kswapd watermark and have kicked background @@ -2401,15 +2550,18 @@ restart: * Find the true preferred zone if the allocation is unconstrained by * cpusets. */ - if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) - first_zones_zonelist(zonelist, high_zoneidx, NULL, - &preferred_zone); + if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) { + struct zoneref *preferred_zoneref; + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, + NULL, &preferred_zone); + classzone_idx = zonelist_zone_idx(preferred_zoneref); + } rebalance: /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto got_pg; @@ -2424,15 +2576,22 @@ rebalance: page = __alloc_pages_high_priority(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) { goto got_pg; } } /* Atomic allocations - we can't balance anything */ - if (!wait) + if (!wait) { + /* + * All existing users of the deprecated __GFP_NOFAIL are + * blockable, so warn of any new users that actually allow this + * type of allocation to fail. + */ + WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL); goto nopage; + } /* Avoid recursion of direct reclaim */ if (current->flags & PF_MEMALLOC) @@ -2446,17 +2605,23 @@ rebalance: * Try direct compaction. The first pass is asynchronous. Subsequent * attempts after direct reclaim are synchronous */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) goto got_pg; - sync_migration = true; + + /* + * It can become very expensive to allocate transparent hugepages at + * fault, so use asynchronous memory compaction for THP unless it is + * khugepaged trying to collapse. + */ + if (!(gfp_mask & __GFP_NO_KSWAPD) || (current->flags & PF_KTHREAD)) + migration_mode = MIGRATE_SYNC_LIGHT; /* * If compaction is deferred for high-order allocations, it is because @@ -2473,7 +2638,8 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + classzone_idx, migratetype, + &did_some_progress); if (page) goto got_pg; @@ -2482,7 +2648,7 @@ rebalance: * running out of options and have to consider going OOM */ if (!did_some_progress) { - if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { + if (oom_gfp_allowed(gfp_mask)) { if (oom_killer_disabled) goto nopage; /* Coredumps can quickly deplete all memory reserves */ @@ -2492,7 +2658,7 @@ rebalance: page = __alloc_pages_may_oom(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, - migratetype); + classzone_idx, migratetype); if (page) goto got_pg; @@ -2531,12 +2697,11 @@ rebalance: * direct reclaim and reclaim/compaction depends on compaction * being called after reclaim so call directly if necessary */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) @@ -2562,11 +2727,12 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, { enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zone *preferred_zone; + struct zoneref *preferred_zoneref; struct page *page = NULL; int migratetype = allocflags_to_migratetype(gfp_mask); unsigned int cpuset_mems_cookie; - int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET; - struct mem_cgroup *memcg = NULL; + int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; + int classzone_idx; gfp_mask &= gfp_allowed_mask; @@ -2585,35 +2751,53 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (unlikely(!zonelist->_zonerefs->zone)) return NULL; - /* - * Will only have any effect when __GFP_KMEMCG is set. This is - * verified in the (always inline) callee - */ - if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) - return NULL; - retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* The preferred zone is used for statistics later */ - first_zones_zonelist(zonelist, high_zoneidx, + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, nodemask ? : &cpuset_current_mems_allowed, &preferred_zone); if (!preferred_zone) goto out; + classzone_idx = zonelist_zone_idx(preferred_zoneref); #ifdef CONFIG_CMA if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; #endif +retry: /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, alloc_flags, - preferred_zone, migratetype); - if (unlikely(!page)) + preferred_zone, classzone_idx, migratetype); + if (unlikely(!page)) { + /* + * The first pass makes sure allocations are spread + * fairly within the local node. However, the local + * node might have free pages left after the fairness + * batches are exhausted, and remote zones haven't + * even been considered yet. Try once more without + * fairness, and include remote zones now, before + * entering the slowpath and waking kswapd: prefer + * spilling to a remote zone over swapping locally. + */ + if (alloc_flags & ALLOC_FAIR) { + reset_alloc_batches(zonelist, high_zoneidx, + preferred_zone); + alloc_flags &= ~ALLOC_FAIR; + goto retry; + } + /* + * Runtime PM, block IO and its error handling path + * can deadlock because I/O on the device might not + * complete. + */ + gfp_mask = memalloc_noio_flags(gfp_mask); page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); + } trace_mm_page_alloc(page, order, gfp_mask, migratetype); @@ -2624,11 +2808,9 @@ out: * the mask is being updated. If a page allocation is about to fail, * check if the cpuset changed during allocation and if so, retry. */ - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; - memcg_kmem_commit_charge(page, memcg, order); - return page; } EXPORT_SYMBOL(__alloc_pages_nodemask); @@ -2663,7 +2845,7 @@ void __free_pages(struct page *page, unsigned int order) { if (put_page_testzero(page)) { if (order == 0) - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); else __free_pages_ok(page, order); } @@ -2682,27 +2864,51 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); /* - * __free_memcg_kmem_pages and free_memcg_kmem_pages will free - * pages allocated with __GFP_KMEMCG. + * alloc_kmem_pages charges newly allocated pages to the kmem resource counter + * of the current memory cgroup. * - * Those pages are accounted to a particular memcg, embedded in the - * corresponding page_cgroup. To avoid adding a hit in the allocator to search - * for that information only to find out that it is NULL for users who have no - * interest in that whatsoever, we provide these functions. - * - * The caller knows better which flags it relies on. + * It should be used when the caller would like to use kmalloc, but since the + * allocation is large, it has to fall back to the page allocator. */ -void __free_memcg_kmem_pages(struct page *page, unsigned int order) +struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order) +{ + struct page *page; + struct mem_cgroup *memcg = NULL; + + if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) + return NULL; + page = alloc_pages(gfp_mask, order); + memcg_kmem_commit_charge(page, memcg, order); + return page; +} + +struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order) +{ + struct page *page; + struct mem_cgroup *memcg = NULL; + + if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) + return NULL; + page = alloc_pages_node(nid, gfp_mask, order); + memcg_kmem_commit_charge(page, memcg, order); + return page; +} + +/* + * __free_kmem_pages and free_kmem_pages will free pages allocated with + * alloc_kmem_pages. + */ +void __free_kmem_pages(struct page *page, unsigned int order) { memcg_kmem_uncharge_pages(page, order); __free_pages(page, order); } -void free_memcg_kmem_pages(unsigned long addr, unsigned int order) +void free_kmem_pages(unsigned long addr, unsigned int order) { if (addr != 0) { VM_BUG_ON(!virt_addr_valid((void *)addr)); - __free_memcg_kmem_pages(virt_to_page((void *)addr), order); + __free_kmem_pages(virt_to_page((void *)addr), order); } } @@ -2785,18 +2991,27 @@ void free_pages_exact(void *virt, size_t size) } EXPORT_SYMBOL(free_pages_exact); -static unsigned int nr_free_zone_pages(int offset) +/** + * nr_free_zone_pages - count number of pages beyond high watermark + * @offset: The zone index of the highest zone + * + * nr_free_zone_pages() counts the number of counts pages which are beyond the + * high watermark within all zones at or below a given zone index. For each + * zone, the number of pages is calculated as: + * managed_pages - high_pages + */ +static unsigned long nr_free_zone_pages(int offset) { struct zoneref *z; struct zone *zone; /* Just pick one node, since fallback list is circular */ - unsigned int sum = 0; + unsigned long sum = 0; struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL); for_each_zone_zonelist(zone, z, zonelist, offset) { - unsigned long size = zone->present_pages; + unsigned long size = zone->managed_pages; unsigned long high = high_wmark_pages(zone); if (size > high) sum += size - high; @@ -2805,19 +3020,25 @@ static unsigned int nr_free_zone_pages(int offset) return sum; } -/* - * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL +/** + * nr_free_buffer_pages - count number of pages beyond high watermark + * + * nr_free_buffer_pages() counts the number of pages which are beyond the high + * watermark within ZONE_DMA and ZONE_NORMAL. */ -unsigned int nr_free_buffer_pages(void) +unsigned long nr_free_buffer_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_USER)); } EXPORT_SYMBOL_GPL(nr_free_buffer_pages); -/* - * Amount of free RAM allocatable within all zones +/** + * nr_free_pagecache_pages - count number of pages beyond high watermark + * + * nr_free_pagecache_pages() counts the number of pages which are beyond the + * high watermark within all zones. */ -unsigned int nr_free_pagecache_pages(void) +unsigned long nr_free_pagecache_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE)); } @@ -2844,12 +3065,16 @@ EXPORT_SYMBOL(si_meminfo); #ifdef CONFIG_NUMA void si_meminfo_node(struct sysinfo *val, int nid) { + int zone_type; /* needs to be signed */ + unsigned long managed_pages = 0; pg_data_t *pgdat = NODE_DATA(nid); - val->totalram = pgdat->node_present_pages; + for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) + managed_pages += pgdat->node_zones[zone_type].managed_pages; + val->totalram = managed_pages; val->freeram = node_page_state(nid, NR_FREE_PAGES); #ifdef CONFIG_HIGHMEM - val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages; + val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages; val->freehigh = zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM], NR_FREE_PAGES); #else @@ -2873,9 +3098,9 @@ bool skip_free_areas_node(unsigned int flags, int nid) goto out; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); ret = !node_isset(nid, cpuset_current_mems_allowed); - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); out: return ret; } @@ -2892,7 +3117,9 @@ static void show_migration_types(unsigned char type) #ifdef CONFIG_CMA [MIGRATE_CMA] = 'C', #endif +#ifdef CONFIG_MEMORY_ISOLATION [MIGRATE_ISOLATE] = 'I', +#endif }; char tmp[MIGRATE_TYPES + 1]; char *p = tmp; @@ -3027,7 +3254,7 @@ void show_free_areas(unsigned int filter) K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), zone->pages_scanned, - (zone->all_unreclaimable ? "yes" : "no") + (!zone_reclaimable(zone) ? "yes" : "no") ); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) @@ -3036,7 +3263,7 @@ void show_free_areas(unsigned int filter) } for_each_populated_zone(zone) { - unsigned long nr[MAX_ORDER], flags, order, total = 0; + unsigned long nr[MAX_ORDER], flags, order, total = 0; unsigned char types[MAX_ORDER]; if (skip_free_areas_node(filter, zone_to_nid(zone))) @@ -3067,6 +3294,8 @@ void show_free_areas(unsigned int filter) printk("= %lukB\n", K(total)); } + hugetlb_show_meminfo(); + printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES)); show_swap_cache_info(); @@ -3084,12 +3313,10 @@ static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref) * Add all populated zones of a node to the zonelist. */ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, - int nr_zones, enum zone_type zone_type) + int nr_zones) { struct zone *zone; - - BUG_ON(zone_type >= MAX_NR_ZONES); - zone_type++; + enum zone_type zone_type = MAX_NR_ZONES; do { zone_type--; @@ -3099,8 +3326,8 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, &zonelist->_zonerefs[nr_zones++]); check_highest_zone(zone_type); } - } while (zone_type); + return nr_zones; } @@ -3175,7 +3402,7 @@ early_param("numa_zonelist_order", setup_numa_zonelist_order); /* * sysctl handler for numa_zonelist_order */ -int numa_zonelist_order_handler(ctl_table *table, int write, +int numa_zonelist_order_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { @@ -3184,18 +3411,25 @@ int numa_zonelist_order_handler(ctl_table *table, int write, static DEFINE_MUTEX(zl_order_mutex); mutex_lock(&zl_order_mutex); - if (write) - strcpy(saved_string, (char*)table->data); + if (write) { + if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) { + ret = -EINVAL; + goto out; + } + strcpy(saved_string, (char *)table->data); + } ret = proc_dostring(table, write, buffer, length, ppos); if (ret) goto out; if (write) { int oldval = user_zonelist_order; - if (__parse_numa_zonelist_order((char*)table->data)) { + + ret = __parse_numa_zonelist_order((char *)table->data); + if (ret) { /* * bogus value. restore saved string */ - strncpy((char*)table->data, saved_string, + strncpy((char *)table->data, saved_string, NUMA_ZONELIST_ORDER_LEN); user_zonelist_order = oldval; } else if (oldval != user_zonelist_order) { @@ -3231,7 +3465,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) { int n, val; int min_val = INT_MAX; - int best_node = -1; + int best_node = NUMA_NO_NODE; const struct cpumask *tmp = cpumask_of_node(0); /* Use the local node if we haven't already */ @@ -3287,8 +3521,7 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node) zonelist = &pgdat->node_zonelists[0]; for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++) ; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, - MAX_NR_ZONES - 1); + j = build_zonelists_node(NODE_DATA(node), zonelist, j); zonelist->_zonerefs[j].zone = NULL; zonelist->_zonerefs[j].zone_idx = 0; } @@ -3302,7 +3535,7 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) struct zonelist *zonelist; zonelist = &pgdat->node_zonelists[1]; - j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1); + j = build_zonelists_node(pgdat, zonelist, 0); zonelist->_zonerefs[j].zone = NULL; zonelist->_zonerefs[j].zone_idx = 0; } @@ -3342,11 +3575,11 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) static int default_zonelist_order(void) { int nid, zone_type; - unsigned long low_kmem_size,total_size; + unsigned long low_kmem_size, total_size; struct zone *z; int average_size; /* - * ZONE_DMA and ZONE_DMA32 can be very small area in the system. + * ZONE_DMA and ZONE_DMA32 can be very small area in the system. * If they are really small and used heavily, the system can fall * into OOM very easily. * This function detect ZONE_DMA/DMA32 size and configures zone order. @@ -3359,8 +3592,8 @@ static int default_zonelist_order(void) z = &NODE_DATA(nid)->node_zones[zone_type]; if (populated_zone(z)) { if (zone_type < ZONE_NORMAL) - low_kmem_size += z->present_pages; - total_size += z->present_pages; + low_kmem_size += z->managed_pages; + total_size += z->managed_pages; } else if (zone_type == ZONE_NORMAL) { /* * If any node has only lowmem, then node order @@ -3378,9 +3611,9 @@ static int default_zonelist_order(void) return ZONELIST_ORDER_NODE; /* * look into each node's config. - * If there is a node whose DMA/DMA32 memory is very big area on - * local memory, NODE_ORDER may be suitable. - */ + * If there is a node whose DMA/DMA32 memory is very big area on + * local memory, NODE_ORDER may be suitable. + */ average_size = total_size / (nodes_weight(node_states[N_MEMORY]) + 1); for_each_online_node(nid) { @@ -3510,7 +3743,7 @@ static void build_zonelists(pg_data_t *pgdat) local_node = pgdat->node_id; zonelist = &pgdat->node_zonelists[0]; - j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1); + j = build_zonelists_node(pgdat, zonelist, 0); /* * Now we build the zonelist so that it contains the zones @@ -3523,14 +3756,12 @@ static void build_zonelists(pg_data_t *pgdat) for (node = local_node + 1; node < MAX_NUMNODES; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, - MAX_NR_ZONES - 1); + j = build_zonelists_node(NODE_DATA(node), zonelist, j); } for (node = 0; node < local_node; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, - MAX_NR_ZONES - 1); + j = build_zonelists_node(NODE_DATA(node), zonelist, j); } zonelist->_zonerefs[j].zone = NULL; @@ -3639,12 +3870,12 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) mminit_verify_zonelist(); cpuset_init_current_mems_allowed(); } else { - /* we have to stop all cpus to guarantee there is no user - of zonelist */ #ifdef CONFIG_MEMORY_HOTPLUG if (zone) setup_zone_pageset(zone); #endif + /* we have to stop all cpus to guarantee there is no user + of zonelist */ stop_machine(__build_all_zonelists, pgdat, NULL); /* cpuset refresh routine should be here */ } @@ -3738,8 +3969,6 @@ static inline unsigned long wait_table_bits(unsigned long size) return ffz(~size); } -#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) - /* * Check if a pageblock contains reserved pages */ @@ -3767,6 +3996,7 @@ static void setup_zone_migrate_reserve(struct zone *zone) struct page *page; unsigned long block_migratetype; int reserve; + int old_reserve; /* * Get the start pfn, end pfn and the number of blocks to reserve @@ -3775,7 +4005,7 @@ static void setup_zone_migrate_reserve(struct zone *zone) * the block. */ start_pfn = zone->zone_start_pfn; - end_pfn = start_pfn + zone->spanned_pages; + end_pfn = zone_end_pfn(zone); start_pfn = roundup(start_pfn, pageblock_nr_pages); reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >> pageblock_order; @@ -3788,6 +4018,12 @@ static void setup_zone_migrate_reserve(struct zone *zone) * future allocation of hugepages at runtime. */ reserve = min(2, reserve); + old_reserve = zone->nr_migrate_reserve_block; + + /* When memory hot-add, we almost always need to do nothing */ + if (reserve == old_reserve) + return; + zone->nr_migrate_reserve_block = reserve; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { if (!pfn_valid(pfn)) @@ -3825,6 +4061,12 @@ static void setup_zone_migrate_reserve(struct zone *zone) reserve--; continue; } + } else if (!old_reserve) { + /* + * At boot time we don't need to scan the whole zone + * for turning off MIGRATE_RESERVE. + */ + break; } /* @@ -3871,8 +4113,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, set_page_links(page, zone, nid, pfn); mminit_verify_page_links(page, zone, nid, pfn); init_page_count(page); - reset_page_mapcount(page); - reset_page_last_nid(page); + page_mapcount_reset(page); + page_cpupid_reset_last(page); SetPageReserved(page); /* * Mark the block movable so that blocks are reserved for @@ -3889,7 +4131,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * pfn out of zone. */ if ((z->zone_start_pfn <= pfn) - && (pfn < z->zone_start_pfn + z->spanned_pages) + && (pfn < zone_end_pfn(z)) && !(pfn & (pageblock_nr_pages - 1))) set_pageblock_migratetype(page, MIGRATE_MOVABLE); @@ -3904,7 +4146,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, static void __meminit zone_init_free_lists(struct zone *zone) { - int order, t; + unsigned int order, t; for_each_migratetype_order(order, t) { INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); zone->free_area[order].nr_free = 0; @@ -3916,7 +4158,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) #endif -static int __meminit zone_batchsize(struct zone *zone) +static int zone_batchsize(struct zone *zone) { #ifdef CONFIG_MMU int batch; @@ -3927,7 +4169,7 @@ static int __meminit zone_batchsize(struct zone *zone) * * OK, so we don't know how big the cache is. So guess. */ - batch = zone->present_pages / 1024; + batch = zone->managed_pages / 1024; if (batch * PAGE_SIZE > 512 * 1024) batch = (512 * 1024) / PAGE_SIZE; batch /= 4; /* We effectively *= 4 below */ @@ -3966,7 +4208,40 @@ static int __meminit zone_batchsize(struct zone *zone) #endif } -static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) +/* + * pcp->high and pcp->batch values are related and dependent on one another: + * ->batch must never be higher then ->high. + * The following function updates them in a safe manner without read side + * locking. + * + * Any new users of pcp->batch and pcp->high should ensure they can cope with + * those fields changing asynchronously (acording the the above rule). + * + * mutex_is_locked(&pcp_batch_high_lock) required when calling this function + * outside of boot time (or some other assurance that no concurrent updaters + * exist). + */ +static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, + unsigned long batch) +{ + /* start with a fail safe value for batch */ + pcp->batch = 1; + smp_wmb(); + + /* Update high, then batch, in order */ + pcp->high = high; + smp_wmb(); + + pcp->batch = batch; +} + +/* a companion to pageset_set_high() */ +static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch) +{ + pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch)); +} + +static void pageset_init(struct per_cpu_pageset *p) { struct per_cpu_pages *pcp; int migratetype; @@ -3975,45 +4250,55 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) pcp = &p->pcp; pcp->count = 0; - pcp->high = 6 * batch; - pcp->batch = max(1UL, 1 * batch); for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) INIT_LIST_HEAD(&pcp->lists[migratetype]); } +static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) +{ + pageset_init(p); + pageset_set_batch(p, batch); +} + /* - * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist + * pageset_set_high() sets the high water mark for hot per_cpu_pagelist * to the value high for the pageset p. */ - -static void setup_pagelist_highmark(struct per_cpu_pageset *p, +static void pageset_set_high(struct per_cpu_pageset *p, unsigned long high) { - struct per_cpu_pages *pcp; + unsigned long batch = max(1UL, high / 4); + if ((high / 4) > (PAGE_SHIFT * 8)) + batch = PAGE_SHIFT * 8; - pcp = &p->pcp; - pcp->high = high; - pcp->batch = max(1UL, high/4); - if ((high/4) > (PAGE_SHIFT * 8)) - pcp->batch = PAGE_SHIFT * 8; + pageset_update(&p->pcp, high, batch); } -static void __meminit setup_zone_pageset(struct zone *zone) +static void pageset_set_high_and_batch(struct zone *zone, + struct per_cpu_pageset *pcp) { - int cpu; - - zone->pageset = alloc_percpu(struct per_cpu_pageset); + if (percpu_pagelist_fraction) + pageset_set_high(pcp, + (zone->managed_pages / + percpu_pagelist_fraction)); + else + pageset_set_batch(pcp, zone_batchsize(zone)); +} - for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu); +static void __meminit zone_pageset_init(struct zone *zone, int cpu) +{ + struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu); - setup_pageset(pcp, zone_batchsize(zone)); + pageset_init(pcp); + pageset_set_high_and_batch(zone, pcp); +} - if (percpu_pagelist_fraction) - setup_pagelist_highmark(pcp, - (zone->present_pages / - percpu_pagelist_fraction)); - } +static void __meminit setup_zone_pageset(struct zone *zone) +{ + int cpu; + zone->pageset = alloc_percpu(struct per_cpu_pageset); + for_each_possible_cpu(cpu) + zone_pageset_init(zone, cpu); } /* @@ -4032,7 +4317,6 @@ static noinline __init_refok int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) { int i; - struct pglist_data *pgdat = zone->zone_pgdat; size_t alloc_size; /* @@ -4048,7 +4332,8 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!slab_is_available()) { zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node_nopanic(pgdat, alloc_size); + memblock_virt_alloc_node_nopanic( + alloc_size, zone->zone_pgdat->node_id); } else { /* * This case means that a zone whose size was 0 gets new memory @@ -4065,7 +4350,7 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!zone->wait_table) return -ENOMEM; - for(i = 0; i < zone->wait_table_hash_nr_entries; ++i) + for (i = 0; i < zone->wait_table_hash_nr_entries; ++i) init_waitqueue_head(zone->wait_table + i); return 0; @@ -4080,7 +4365,7 @@ static __meminit void zone_pcp_init(struct zone *zone) */ zone->pageset = &boot_pageset; - if (zone->present_pages) + if (populated_zone(zone)) printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n", zone->name, zone->present_pages, zone_batchsize(zone)); @@ -4115,20 +4400,29 @@ int __meminit init_currently_empty_zone(struct zone *zone, #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 __meminit __early_pfn_to_nid(unsigned long pfn) { unsigned long start_pfn, end_pfn; - int i, nid; + int nid; + /* + * NOTE: The following SMP-unsafe globals are only used early in boot + * when the kernel is running single-threaded. + */ + static unsigned long __meminitdata last_start_pfn, last_end_pfn; + static int __meminitdata last_nid; - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) - if (start_pfn <= pfn && pfn < end_pfn) - return nid; - /* This is a memory hole */ - return -1; + if (last_start_pfn <= pfn && pfn < last_end_pfn) + return last_nid; + + nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); + if (nid != -1) { + last_start_pfn = start_pfn; + last_end_pfn = end_pfn; + last_nid = nid; + } + + return nid; } #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ @@ -4156,13 +4450,13 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node) #endif /** - * free_bootmem_with_active_regions - Call free_bootmem_node for each active range + * free_bootmem_with_active_regions - Call memblock_free_early_nid 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 + * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid * - * 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. + * If an architecture guarantees that all ranges registered contain no holes + * and may be freed, this this function may be used instead of calling + * memblock_free_early_nid() manually. */ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) { @@ -4174,9 +4468,9 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) end_pfn = min(end_pfn, max_low_pfn); if (start_pfn < end_pfn) - free_bootmem_node(NODE_DATA(this_nid), - PFN_PHYS(start_pfn), - (end_pfn - start_pfn) << PAGE_SHIFT); + memblock_free_early_nid(PFN_PHYS(start_pfn), + (end_pfn - start_pfn) << PAGE_SHIFT, + this_nid); } } @@ -4184,9 +4478,8 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) * 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. + * If an architecture guarantees that all ranges registered 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) { @@ -4204,7 +4497,7 @@ void __init sparse_memory_present_with_active_regions(int nid) * @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 + * provided by memblock_set_node(). If called for a node * with no available memory, a warning is printed and the start and end * PFNs will be 0. */ @@ -4289,13 +4582,13 @@ static void __meminit adjust_zone_range_for_zone_movable(int nid, */ static unsigned long __meminit zone_spanned_pages_in_node(int nid, unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, 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); + /* Get the start and end of the zone */ zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type]; zone_end_pfn = arch_zone_highest_possible_pfn[zone_type]; adjust_zone_range_for_zone_movable(nid, zone_type, @@ -4350,14 +4643,14 @@ unsigned long __init absent_pages_in_range(unsigned long start_pfn, /* Return the number of page frames in holes in a zone on a node */ static unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, unsigned long *ignored) { unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; - 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 = clamp(node_start_pfn, zone_low, zone_high); zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); @@ -4370,6 +4663,8 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, #else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid, unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, unsigned long *zones_size) { return zones_size[zone_type]; @@ -4377,6 +4672,8 @@ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid, static inline unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, unsigned long *zholes_size) { if (!zholes_size) @@ -4388,21 +4685,27 @@ static inline unsigned long __meminit zone_absent_pages_in_node(int nid, #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, - unsigned long *zones_size, unsigned long *zholes_size) + unsigned long node_start_pfn, + unsigned long node_end_pfn, + 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); + node_start_pfn, + node_end_pfn, + 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); + node_start_pfn, node_end_pfn, + zholes_size); pgdat->node_present_pages = realtotalpages; printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); @@ -4416,10 +4719,11 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, * round what is now in bits to nearest long in bits, then return it in * bytes. */ -static unsigned long __init usemap_size(unsigned long zonesize) +static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize) { unsigned long usemapsize; + zonesize += zone_start_pfn & (pageblock_nr_pages-1); usemapsize = roundup(zonesize, pageblock_nr_pages); usemapsize = usemapsize >> pageblock_order; usemapsize *= NR_PAGEBLOCK_BITS; @@ -4429,23 +4733,26 @@ static unsigned long __init usemap_size(unsigned long zonesize) } static void __init setup_usemap(struct pglist_data *pgdat, - struct zone *zone, unsigned long zonesize) + struct zone *zone, + unsigned long zone_start_pfn, + unsigned long zonesize) { - unsigned long usemapsize = usemap_size(zonesize); + unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); zone->pageblock_flags = NULL; if (usemapsize) - zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat, - usemapsize); + zone->pageblock_flags = + memblock_virt_alloc_node_nopanic(usemapsize, + pgdat->node_id); } #else -static inline void setup_usemap(struct pglist_data *pgdat, - struct zone *zone, unsigned long zonesize) {} +static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, + unsigned long zone_start_pfn, unsigned long zonesize) {} #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ -void __init set_pageblock_order(void) +void __paginginit set_pageblock_order(void) { unsigned int order; @@ -4473,7 +4780,7 @@ void __init set_pageblock_order(void) * include/linux/pageblock-flags.h for the values of pageblock_order based on * the kernel config */ -void __init set_pageblock_order(void) +void __paginginit set_pageblock_order(void) { } @@ -4508,6 +4815,7 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages, * NOTE: pgdat should get zeroed by caller. */ static void __paginginit free_area_init_core(struct pglist_data *pgdat, + unsigned long node_start_pfn, unsigned long node_end_pfn, unsigned long *zones_size, unsigned long *zholes_size) { enum zone_type j; @@ -4529,8 +4837,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize, freesize, memmap_pages; - size = zone_spanned_pages_in_node(nid, j, zones_size); + size = zone_spanned_pages_in_node(nid, j, node_start_pfn, + node_end_pfn, zones_size); realsize = freesize = size - zone_absent_pages_in_node(nid, j, + node_start_pfn, + node_end_pfn, zholes_size); /* @@ -4565,7 +4876,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, nr_all_pages += freesize; zone->spanned_pages = size; - zone->present_pages = freesize; + zone->present_pages = realsize; /* * Set an approximate value for lowmem here, it will be adjusted * when the bootmem allocator frees pages into the buddy system. @@ -4583,14 +4894,17 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, spin_lock_init(&zone->lru_lock); zone_seqlock_init(zone); zone->zone_pgdat = pgdat; - zone_pcp_init(zone); + + /* For bootup, initialized properly in watermark setup */ + mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages); + lruvec_init(&zone->lruvec); if (!size) continue; set_pageblock_order(); - setup_usemap(pgdat, zone, size); + setup_usemap(pgdat, zone, zone_start_pfn, size); ret = init_currently_empty_zone(zone, zone_start_pfn, size, MEMMAP_EARLY); BUG_ON(ret); @@ -4617,12 +4931,13 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) * for the buddy allocator to function correctly. */ start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); - end = pgdat->node_start_pfn + pgdat->node_spanned_pages; + end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); map = alloc_remap(pgdat->node_id, size); if (!map) - map = alloc_bootmem_node_nopanic(pgdat, size); + map = memblock_virt_alloc_node_nopanic(size, + pgdat->node_id); pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); } #ifndef CONFIG_NEED_MULTIPLE_NODES @@ -4644,14 +4959,19 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, unsigned long node_start_pfn, unsigned long *zholes_size) { pg_data_t *pgdat = NODE_DATA(nid); + unsigned long start_pfn = 0; + unsigned long end_pfn = 0; /* pg_data_t should be reset to zero when it's allocated */ WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - init_zone_allows_reclaim(nid); - calculate_node_totalpages(pgdat, zones_size, zholes_size); +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); +#endif + calculate_node_totalpages(pgdat, start_pfn, end_pfn, + zones_size, zholes_size); alloc_node_mem_map(pgdat); #ifdef CONFIG_FLAT_NODE_MEM_MAP @@ -4660,7 +4980,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, (unsigned long)pgdat->node_mem_map); #endif - free_area_init_core(pgdat, zones_size, zholes_size); + free_area_init_core(pgdat, start_pfn, end_pfn, + zones_size, zholes_size); } #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -4669,7 +4990,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, /* * Figure out the number of possible node ids. */ -static void __init setup_nr_node_ids(void) +void __init setup_nr_node_ids(void) { unsigned int node; unsigned int highest = 0; @@ -4678,10 +4999,6 @@ static void __init setup_nr_node_ids(void) highest = node; nr_node_ids = highest + 1; } -#else -static inline void setup_nr_node_ids(void) -{ -} #endif /** @@ -4757,7 +5074,7 @@ static unsigned long __init find_min_pfn_for_node(int nid) * find_min_pfn_with_active_regions - Find the minimum PFN registered * * It returns the minimum PFN based on information provided via - * add_active_range(). + * memblock_set_node(). */ unsigned long __init find_min_pfn_with_active_regions(void) { @@ -4782,7 +5099,7 @@ static unsigned long __init early_calculate_totalpages(void) if (pages) node_set_state(nid, N_MEMORY); } - return totalpages; + return totalpages; } /* @@ -4800,9 +5117,33 @@ static void __init find_zone_movable_pfns_for_nodes(void) nodemask_t saved_node_state = node_states[N_MEMORY]; unsigned long totalpages = early_calculate_totalpages(); int usable_nodes = nodes_weight(node_states[N_MEMORY]); + struct memblock_region *r; + + /* Need to find movable_zone earlier when movable_node is specified. */ + find_usable_zone_for_movable(); /* - * If movablecore was specified, calculate what size of + * If movable_node is specified, ignore kernelcore and movablecore + * options. + */ + if (movable_node_is_enabled()) { + for_each_memblock(memory, r) { + if (!memblock_is_hotpluggable(r)) + continue; + + nid = r->nid; + + usable_startpfn = PFN_DOWN(r->base); + zone_movable_pfn[nid] = zone_movable_pfn[nid] ? + min(usable_startpfn, zone_movable_pfn[nid]) : + usable_startpfn; + } + + goto out2; + } + + /* + * If movablecore=nn[KMG] was specified, calculate what size of * kernelcore that corresponds so that memory usable for * any allocation type is evenly spread. If both kernelcore * and movablecore are specified, then the value of kernelcore @@ -4828,7 +5169,6 @@ static void __init find_zone_movable_pfns_for_nodes(void) goto out; /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ - find_usable_zone_for_movable(); usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone]; restart: @@ -4899,7 +5239,7 @@ restart: /* * Some kernelcore has been met, update counts and * break if the kernelcore for this node has been - * satisified + * satisfied */ required_kernelcore -= min(required_kernelcore, size_pages); @@ -4913,12 +5253,13 @@ restart: * If there is still required_kernelcore, we do another pass with one * less node in the count. This will push zone_movable_pfn[nid] further * along on the nodes that still have memory until kernelcore is - * satisified + * satisfied */ usable_nodes--; if (usable_nodes && required_kernelcore > usable_nodes) goto restart; +out2: /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ for (nid = 0; nid < MAX_NUMNODES; nid++) zone_movable_pfn[nid] = @@ -4939,7 +5280,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid) for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) { struct zone *zone = &pgdat->node_zones[zone_type]; - if (zone->present_pages) { + if (populated_zone(zone)) { node_set_state(nid, N_HIGH_MEMORY); if (N_NORMAL_MEMORY != N_HIGH_MEMORY && zone_type <= ZONE_NORMAL) @@ -4954,7 +5295,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid) * @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 + * Using the page ranges provided by memblock_set_node(), 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 @@ -5072,6 +5413,103 @@ early_param("movablecore", cmdline_parse_movablecore); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +void adjust_managed_page_count(struct page *page, long count) +{ + spin_lock(&managed_page_count_lock); + page_zone(page)->managed_pages += count; + totalram_pages += count; +#ifdef CONFIG_HIGHMEM + if (PageHighMem(page)) + totalhigh_pages += count; +#endif + spin_unlock(&managed_page_count_lock); +} +EXPORT_SYMBOL(adjust_managed_page_count); + +unsigned long free_reserved_area(void *start, void *end, int poison, char *s) +{ + void *pos; + unsigned long pages = 0; + + start = (void *)PAGE_ALIGN((unsigned long)start); + end = (void *)((unsigned long)end & PAGE_MASK); + for (pos = start; pos < end; pos += PAGE_SIZE, pages++) { + if ((unsigned int)poison <= 0xFF) + memset(pos, poison, PAGE_SIZE); + free_reserved_page(virt_to_page(pos)); + } + + if (pages && s) + pr_info("Freeing %s memory: %ldK (%p - %p)\n", + s, pages << (PAGE_SHIFT - 10), start, end); + + return pages; +} +EXPORT_SYMBOL(free_reserved_area); + +#ifdef CONFIG_HIGHMEM +void free_highmem_page(struct page *page) +{ + __free_reserved_page(page); + totalram_pages++; + page_zone(page)->managed_pages++; + totalhigh_pages++; +} +#endif + + +void __init mem_init_print_info(const char *str) +{ + unsigned long physpages, codesize, datasize, rosize, bss_size; + unsigned long init_code_size, init_data_size; + + physpages = get_num_physpages(); + codesize = _etext - _stext; + datasize = _edata - _sdata; + rosize = __end_rodata - __start_rodata; + bss_size = __bss_stop - __bss_start; + init_data_size = __init_end - __init_begin; + init_code_size = _einittext - _sinittext; + + /* + * Detect special cases and adjust section sizes accordingly: + * 1) .init.* may be embedded into .data sections + * 2) .init.text.* may be out of [__init_begin, __init_end], + * please refer to arch/tile/kernel/vmlinux.lds.S. + * 3) .rodata.* may be embedded into .text or .data sections. + */ +#define adj_init_size(start, end, size, pos, adj) \ + do { \ + if (start <= pos && pos < end && size > adj) \ + size -= adj; \ + } while (0) + + adj_init_size(__init_begin, __init_end, init_data_size, + _sinittext, init_code_size); + adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); + adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); + adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); + adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); + +#undef adj_init_size + + printk("Memory: %luK/%luK available " + "(%luK kernel code, %luK rwdata, %luK rodata, " + "%luK init, %luK bss, %luK reserved" +#ifdef CONFIG_HIGHMEM + ", %luK highmem" +#endif + "%s%s)\n", + nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10), + codesize >> 10, datasize >> 10, rosize >> 10, + (init_data_size + init_code_size) >> 10, bss_size >> 10, + (physpages - totalram_pages) << (PAGE_SHIFT-10), +#ifdef CONFIG_HIGHMEM + totalhigh_pages << (PAGE_SHIFT-10), +#endif + str ? ", " : "", str ? str : ""); +} + /** * set_dma_reserve - set the specified number of pages reserved in the first zone * @new_dma_reserve: The number of pages to mark reserved @@ -5118,7 +5556,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self, * This is only okay since the processor is dead and cannot * race with what we are doing. */ - refresh_cpu_vm_stats(cpu); + cpu_vm_stats_fold(cpu); } return NOTIFY_OK; } @@ -5152,8 +5590,8 @@ static void calculate_totalreserve_pages(void) /* we treat the high watermark as reserved pages. */ max += high_wmark_pages(zone); - if (max > zone->present_pages) - max = zone->present_pages; + if (max > zone->managed_pages) + max = zone->managed_pages; reserve_pages += max; /* * Lowmem reserves are not available to @@ -5185,7 +5623,7 @@ static void setup_per_zone_lowmem_reserve(void) for_each_online_pgdat(pgdat) { for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long present_pages = zone->present_pages; + unsigned long managed_pages = zone->managed_pages; zone->lowmem_reserve[j] = 0; @@ -5199,9 +5637,9 @@ static void setup_per_zone_lowmem_reserve(void) sysctl_lowmem_reserve_ratio[idx] = 1; lower_zone = pgdat->node_zones + idx; - lower_zone->lowmem_reserve[j] = present_pages / + lower_zone->lowmem_reserve[j] = managed_pages / sysctl_lowmem_reserve_ratio[idx]; - present_pages += lower_zone->present_pages; + managed_pages += lower_zone->managed_pages; } } } @@ -5220,14 +5658,14 @@ static void __setup_per_zone_wmarks(void) /* Calculate total number of !ZONE_HIGHMEM pages */ for_each_zone(zone) { if (!is_highmem(zone)) - lowmem_pages += zone->present_pages; + lowmem_pages += zone->managed_pages; } for_each_zone(zone) { u64 tmp; spin_lock_irqsave(&zone->lock, flags); - tmp = (u64)pages_min * zone->present_pages; + tmp = (u64)pages_min * zone->managed_pages; do_div(tmp, lowmem_pages); if (is_highmem(zone)) { /* @@ -5239,13 +5677,10 @@ static void __setup_per_zone_wmarks(void) * deltas controls asynch page reclaim, and so should * not be capped for highmem. */ - int min_pages; + unsigned long min_pages; - min_pages = zone->present_pages / 1024; - if (min_pages < SWAP_CLUSTER_MAX) - min_pages = SWAP_CLUSTER_MAX; - if (min_pages > 128) - min_pages = 128; + min_pages = zone->managed_pages / 1024; + min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL); zone->watermark[WMARK_MIN] = min_pages; } else { /* @@ -5258,6 +5693,11 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); + __mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - + low_wmark_pages(zone) - + zone_page_state(zone, NR_ALLOC_BATCH)); + setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -5306,7 +5746,7 @@ static void __meminit calculate_zone_inactive_ratio(struct zone *zone) unsigned int gb, ratio; /* Zone size in gigabytes */ - gb = zone->present_pages >> (30 - PAGE_SHIFT); + gb = zone->managed_pages >> (30 - PAGE_SHIFT); if (gb) ratio = int_sqrt(10 * gb); else @@ -5330,7 +5770,7 @@ static void __meminit setup_per_zone_inactive_ratio(void) * we want it large (64MB max). But it is not linear, because network * bandwidth does not increase linearly with machine size. We use * - * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: + * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: * min_free_kbytes = sqrt(lowmem_kbytes * 16) * * which yields @@ -5350,14 +5790,21 @@ static void __meminit setup_per_zone_inactive_ratio(void) int __meminit init_per_zone_wmark_min(void) { unsigned long lowmem_kbytes; + int new_min_free_kbytes; lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10); - - min_free_kbytes = int_sqrt(lowmem_kbytes * 16); - if (min_free_kbytes < 128) - min_free_kbytes = 128; - if (min_free_kbytes > 65536) - min_free_kbytes = 65536; + new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16); + + if (new_min_free_kbytes > user_min_free_kbytes) { + min_free_kbytes = new_min_free_kbytes; + if (min_free_kbytes < 128) + min_free_kbytes = 128; + if (min_free_kbytes > 65536) + min_free_kbytes = 65536; + } else { + pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n", + new_min_free_kbytes, user_min_free_kbytes); + } setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); @@ -5367,21 +5814,28 @@ int __meminit init_per_zone_wmark_min(void) module_init(init_per_zone_wmark_min) /* - * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so + * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so * that we can call two helper functions whenever min_free_kbytes * changes. */ -int min_free_kbytes_sysctl_handler(ctl_table *table, int write, +int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, buffer, length, ppos); - if (write) + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write) { + user_min_free_kbytes = min_free_kbytes; setup_per_zone_wmarks(); + } return 0; } #ifdef CONFIG_NUMA -int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, +int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; @@ -5392,12 +5846,12 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, return rc; for_each_zone(zone) - zone->min_unmapped_pages = (zone->present_pages * + zone->min_unmapped_pages = (zone->managed_pages * sysctl_min_unmapped_ratio) / 100; return 0; } -int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, +int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; @@ -5408,7 +5862,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, return rc; for_each_zone(zone) - zone->min_slab_pages = (zone->present_pages * + zone->min_slab_pages = (zone->managed_pages * sysctl_min_slab_ratio) / 100; return 0; } @@ -5423,7 +5877,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, * minimum watermarks. The lowmem reserve ratio can only make sense * if in function of the boot time zone sizes. */ -int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec_minmax(table, write, buffer, length, ppos); @@ -5433,29 +5887,45 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, /* * percpu_pagelist_fraction - changes the pcp->high for each zone on each - * cpu. It is the fraction of total pages in each zone that a hot per cpu pagelist - * can have before it gets flushed back to buddy allocator. + * cpu. It is the fraction of total pages in each zone that a hot per cpu + * pagelist can have before it gets flushed back to buddy allocator. */ - -int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, +int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - unsigned int cpu; + int old_percpu_pagelist_fraction; int ret; + mutex_lock(&pcp_batch_high_lock); + old_percpu_pagelist_fraction = percpu_pagelist_fraction; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || (ret < 0)) - return ret; + if (!write || ret < 0) + goto out; + + /* Sanity checking to avoid pcp imbalance */ + if (percpu_pagelist_fraction && + percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { + percpu_pagelist_fraction = old_percpu_pagelist_fraction; + ret = -EINVAL; + goto out; + } + + /* No change? */ + if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + goto out; + for_each_populated_zone(zone) { - for_each_possible_cpu(cpu) { - unsigned long high; - high = zone->present_pages / percpu_pagelist_fraction; - setup_pagelist_highmark( - per_cpu_ptr(zone->pageset, cpu), high); - } + unsigned int cpu; + + for_each_possible_cpu(cpu) + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); } - return 0; +out: + mutex_unlock(&pcp_batch_high_lock); + return ret; } int hashdist = HASHDIST_DEFAULT; @@ -5495,9 +5965,10 @@ void *__init alloc_large_system_hash(const char *tablename, if (!numentries) { /* round applicable memory size up to nearest megabyte */ numentries = nr_kernel_pages; - numentries += (1UL << (20 - PAGE_SHIFT)) - 1; - numentries >>= 20 - PAGE_SHIFT; - numentries <<= 20 - PAGE_SHIFT; + + /* It isn't necessary when PAGE_SIZE >= 1MB */ + if (PAGE_SHIFT < 20) + numentries = round_up(numentries, (1<<20)/PAGE_SIZE); /* limit to 1 bucket per 2^scale bytes of low memory */ if (scale > PAGE_SHIFT) @@ -5535,7 +6006,7 @@ void *__init alloc_large_system_hash(const char *tablename, do { size = bucketsize << log2qty; if (flags & HASH_EARLY) - table = alloc_bootmem_nopanic(size); + table = memblock_virt_alloc_nopanic(size, 0); else if (hashdist) table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL); else { @@ -5591,67 +6062,80 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) } /** - * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages + * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages * @page: The page within the block of interest - * @start_bitidx: The first bit of interest to retrieve - * @end_bitidx: The last bit of interest - * returns pageblock_bits flags + * @pfn: The target page frame number + * @end_bitidx: The last bit of interest to retrieve + * @mask: mask of bits that the caller is interested in + * + * Return: pageblock_bits flags */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) +unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long flags = 0; - unsigned long value = 1; + unsigned long bitidx, word_bitidx; + unsigned long word; zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (test_bit(bitidx + start_bitidx, bitmap)) - flags |= value; - - return flags; + word = bitmap[word_bitidx]; + bitidx += end_bitidx; + return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; } /** - * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest - * @start_bitidx: The first bit of interest - * @end_bitidx: The last bit of interest * @flags: The flags to set + * @pfn: The target page frame number + * @end_bitidx: The last bit of interest + * @mask: mask of bits that the caller is interested in */ -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx) +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long value = 1; + unsigned long bitidx, word_bitidx; + unsigned long old_word, word; + + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); - VM_BUG_ON(pfn < zone->zone_start_pfn); - VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (flags & value) - __set_bit(bitidx + start_bitidx, bitmap); - else - __clear_bit(bitidx + start_bitidx, bitmap); + VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page); + + bitidx += end_bitidx; + mask <<= (BITS_PER_LONG - bitidx - 1); + flags <<= (BITS_PER_LONG - bitidx - 1); + + word = ACCESS_ONCE(bitmap[word_bitidx]); + for (;;) { + old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); + if (word == old_word) + break; + word = old_word; + } } /* * This function checks whether pageblock includes unmovable pages or not. * If @count is not zero, it is okay to include less @count unmovable pages * - * PageLRU check wihtout isolation or lru_lock could race so that + * PageLRU check without isolation or lru_lock could race so that * MIGRATE_MOVABLE block might include unmovable pages. It means you can't * expect this function should be exact. */ @@ -5679,6 +6163,17 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, continue; page = pfn_to_page(check); + + /* + * Hugepages are not in LRU lists, but they're movable. + * We need not scan over tail pages bacause we don't + * handle each tail page individually in migration. + */ + if (PageHuge(page)) { + iter = round_up(iter + 1, 1<<compound_order(page)) - 1; + continue; + } + /* * We can't use page_count without pin a page * because another CPU can free compound page. @@ -5736,8 +6231,7 @@ bool is_pageblock_removable_nolock(struct page *page) zone = page_zone(page); pfn = page_to_pfn(page); - if (zone->zone_start_pfn > pfn || - zone->zone_start_pfn + zone->spanned_pages <= pfn) + if (!zone_spans_pfn(zone, pfn)) return false; return !has_unmovable_pages(zone, page, 0, true); @@ -5793,14 +6287,14 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, &cc->migratepages); cc->nr_migratepages -= nr_reclaimed; - ret = migrate_pages(&cc->migratepages, - alloc_migrate_target, - 0, false, MIGRATE_SYNC, - MR_CMA); + ret = migrate_pages(&cc->migratepages, alloc_migrate_target, + NULL, 0, cc->mode, MR_CMA); } - - putback_movable_pages(&cc->migratepages); - return ret > 0 ? 0 : ret; + if (ret < 0) { + putback_movable_pages(&cc->migratepages); + return ret; + } + return 0; } /** @@ -5833,7 +6327,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; INIT_LIST_HEAD(&cc.migratepages); @@ -5945,32 +6439,18 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages) #endif #ifdef CONFIG_MEMORY_HOTPLUG -static int __meminit __zone_pcp_update(void *data) -{ - struct zone *zone = data; - int cpu; - unsigned long batch = zone_batchsize(zone), flags; - - for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pset; - struct per_cpu_pages *pcp; - - pset = per_cpu_ptr(zone->pageset, cpu); - pcp = &pset->pcp; - - local_irq_save(flags); - if (pcp->count > 0) - free_pcppages_bulk(zone, pcp->count, pcp); - drain_zonestat(zone, pset); - setup_pageset(pset, batch); - local_irq_restore(flags); - } - return 0; -} - +/* + * The zone indicated has a new number of managed_pages; batch sizes and percpu + * page high values need to be recalulated. + */ void __meminit zone_pcp_update(struct zone *zone) { - stop_machine(__zone_pcp_update, zone, NULL); + unsigned cpu; + mutex_lock(&pcp_batch_high_lock); + for_each_possible_cpu(cpu) + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); + mutex_unlock(&pcp_batch_high_lock); } #endif @@ -6002,7 +6482,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; struct zone *zone; - int order, i; + unsigned int order, i; unsigned long pfn; unsigned long flags; /* find the first valid pfn */ @@ -6054,7 +6534,7 @@ bool is_free_buddy_page(struct page *page) struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); unsigned long flags; - int order; + unsigned int order; spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { @@ -6140,12 +6620,25 @@ static void dump_page_flags(unsigned long flags) printk(")\n"); } -void dump_page(struct page *page) +void dump_page_badflags(struct page *page, const char *reason, + unsigned long badflags) { printk(KERN_ALERT "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n", page, atomic_read(&page->_count), page_mapcount(page), page->mapping, page->index); dump_page_flags(page->flags); + if (reason) + pr_alert("page dumped because: %s\n", reason); + if (page->flags & badflags) { + pr_alert("bad because of flags:\n"); + dump_page_flags(page->flags & badflags); + } mem_cgroup_print_bad_page(page); } + +void dump_page(struct page *page, const char *reason) +{ + dump_page_badflags(page, reason, 0); +} +EXPORT_SYMBOL(dump_page); diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 6d757e3a872..3708264d283 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -54,8 +54,9 @@ static int __init alloc_node_page_cgroup(int nid) table_size = sizeof(struct page_cgroup) * nr_pages; - base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), - table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + base = memblock_virt_alloc_try_nid_nopanic( + table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + BOOTMEM_ALLOC_ACCESSIBLE, nid); if (!base) return -ENOMEM; NODE_DATA(nid)->node_page_cgroup = base; @@ -174,7 +175,7 @@ static void free_page_cgroup(void *addr) } } -void __free_page_cgroup(unsigned long pfn) +static void __free_page_cgroup(unsigned long pfn) { struct mem_section *ms; struct page_cgroup *base; @@ -187,9 +188,9 @@ void __free_page_cgroup(unsigned long pfn) ms->page_cgroup = NULL; } -int __meminit online_page_cgroup(unsigned long start_pfn, - unsigned long nr_pages, - int nid) +static int __meminit online_page_cgroup(unsigned long start_pfn, + unsigned long nr_pages, + int nid) { unsigned long start, end, pfn; int fail = 0; @@ -222,8 +223,8 @@ int __meminit online_page_cgroup(unsigned long start_pfn, return -ENOMEM; } -int __meminit offline_page_cgroup(unsigned long start_pfn, - unsigned long nr_pages, int nid) +static int __meminit offline_page_cgroup(unsigned long start_pfn, + unsigned long nr_pages, int nid) { unsigned long start, end, pfn; @@ -451,7 +452,7 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry * @ent: swap entry to be looked up. * - * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID) + * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID) */ unsigned short lookup_swap_cgroup_id(swp_entry_t ent) { diff --git a/mm/page_io.c b/mm/page_io.c index 78eee32ee48..955db8b0d49 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -20,6 +20,8 @@ #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/frontswap.h> +#include <linux/aio.h> +#include <linux/blkdev.h> #include <asm/pgtable.h> static struct bio *get_swap_bio(gfp_t gfp_flags, @@ -29,20 +31,19 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, bio = bio_alloc(gfp_flags, 1); if (bio) { - bio->bi_sector = map_swap_page(page, &bio->bi_bdev); - bio->bi_sector <<= PAGE_SHIFT - 9; + bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev); + bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9; bio->bi_io_vec[0].bv_page = page; bio->bi_io_vec[0].bv_len = PAGE_SIZE; bio->bi_io_vec[0].bv_offset = 0; bio->bi_vcnt = 1; - bio->bi_idx = 0; - bio->bi_size = PAGE_SIZE; + bio->bi_iter.bi_size = PAGE_SIZE; bio->bi_end_io = end_io; } return bio; } -static void end_swap_bio_write(struct bio *bio, int err) +void end_swap_bio_write(struct bio *bio, int err) { const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct page *page = bio->bi_io_vec[0].bv_page; @@ -61,7 +62,7 @@ static void end_swap_bio_write(struct bio *bio, int err) printk(KERN_ALERT "Write-error on swap-device (%u:%u:%Lu)\n", imajor(bio->bi_bdev->bd_inode), iminor(bio->bi_bdev->bd_inode), - (unsigned long long)bio->bi_sector); + (unsigned long long)bio->bi_iter.bi_sector); ClearPageReclaim(page); } end_page_writeback(page); @@ -79,10 +80,55 @@ void end_swap_bio_read(struct bio *bio, int err) printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n", imajor(bio->bi_bdev->bd_inode), iminor(bio->bi_bdev->bd_inode), - (unsigned long long)bio->bi_sector); - } else { - SetPageUptodate(page); + (unsigned long long)bio->bi_iter.bi_sector); + goto out; + } + + SetPageUptodate(page); + + /* + * There is no guarantee that the page is in swap cache - the software + * suspend code (at least) uses end_swap_bio_read() against a non- + * swapcache page. So we must check PG_swapcache before proceeding with + * this optimization. + */ + if (likely(PageSwapCache(page))) { + struct swap_info_struct *sis; + + sis = page_swap_info(page); + if (sis->flags & SWP_BLKDEV) { + /* + * The swap subsystem performs lazy swap slot freeing, + * expecting that the page will be swapped out again. + * So we can avoid an unnecessary write if the page + * isn't redirtied. + * This is good for real swap storage because we can + * reduce unnecessary I/O and enhance wear-leveling + * if an SSD is used as the as swap device. + * But if in-memory swap device (eg zram) is used, + * this causes a duplicated copy between uncompressed + * data in VM-owned memory and compressed data in + * zram-owned memory. So let's free zram-owned memory + * and make the VM-owned decompressed page *dirty*, + * so the page should be swapped out somewhere again if + * we again wish to reclaim it. + */ + struct gendisk *disk = sis->bdev->bd_disk; + if (disk->fops->swap_slot_free_notify) { + swp_entry_t entry; + unsigned long offset; + + entry.val = page_private(page); + offset = swp_offset(entry); + + SetPageDirty(page); + disk->fops->swap_slot_free_notify(sis->bdev, + offset); + } + } } + +out: unlock_page(page); bio_put(bio); } @@ -185,9 +231,7 @@ bad_bmap: */ int swap_writepage(struct page *page, struct writeback_control *wbc) { - struct bio *bio; - int ret = 0, rw = WRITE; - struct swap_info_struct *sis = page_swap_info(page); + int ret = 0; if (try_to_free_swap(page)) { unlock_page(page); @@ -199,34 +243,80 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) end_page_writeback(page); goto out; } + ret = __swap_writepage(page, wbc, end_swap_bio_write); +out: + return ret; +} + +static sector_t swap_page_sector(struct page *page) +{ + return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9); +} + +int __swap_writepage(struct page *page, struct writeback_control *wbc, + void (*end_write_func)(struct bio *, int)) +{ + struct bio *bio; + int ret, rw = WRITE; + struct swap_info_struct *sis = page_swap_info(page); if (sis->flags & SWP_FILE) { struct kiocb kiocb; struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; - struct iovec iov = { - .iov_base = kmap(page), - .iov_len = PAGE_SIZE, + struct bio_vec bv = { + .bv_page = page, + .bv_len = PAGE_SIZE, + .bv_offset = 0 + }; + struct iov_iter from = { + .type = ITER_BVEC | WRITE, + .count = PAGE_SIZE, + .iov_offset = 0, + .nr_segs = 1, }; + from.bvec = &bv; /* older gcc versions are broken */ init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); - kiocb.ki_left = PAGE_SIZE; kiocb.ki_nbytes = PAGE_SIZE; + set_page_writeback(page); unlock_page(page); - ret = mapping->a_ops->direct_IO(KERNEL_WRITE, - &kiocb, &iov, - kiocb.ki_pos, 1); - kunmap(page); + ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE, + &kiocb, &from, + kiocb.ki_pos); if (ret == PAGE_SIZE) { count_vm_event(PSWPOUT); ret = 0; + } else { + /* + * In the case of swap-over-nfs, this can be a + * temporary failure if the system has limited + * memory for allocating transmit buffers. + * Mark the page dirty and avoid + * rotate_reclaimable_page but rate-limit the + * messages but do not flag PageError like + * the normal direct-to-bio case as it could + * be temporary. + */ + set_page_dirty(page); + ClearPageReclaim(page); + pr_err_ratelimited("Write error on dio swapfile (%Lu)\n", + page_file_offset(page)); } + end_page_writeback(page); return ret; } - bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write); + ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc); + if (!ret) { + count_vm_event(PSWPOUT); + return 0; + } + + ret = 0; + bio = get_swap_bio(GFP_NOIO, page, end_write_func); if (bio == NULL) { set_page_dirty(page); unlock_page(page); @@ -249,8 +339,8 @@ int swap_readpage(struct page *page) int ret = 0; struct swap_info_struct *sis = page_swap_info(page); - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageUptodate(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageUptodate(page), page); if (frontswap_load(page) == 0) { SetPageUptodate(page); unlock_page(page); @@ -267,6 +357,13 @@ int swap_readpage(struct page *page) return ret; } + ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); + if (!ret) { + count_vm_event(PSWPIN); + return 0; + } + + ret = 0; bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read); if (bio == NULL) { unlock_page(page); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 383bdbb98b0..d1473b2e948 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -6,6 +6,7 @@ #include <linux/page-isolation.h> #include <linux/pageblock-flags.h> #include <linux/memory.h> +#include <linux/hugetlb.h> #include "internal.h" int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages) @@ -226,9 +227,9 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, int ret; /* - * Note: pageblock_nr_page != MAX_ORDER. Then, chunks of free page - * is not aligned to pageblock_nr_pages. - * Then we just check pagetype fist. + * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages + * are not aligned to pageblock_nr_pages. + * Then we just check migratetype first. */ for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); @@ -238,7 +239,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, page = __first_valid_page(start_pfn, end_pfn - start_pfn); if ((pfn < end_pfn) || !page) return -EBUSY; - /* Check all pages are free or Marked as ISOLATED */ + /* Check all pages are free or marked as ISOLATED */ zone = page_zone(page); spin_lock_irqsave(&zone->lock, flags); ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn, @@ -252,6 +253,19 @@ struct page *alloc_migrate_target(struct page *page, unsigned long private, { gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + /* + * TODO: allocate a destination hugepage from a nearest neighbor node, + * accordance with memory policy of the user process if possible. For + * now as a simple work-around, we use the next node for destination. + */ + if (PageHuge(page)) { + nodemask_t src = nodemask_of_node(page_to_nid(page)); + nodemask_t dst; + nodes_complement(dst, src); + return alloc_huge_page_node(page_hstate(compound_head(page)), + next_node(page_to_nid(page), dst)); + } + if (PageHighMem(page)) gfp_mask |= __GFP_HIGHMEM; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 35aa294656c..2beeabf502c 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -127,28 +127,7 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, return 0; } -static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk) -{ - struct vm_area_struct *vma; - - /* We don't need vma lookup at all. */ - if (!walk->hugetlb_entry) - return NULL; - - VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); - vma = find_vma(walk->mm, addr); - if (vma && vma->vm_start <= addr && is_vm_hugetlb_page(vma)) - return vma; - - return NULL; -} - #else /* CONFIG_HUGETLB_PAGE */ -static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk) -{ - return NULL; -} - static int walk_hugetlb_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -198,30 +177,53 @@ int walk_page_range(unsigned long addr, unsigned long end, if (!walk->mm) return -EINVAL; + VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); + pgd = pgd_offset(walk->mm, addr); do { - struct vm_area_struct *vma; + struct vm_area_struct *vma = NULL; next = pgd_addr_end(addr, end); /* - * handle hugetlb vma individually because pagetable walk for - * the hugetlb page is dependent on the architecture and - * we can't handled it in the same manner as non-huge pages. + * This function was not intended to be vma based. + * But there are vma special cases to be handled: + * - hugetlb vma's + * - VM_PFNMAP vma's */ - vma = hugetlb_vma(addr, walk); + vma = find_vma(walk->mm, addr); if (vma) { - if (vma->vm_end < next) + /* + * There are no page structures backing a VM_PFNMAP + * range, so do not allow split_huge_page_pmd(). + */ + if ((vma->vm_start <= addr) && + (vma->vm_flags & VM_PFNMAP)) { next = vma->vm_end; + pgd = pgd_offset(walk->mm, next); + continue; + } /* - * Hugepage is very tightly coupled with vma, so - * walk through hugetlb entries within a given vma. + * Handle hugetlb vma individually because pagetable + * walk for the hugetlb page is dependent on the + * architecture and we can't handled it in the same + * manner as non-huge pages. */ - err = walk_hugetlb_range(vma, addr, next, walk); - if (err) - break; - pgd = pgd_offset(walk->mm, next); - continue; + if (walk->hugetlb_entry && (vma->vm_start <= addr) && + is_vm_hugetlb_page(vma)) { + if (vma->vm_end < next) + next = vma->vm_end; + /* + * Hugepage is very tightly coupled with vma, + * so walk through hugetlb entries within a + * given vma. + */ + err = walk_hugetlb_range(vma, addr, next, walk); + if (err) + break; + pgd = pgd_offset(walk->mm, next); + continue; + } } if (pgd_none_or_clear_bad(pgd)) { @@ -240,7 +242,7 @@ int walk_page_range(unsigned long addr, unsigned long end, if (err) break; pgd++; - } while (addr = next, addr != end); + } while (addr = next, addr < end); return err; } diff --git a/mm/percpu.c b/mm/percpu.c index 8c8e08f3a69..2ddf9a990db 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -102,10 +102,11 @@ struct pcpu_chunk { int free_size; /* free bytes in the chunk */ int contig_hint; /* max contiguous size hint */ void *base_addr; /* base address of this chunk */ - int map_used; /* # of map entries used */ + int map_used; /* # of map entries used before the sentry */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ void *data; /* chunk data */ + int first_free; /* no free below this */ bool immutable; /* no [de]population allowed */ unsigned long populated[]; /* populated bitmap */ }; @@ -356,11 +357,11 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk) { int new_alloc; - if (chunk->map_alloc >= chunk->map_used + 2) + if (chunk->map_alloc >= chunk->map_used + 3) return 0; new_alloc = PCPU_DFL_MAP_ALLOC; - while (new_alloc < chunk->map_used + 2) + while (new_alloc < chunk->map_used + 3) new_alloc *= 2; return new_alloc; @@ -418,48 +419,6 @@ out_unlock: } /** - * pcpu_split_block - split a map block - * @chunk: chunk of interest - * @i: index of map block to split - * @head: head size in bytes (can be 0) - * @tail: tail size in bytes (can be 0) - * - * Split the @i'th map block into two or three blocks. If @head is - * non-zero, @head bytes block is inserted before block @i moving it - * to @i+1 and reducing its size by @head bytes. - * - * If @tail is non-zero, the target block, which can be @i or @i+1 - * depending on @head, is reduced by @tail bytes and @tail byte block - * is inserted after the target block. - * - * @chunk->map must have enough free slots to accommodate the split. - * - * CONTEXT: - * pcpu_lock. - */ -static void pcpu_split_block(struct pcpu_chunk *chunk, int i, - int head, int tail) -{ - int nr_extra = !!head + !!tail; - - BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra); - - /* insert new subblocks */ - memmove(&chunk->map[i + nr_extra], &chunk->map[i], - sizeof(chunk->map[0]) * (chunk->map_used - i)); - chunk->map_used += nr_extra; - - if (head) { - chunk->map[i + 1] = chunk->map[i] - head; - chunk->map[i++] = head; - } - if (tail) { - chunk->map[i++] -= tail; - chunk->map[i] = tail; - } -} - -/** * pcpu_alloc_area - allocate area from a pcpu_chunk * @chunk: chunk of interest * @size: wanted size in bytes @@ -483,19 +442,27 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) int oslot = pcpu_chunk_slot(chunk); int max_contig = 0; int i, off; + bool seen_free = false; + int *p; - for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) { - bool is_last = i + 1 == chunk->map_used; + for (i = chunk->first_free, p = chunk->map + i; i < chunk->map_used; i++, p++) { int head, tail; + int this_size; + + off = *p; + if (off & 1) + continue; /* extra for alignment requirement */ head = ALIGN(off, align) - off; - BUG_ON(i == 0 && head != 0); - if (chunk->map[i] < 0) - continue; - if (chunk->map[i] < head + size) { - max_contig = max(chunk->map[i], max_contig); + this_size = (p[1] & ~1) - off; + if (this_size < head + size) { + if (!seen_free) { + chunk->first_free = i; + seen_free = true; + } + max_contig = max(this_size, max_contig); continue; } @@ -505,44 +472,59 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) * than sizeof(int), which is very small but isn't too * uncommon for percpu allocations. */ - if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) { - if (chunk->map[i - 1] > 0) - chunk->map[i - 1] += head; - else { - chunk->map[i - 1] -= head; + if (head && (head < sizeof(int) || !(p[-1] & 1))) { + *p = off += head; + if (p[-1] & 1) chunk->free_size -= head; - } - chunk->map[i] -= head; - off += head; + else + max_contig = max(*p - p[-1], max_contig); + this_size -= head; head = 0; } /* if tail is small, just keep it around */ - tail = chunk->map[i] - head - size; - if (tail < sizeof(int)) + tail = this_size - head - size; + if (tail < sizeof(int)) { tail = 0; + size = this_size - head; + } /* split if warranted */ if (head || tail) { - pcpu_split_block(chunk, i, head, tail); + int nr_extra = !!head + !!tail; + + /* insert new subblocks */ + memmove(p + nr_extra + 1, p + 1, + sizeof(chunk->map[0]) * (chunk->map_used - i)); + chunk->map_used += nr_extra; + if (head) { - i++; - off += head; - max_contig = max(chunk->map[i - 1], max_contig); + if (!seen_free) { + chunk->first_free = i; + seen_free = true; + } + *++p = off += head; + ++i; + max_contig = max(head, max_contig); + } + if (tail) { + p[1] = off + size; + max_contig = max(tail, max_contig); } - if (tail) - max_contig = max(chunk->map[i + 1], max_contig); } + if (!seen_free) + chunk->first_free = i + 1; + /* update hint and mark allocated */ - if (is_last) + if (i + 1 == chunk->map_used) chunk->contig_hint = max_contig; /* fully scanned */ else chunk->contig_hint = max(chunk->contig_hint, max_contig); - chunk->free_size -= chunk->map[i]; - chunk->map[i] = -chunk->map[i]; + chunk->free_size -= size; + *p |= 1; pcpu_chunk_relocate(chunk, oslot); return off; @@ -570,34 +552,50 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) { int oslot = pcpu_chunk_slot(chunk); - int i, off; - - for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) - if (off == freeme) - break; + int off = 0; + unsigned i, j; + int to_free = 0; + int *p; + + freeme |= 1; /* we are searching for <given offset, in use> pair */ + + i = 0; + j = chunk->map_used; + while (i != j) { + unsigned k = (i + j) / 2; + off = chunk->map[k]; + if (off < freeme) + i = k + 1; + else if (off > freeme) + j = k; + else + i = j = k; + } BUG_ON(off != freeme); - BUG_ON(chunk->map[i] > 0); - chunk->map[i] = -chunk->map[i]; - chunk->free_size += chunk->map[i]; + if (i < chunk->first_free) + chunk->first_free = i; + p = chunk->map + i; + *p = off &= ~1; + chunk->free_size += (p[1] & ~1) - off; + + /* merge with next? */ + if (!(p[1] & 1)) + to_free++; /* merge with previous? */ - if (i > 0 && chunk->map[i - 1] >= 0) { - chunk->map[i - 1] += chunk->map[i]; - chunk->map_used--; - memmove(&chunk->map[i], &chunk->map[i + 1], - (chunk->map_used - i) * sizeof(chunk->map[0])); + if (i > 0 && !(p[-1] & 1)) { + to_free++; i--; + p--; } - /* merge with next? */ - if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) { - chunk->map[i] += chunk->map[i + 1]; - chunk->map_used--; - memmove(&chunk->map[i + 1], &chunk->map[i + 2], - (chunk->map_used - (i + 1)) * sizeof(chunk->map[0])); + if (to_free) { + chunk->map_used -= to_free; + memmove(p + 1, p + 1 + to_free, + (chunk->map_used - i) * sizeof(chunk->map[0])); } - chunk->contig_hint = max(chunk->map[i], chunk->contig_hint); + chunk->contig_hint = max(chunk->map[i + 1] - chunk->map[i] - 1, chunk->contig_hint); pcpu_chunk_relocate(chunk, oslot); } @@ -612,12 +610,14 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); if (!chunk->map) { - kfree(chunk); + pcpu_mem_free(chunk, pcpu_chunk_struct_size); return NULL; } chunk->map_alloc = PCPU_DFL_MAP_ALLOC; - chunk->map[chunk->map_used++] = pcpu_unit_size; + chunk->map[0] = 0; + chunk->map[1] = pcpu_unit_size | 1; + chunk->map_used = 1; INIT_LIST_HEAD(&chunk->list); chunk->free_size = pcpu_unit_size; @@ -713,6 +713,16 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved) unsigned long flags; void __percpu *ptr; + /* + * We want the lowest bit of offset available for in-use/free + * indicator, so force >= 16bit alignment and make size even. + */ + if (unlikely(align < 2)) + align = 2; + + if (unlikely(size & 1)) + size++; + if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { WARN(true, "illegal size (%zu) or align (%zu) for " "percpu allocation\n", size, align); @@ -1063,7 +1073,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); - ptr = alloc_bootmem_nopanic(PFN_ALIGN(ai_size)); + ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), 0); if (!ptr) return NULL; ai = ptr; @@ -1088,7 +1098,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - free_bootmem(__pa(ai), ai->__ai_size); + memblock_free_early(__pa(ai), ai->__ai_size); } /** @@ -1246,10 +1256,12 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ - group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0])); - group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0])); - unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0])); - unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0])); + group_offsets = memblock_virt_alloc(ai->nr_groups * + sizeof(group_offsets[0]), 0); + group_sizes = memblock_virt_alloc(ai->nr_groups * + sizeof(group_sizes[0]), 0); + unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); + unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; @@ -1311,7 +1323,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; - pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0])); + pcpu_slot = memblock_virt_alloc( + pcpu_nr_slots * sizeof(pcpu_slot[0]), 0); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); @@ -1322,7 +1335,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, * covers static area + reserved area (mostly used for module * static percpu allocation). */ - schunk = alloc_bootmem(pcpu_chunk_struct_size); + schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&schunk->list); schunk->base_addr = base_addr; schunk->map = smap; @@ -1340,13 +1353,17 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, } schunk->contig_hint = schunk->free_size; - schunk->map[schunk->map_used++] = -ai->static_size; + schunk->map[0] = 1; + schunk->map[1] = ai->static_size; + schunk->map_used = 1; if (schunk->free_size) - schunk->map[schunk->map_used++] = schunk->free_size; + schunk->map[++schunk->map_used] = 1 | (ai->static_size + schunk->free_size); + else + schunk->map[1] |= 1; /* init dynamic chunk if necessary */ if (dyn_size) { - dchunk = alloc_bootmem(pcpu_chunk_struct_size); + dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&dchunk->list); dchunk->base_addr = base_addr; dchunk->map = dmap; @@ -1355,8 +1372,10 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, bitmap_fill(dchunk->populated, pcpu_unit_pages); dchunk->contig_hint = dchunk->free_size = dyn_size; - dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit; - dchunk->map[dchunk->map_used++] = dchunk->free_size; + dchunk->map[0] = 1; + dchunk->map[1] = pcpu_reserved_chunk_limit; + dchunk->map[2] = (pcpu_reserved_chunk_limit + dchunk->free_size) | 1; + dchunk->map_used = 2; } /* link the first chunk in */ @@ -1626,7 +1645,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); - areas = alloc_bootmem_nopanic(areas_size); + areas = memblock_virt_alloc_nopanic(areas_size, 0); if (!areas) { rc = -ENOMEM; goto out_free; @@ -1686,10 +1705,10 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, max_distance += ai->unit_size; /* warn if maximum distance is further than 75% of vmalloc space */ - if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) { + if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc " "space 0x%lx\n", max_distance, - (unsigned long)(VMALLOC_END - VMALLOC_START)); + VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; @@ -1706,12 +1725,13 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, out_free_areas: for (group = 0; group < ai->nr_groups; group++) - free_fn(areas[group], - ai->groups[group].nr_units * ai->unit_size); + if (areas[group]) + free_fn(areas[group], + ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) - free_bootmem(__pa(areas), areas_size); + memblock_free_early(__pa(areas), areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -1759,7 +1779,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); - pages = alloc_bootmem(pages_size); + pages = memblock_virt_alloc(pages_size, 0); /* allocate pages */ j = 0; @@ -1822,7 +1842,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - free_bootmem(__pa(pages), pages_size); + memblock_free_early(__pa(pages), pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -1847,12 +1867,13 @@ EXPORT_SYMBOL(__per_cpu_offset); static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS)); + return memblock_virt_alloc_from_nopanic( + size, align, __pa(MAX_DMA_ADDRESS)); } static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - free_bootmem(__pa(ptr), size); + memblock_free_early(__pa(ptr), size); } void __init setup_per_cpu_areas(void) @@ -1895,7 +1916,9 @@ void __init setup_per_cpu_areas(void) void *fc; ai = pcpu_alloc_alloc_info(1, 1); - fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + fc = memblock_virt_alloc_from_nopanic(unit_size, + PAGE_SIZE, + __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 0c8323fe6c8..a8b91992593 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -10,6 +10,30 @@ #include <asm/tlb.h> #include <asm-generic/pgtable.h> +/* + * If a p?d_bad entry is found while walking page tables, report + * the error, before resetting entry to p?d_none. Usually (but + * very seldom) called out from the p?d_none_or_clear_bad macros. + */ + +void pgd_clear_bad(pgd_t *pgd) +{ + pgd_ERROR(*pgd); + pgd_clear(pgd); +} + +void pud_clear_bad(pud_t *pud) +{ + pud_ERROR(*pud); + pud_clear(pud); +} + +void pmd_clear_bad(pmd_t *pmd) +{ + pmd_ERROR(*pmd); + pmd_clear(pmd); +} + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* * Only sets the access flags (dirty, accessed), as well as write @@ -86,9 +110,10 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { + struct mm_struct *mm = (vma)->vm_mm; pte_t pte; - pte = ptep_get_and_clear((vma)->vm_mm, address, ptep); - if (pte_accessible(pte)) + pte = ptep_get_and_clear(mm, address, ptep); + if (pte_accessible(mm, pte)) flush_tlb_page(vma, address); return pte; } @@ -124,16 +149,17 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT #ifdef CONFIG_TRANSPARENT_HUGEPAGE -void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) { - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ - if (!mm->pmd_huge_pte) + if (!pmd_huge_pte(mm, pmdp)) INIT_LIST_HEAD(&pgtable->lru); else - list_add(&pgtable->lru, &mm->pmd_huge_pte->lru); - mm->pmd_huge_pte = pgtable; + list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru); + pmd_huge_pte(mm, pmdp) = pgtable; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif @@ -141,18 +167,18 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* no "address" argument so destroys page coloring of some arch */ -pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm) +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { pgtable_t pgtable; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ - pgtable = mm->pmd_huge_pte; + pgtable = pmd_huge_pte(mm, pmdp); if (list_empty(&pgtable->lru)) - mm->pmd_huge_pte = NULL; + pmd_huge_pte(mm, pmdp) = NULL; else { - mm->pmd_huge_pte = list_entry(pgtable->lru.next, + pmd_huge_pte(mm, pmdp) = list_entry(pgtable->lru.next, struct page, lru); list_del(&pgtable->lru); } @@ -166,6 +192,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm) void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + pmd_t entry = *pmdp; + if (pmd_numa(entry)) + entry = pmd_mknonnuma(entry); set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp)); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 926b4664974..5077afcd9e1 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -23,129 +23,40 @@ /** * process_vm_rw_pages - read/write pages from task specified - * @task: task to read/write from - * @mm: mm for task - * @process_pages: struct pages area that can store at least - * nr_pages_to_copy struct page pointers - * @pa: address of page in task to start copying from/to + * @pages: array of pointers to pages we want to copy * @start_offset: offset in page to start copying from/to * @len: number of bytes to copy - * @lvec: iovec array specifying where to copy to/from - * @lvec_cnt: number of elements in iovec array - * @lvec_current: index in iovec array we are up to - * @lvec_offset: offset in bytes from current iovec iov_base we are up to + * @iter: where to copy to/from locally * @vm_write: 0 means copy from, 1 means copy to - * @nr_pages_to_copy: number of pages to copy - * @bytes_copied: returns number of bytes successfully copied * Returns 0 on success, error code otherwise */ -static int process_vm_rw_pages(struct task_struct *task, - struct mm_struct *mm, - struct page **process_pages, - unsigned long pa, - unsigned long start_offset, - unsigned long len, - const struct iovec *lvec, - unsigned long lvec_cnt, - unsigned long *lvec_current, - size_t *lvec_offset, - int vm_write, - unsigned int nr_pages_to_copy, - ssize_t *bytes_copied) +static int process_vm_rw_pages(struct page **pages, + unsigned offset, + size_t len, + struct iov_iter *iter, + int vm_write) { - int pages_pinned; - void *target_kaddr; - int pgs_copied = 0; - int j; - int ret; - ssize_t bytes_to_copy; - ssize_t rc = 0; - - *bytes_copied = 0; - - /* Get the pages we're interested in */ - down_read(&mm->mmap_sem); - pages_pinned = get_user_pages(task, mm, pa, - nr_pages_to_copy, - vm_write, 0, process_pages, NULL); - up_read(&mm->mmap_sem); - - if (pages_pinned != nr_pages_to_copy) { - rc = -EFAULT; - goto end; - } - /* Do the copy for each page */ - for (pgs_copied = 0; - (pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt); - pgs_copied++) { - /* Make sure we have a non zero length iovec */ - while (*lvec_current < lvec_cnt - && lvec[*lvec_current].iov_len == 0) - (*lvec_current)++; - if (*lvec_current == lvec_cnt) - break; + while (len && iov_iter_count(iter)) { + struct page *page = *pages++; + size_t copy = PAGE_SIZE - offset; + size_t copied; - /* - * Will copy smallest of: - * - bytes remaining in page - * - bytes remaining in destination iovec - */ - bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset, - len - *bytes_copied); - bytes_to_copy = min_t(ssize_t, bytes_to_copy, - lvec[*lvec_current].iov_len - - *lvec_offset); - - target_kaddr = kmap(process_pages[pgs_copied]) + start_offset; - - if (vm_write) - ret = copy_from_user(target_kaddr, - lvec[*lvec_current].iov_base - + *lvec_offset, - bytes_to_copy); - else - ret = copy_to_user(lvec[*lvec_current].iov_base - + *lvec_offset, - target_kaddr, bytes_to_copy); - kunmap(process_pages[pgs_copied]); - if (ret) { - *bytes_copied += bytes_to_copy - ret; - pgs_copied++; - rc = -EFAULT; - goto end; - } - *bytes_copied += bytes_to_copy; - *lvec_offset += bytes_to_copy; - if (*lvec_offset == lvec[*lvec_current].iov_len) { - /* - * Need to copy remaining part of page into the - * next iovec if there are any bytes left in page - */ - (*lvec_current)++; - *lvec_offset = 0; - start_offset = (start_offset + bytes_to_copy) - % PAGE_SIZE; - if (start_offset) - pgs_copied--; - } else { - start_offset = 0; - } - } + if (copy > len) + copy = len; -end: - if (vm_write) { - for (j = 0; j < pages_pinned; j++) { - if (j < pgs_copied) - set_page_dirty_lock(process_pages[j]); - put_page(process_pages[j]); + if (vm_write) { + copied = copy_page_from_iter(page, offset, copy, iter); + set_page_dirty_lock(page); + } else { + copied = copy_page_to_iter(page, offset, copy, iter); } - } else { - for (j = 0; j < pages_pinned; j++) - put_page(process_pages[j]); + len -= copied; + if (copied < copy && iov_iter_count(iter)) + return -EFAULT; + offset = 0; } - - return rc; + return 0; } /* Maximum number of pages kmalloc'd to hold struct page's during copy */ @@ -155,67 +66,60 @@ end: * process_vm_rw_single_vec - read/write pages from task specified * @addr: start memory address of target process * @len: size of area to copy to/from - * @lvec: iovec array specifying where to copy to/from locally - * @lvec_cnt: number of elements in iovec array - * @lvec_current: index in iovec array we are up to - * @lvec_offset: offset in bytes from current iovec iov_base we are up to + * @iter: where to copy to/from locally * @process_pages: struct pages area that can store at least * nr_pages_to_copy struct page pointers * @mm: mm for task * @task: task to read/write from * @vm_write: 0 means copy from, 1 means copy to - * @bytes_copied: returns number of bytes successfully copied * Returns 0 on success or on failure error code */ static int process_vm_rw_single_vec(unsigned long addr, unsigned long len, - const struct iovec *lvec, - unsigned long lvec_cnt, - unsigned long *lvec_current, - size_t *lvec_offset, + struct iov_iter *iter, struct page **process_pages, struct mm_struct *mm, struct task_struct *task, - int vm_write, - ssize_t *bytes_copied) + int vm_write) { unsigned long pa = addr & PAGE_MASK; unsigned long start_offset = addr - pa; unsigned long nr_pages; - ssize_t bytes_copied_loop; ssize_t rc = 0; - unsigned long nr_pages_copied = 0; - unsigned long nr_pages_to_copy; unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES / sizeof(struct pages *); - *bytes_copied = 0; - /* Work out address and page range required */ if (len == 0) return 0; nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1; - while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) { - nr_pages_to_copy = min(nr_pages - nr_pages_copied, - max_pages_per_loop); + while (!rc && nr_pages && iov_iter_count(iter)) { + int pages = min(nr_pages, max_pages_per_loop); + size_t bytes; - rc = process_vm_rw_pages(task, mm, process_pages, pa, - start_offset, len, - lvec, lvec_cnt, - lvec_current, lvec_offset, - vm_write, nr_pages_to_copy, - &bytes_copied_loop); - start_offset = 0; - *bytes_copied += bytes_copied_loop; + /* Get the pages we're interested in */ + down_read(&mm->mmap_sem); + pages = get_user_pages(task, mm, pa, pages, + vm_write, 0, process_pages, NULL); + up_read(&mm->mmap_sem); - if (rc < 0) { - return rc; - } else { - len -= bytes_copied_loop; - nr_pages_copied += nr_pages_to_copy; - pa += nr_pages_to_copy * PAGE_SIZE; - } + if (pages <= 0) + return -EFAULT; + + bytes = pages * PAGE_SIZE - start_offset; + if (bytes > len) + bytes = len; + + rc = process_vm_rw_pages(process_pages, + start_offset, bytes, iter, + vm_write); + len -= bytes; + start_offset = 0; + nr_pages -= pages; + pa += pages * PAGE_SIZE; + while (pages) + put_page(process_pages[--pages]); } return rc; @@ -228,8 +132,7 @@ static int process_vm_rw_single_vec(unsigned long addr, /** * process_vm_rw_core - core of reading/writing pages from task specified * @pid: PID of process to read/write from/to - * @lvec: iovec array specifying where to copy to/from locally - * @liovcnt: size of lvec array + * @iter: where to copy to/from locally * @rvec: iovec array specifying where to copy to/from in the other process * @riovcnt: size of rvec array * @flags: currently unused @@ -238,8 +141,7 @@ static int process_vm_rw_single_vec(unsigned long addr, * return less bytes than expected if an error occurs during the copying * process. */ -static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, - unsigned long liovcnt, +static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, const struct iovec *rvec, unsigned long riovcnt, unsigned long flags, int vm_write) @@ -250,13 +152,10 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, struct mm_struct *mm; unsigned long i; ssize_t rc = 0; - ssize_t bytes_copied_loop; - ssize_t bytes_copied = 0; unsigned long nr_pages = 0; unsigned long nr_pages_iov; - unsigned long iov_l_curr_idx = 0; - size_t iov_l_curr_offset = 0; ssize_t iov_len; + size_t total_len = iov_iter_count(iter); /* * Work out how many pages of struct pages we're going to need @@ -310,24 +209,20 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, goto put_task_struct; } - for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) { + for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++) rc = process_vm_rw_single_vec( (unsigned long)rvec[i].iov_base, rvec[i].iov_len, - lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset, - process_pages, mm, task, vm_write, &bytes_copied_loop); - bytes_copied += bytes_copied_loop; - if (rc != 0) { - /* If we have managed to copy any data at all then - we return the number of bytes copied. Otherwise - we return the error code */ - if (bytes_copied) - rc = bytes_copied; - goto put_mm; - } - } + iter, process_pages, mm, task, vm_write); + + /* copied = space before - space after */ + total_len -= iov_iter_count(iter); + + /* If we have managed to copy any data at all then + we return the number of bytes copied. Otherwise + we return the error code */ + if (total_len) + rc = total_len; - rc = bytes_copied; -put_mm: mmput(mm); put_task_struct: @@ -363,6 +258,7 @@ static ssize_t process_vm_rw(pid_t pid, struct iovec iovstack_r[UIO_FASTIOV]; struct iovec *iov_l = iovstack_l; struct iovec *iov_r = iovstack_r; + struct iov_iter iter; ssize_t rc; if (flags != 0) @@ -378,13 +274,14 @@ static ssize_t process_vm_rw(pid_t pid, if (rc <= 0) goto free_iovecs; + iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc); + rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); if (rc <= 0) goto free_iovecs; - rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, - vm_write); + rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write); free_iovecs: if (iov_r != iovstack_r) @@ -412,7 +309,7 @@ SYSCALL_DEFINE6(process_vm_writev, pid_t, pid, #ifdef CONFIG_COMPAT -asmlinkage ssize_t +static ssize_t compat_process_vm_rw(compat_pid_t pid, const struct compat_iovec __user *lvec, unsigned long liovcnt, @@ -424,17 +321,12 @@ compat_process_vm_rw(compat_pid_t pid, struct iovec iovstack_r[UIO_FASTIOV]; struct iovec *iov_l = iovstack_l; struct iovec *iov_r = iovstack_r; + struct iov_iter iter; ssize_t rc = -EFAULT; if (flags != 0) return -EINVAL; - if (!access_ok(VERIFY_READ, lvec, liovcnt * sizeof(*lvec))) - goto out; - - if (!access_ok(VERIFY_READ, rvec, riovcnt * sizeof(*rvec))) - goto out; - if (vm_write) rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV, iovstack_l, @@ -445,44 +337,40 @@ compat_process_vm_rw(compat_pid_t pid, &iov_l); if (rc <= 0) goto free_iovecs; + iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc); rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); if (rc <= 0) goto free_iovecs; - rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, - vm_write); + rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write); free_iovecs: if (iov_r != iovstack_r) kfree(iov_r); if (iov_l != iovstack_l) kfree(iov_l); - -out: return rc; } -asmlinkage ssize_t -compat_sys_process_vm_readv(compat_pid_t pid, - const struct compat_iovec __user *lvec, - unsigned long liovcnt, - const struct compat_iovec __user *rvec, - unsigned long riovcnt, - unsigned long flags) +COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid, + const struct compat_iovec __user *, lvec, + compat_ulong_t, liovcnt, + const struct compat_iovec __user *, rvec, + compat_ulong_t, riovcnt, + compat_ulong_t, flags) { return compat_process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0); } -asmlinkage ssize_t -compat_sys_process_vm_writev(compat_pid_t pid, - const struct compat_iovec __user *lvec, - unsigned long liovcnt, - const struct compat_iovec __user *rvec, - unsigned long riovcnt, - unsigned long flags) +COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid, + const struct compat_iovec __user *, lvec, + compat_ulong_t, liovcnt, + const struct compat_iovec __user *, rvec, + compat_ulong_t, riovcnt, + compat_ulong_t, flags) { return compat_process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1); diff --git a/mm/readahead.c b/mm/readahead.c index 7963f239123..0ca36a7770b 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,9 +8,7 @@ */ #include <linux/kernel.h> -#include <linux/fs.h> #include <linux/gfp.h> -#include <linux/mm.h> #include <linux/export.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> @@ -20,6 +18,8 @@ #include <linux/syscalls.h> #include <linux/file.h> +#include "internal.h" + /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. @@ -48,7 +48,7 @@ static void read_cache_pages_invalidate_page(struct address_space *mapping, if (!trylock_page(page)) BUG(); page->mapping = mapping; - do_invalidatepage(page, 0); + do_invalidatepage(page, 0, PAGE_CACHE_SIZE); page->mapping = NULL; unlock_page(page); } @@ -149,8 +149,7 @@ out: * * Returns the number of pages requested, or the maximum amount of I/O allowed. */ -static int -__do_page_cache_readahead(struct address_space *mapping, struct file *filp, +int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read, unsigned long lookahead_size) { @@ -179,7 +178,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, page_offset); rcu_read_unlock(); - if (page) + if (page && !radix_tree_exceptional_entry(page)) continue; page = page_cache_alloc_readahead(mapping); @@ -211,8 +210,6 @@ out: int force_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read) { - int ret = 0; - if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages)) return -EINVAL; @@ -226,39 +223,23 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, this_chunk = nr_to_read; err = __do_page_cache_readahead(mapping, filp, offset, this_chunk, 0); - if (err < 0) { - ret = err; - break; - } - ret += err; + if (err < 0) + return err; + offset += this_chunk; nr_to_read -= this_chunk; } - return ret; + return 0; } +#define MAX_READAHEAD ((512*4096)/PAGE_CACHE_SIZE) /* * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a * sensible upper limit. */ unsigned long max_sane_readahead(unsigned long nr) { - return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE) - + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2); -} - -/* - * Submit IO for the read-ahead request in file_ra_state. - */ -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, struct file *filp) -{ - int actual; - - actual = __do_page_cache_readahead(mapping, filp, - ra->start, ra->size, ra->async_size); - - return actual; + return min(nr, MAX_READAHEAD); } /* @@ -351,7 +332,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t head; rcu_read_lock(); - head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max); + head = page_cache_prev_hole(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; @@ -371,10 +352,10 @@ static int try_context_readahead(struct address_space *mapping, size = count_history_pages(mapping, ra, offset, max); /* - * no history pages: + * not enough history pages: * it could be a random read */ - if (!size) + if (size <= req_size) return 0; /* @@ -385,8 +366,8 @@ static int try_context_readahead(struct address_space *mapping, size *= 2; ra->start = offset; - ra->size = get_init_ra_size(size + req_size, max); - ra->async_size = ra->size; + ra->size = min(size + req_size, max); + ra->async_size = 1; return 1; } @@ -401,6 +382,7 @@ ondemand_readahead(struct address_space *mapping, unsigned long req_size) { unsigned long max = max_sane_readahead(ra->ra_pages); + pgoff_t prev_offset; /* * start of file @@ -430,7 +412,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = radix_tree_next_hole(&mapping->page_tree, offset+1,max); + start = page_cache_next_hole(mapping, offset + 1, max); rcu_read_unlock(); if (!start || start - offset > max) @@ -452,8 +434,11 @@ ondemand_readahead(struct address_space *mapping, /* * sequential cache miss + * trivial case: (offset - prev_offset) == 1 + * unaligned reads: (offset - prev_offset) == 0 */ - if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL) + prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT; + if (offset - prev_offset <= 1UL) goto initial_readahead; /* @@ -569,14 +554,13 @@ static ssize_t do_readahead(struct address_space *mapping, struct file *filp, pgoff_t index, unsigned long nr) { - if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage) + if (!mapping || !mapping->a_ops) return -EINVAL; - force_page_cache_readahead(mapping, filp, index, nr); - return 0; + return force_page_cache_readahead(mapping, filp, index, nr); } -SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count) +SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { ssize_t ret; struct fd f; @@ -595,10 +579,3 @@ SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count) } return ret; } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_readahead(long fd, loff_t offset, long count) -{ - return SYSC_readahead((int) fd, offset, (size_t) count); -} -SYSCALL_ALIAS(sys_readahead, SyS_readahead); -#endif diff --git a/mm/rmap.c b/mm/rmap.c index 2c78f8cadc9..22a4a7699cd 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -103,9 +103,10 @@ static inline void anon_vma_free(struct anon_vma *anon_vma) * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ + might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); @@ -191,7 +192,7 @@ int anon_vma_prepare(struct vm_area_struct *vma) avc = NULL; } spin_unlock(&mm->page_table_lock); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); @@ -308,7 +309,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); return 0; @@ -426,8 +427,9 @@ struct anon_vma *page_get_anon_vma(struct page *page) * above cannot corrupt). */ if (!page_mapped(page)) { + rcu_read_unlock(); put_anon_vma(anon_vma); - anon_vma = NULL; + return NULL; } out: rcu_read_unlock(); @@ -477,9 +479,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page) } if (!page_mapped(page)) { + rcu_read_unlock(); put_anon_vma(anon_vma); - anon_vma = NULL; - goto out; + return NULL; } /* we pinned the anon_vma, its safe to sleep */ @@ -515,11 +517,7 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma) static inline unsigned long __vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - - if (unlikely(is_vm_hugetlb_page(vma))) - pgoff = page->index << huge_page_order(page_hstate(page)); - + pgoff_t pgoff = page_to_pgoff(page); return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); } @@ -567,6 +565,7 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) pgd_t *pgd; pud_t *pud; pmd_t *pmd = NULL; + pmd_t pmde; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) @@ -577,7 +576,13 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) goto out; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) + /* + * Some THP functions use the sequence pmdp_clear_flush(), set_pmd_at() + * without holding anon_vma lock for write. So when looking for a + * genuine pmde (in which to find pte), test present and !THP together. + */ + pmde = ACCESS_ONCE(*pmd); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: return pmd; @@ -600,8 +605,12 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm, spinlock_t *ptl; if (unlikely(PageHuge(page))) { + /* when pud is not present, pte will be NULL */ pte = huge_pte_offset(mm, address); - ptl = &mm->page_table_lock; + if (!pte) + return NULL; + + ptl = huge_pte_lockptr(page_hstate(page), mm, pte); goto check; } @@ -609,9 +618,6 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm, if (!pmd) return NULL; - if (pmd_trans_huge(*pmd)) - return NULL; - pte = pte_offset_map(pmd, address); /* Make a quick check before getting the lock */ if (!sync && !pte_present(*pte)) { @@ -656,46 +662,47 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) return 1; } +struct page_referenced_arg { + int mapcount; + int referenced; + unsigned long vm_flags; + struct mem_cgroup *memcg; +}; /* - * Subfunctions of page_referenced: page_referenced_one called - * repeatedly from either page_referenced_anon or page_referenced_file. + * arg: page_referenced_arg will be passed */ -int page_referenced_one(struct page *page, struct vm_area_struct *vma, - unsigned long address, unsigned int *mapcount, - unsigned long *vm_flags) +static int page_referenced_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; int referenced = 0; + struct page_referenced_arg *pra = arg; if (unlikely(PageTransHuge(page))) { pmd_t *pmd; - spin_lock(&mm->page_table_lock); /* * rmap might return false positives; we must filter * these out using page_check_address_pmd(). */ pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_FLAG); - if (!pmd) { - spin_unlock(&mm->page_table_lock); - goto out; - } + PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl); + if (!pmd) + return SWAP_AGAIN; if (vma->vm_flags & VM_LOCKED) { - spin_unlock(&mm->page_table_lock); - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; + spin_unlock(ptl); + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ } /* go ahead even if the pmd is pmd_trans_splitting() */ if (pmdp_clear_flush_young_notify(vma, address, pmd)) referenced++; - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); } else { pte_t *pte; - spinlock_t *ptl; /* * rmap might return false positives; we must filter @@ -703,13 +710,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, */ pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) - goto out; + return SWAP_AGAIN; if (vma->vm_flags & VM_LOCKED) { pte_unmap_unlock(pte, ptl); - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ } if (ptep_clear_flush_young_notify(vma, address, pte)) { @@ -720,119 +726,33 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, * mapping is already gone, the unmap path will have * set PG_referenced or activated the page. */ - if (likely(!VM_SequentialReadHint(vma))) + if (likely(!(vma->vm_flags & VM_SEQ_READ))) referenced++; } pte_unmap_unlock(pte, ptl); } - (*mapcount)--; - - if (referenced) - *vm_flags |= vma->vm_flags; -out: - return referenced; -} - -static int page_referenced_anon(struct page *page, - struct mem_cgroup *memcg, - unsigned long *vm_flags) -{ - unsigned int mapcount; - struct anon_vma *anon_vma; - pgoff_t pgoff; - struct anon_vma_chain *avc; - int referenced = 0; - - anon_vma = page_lock_anon_vma_read(page); - if (!anon_vma) - return referenced; - - mapcount = page_mapcount(page); - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - struct vm_area_struct *vma = avc->vma; - unsigned long address = vma_address(page, vma); - /* - * If we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups - */ - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - referenced += page_referenced_one(page, vma, address, - &mapcount, vm_flags); - if (!mapcount) - break; + if (referenced) { + pra->referenced++; + pra->vm_flags |= vma->vm_flags; } - page_unlock_anon_vma_read(anon_vma); - return referenced; + pra->mapcount--; + if (!pra->mapcount) + return SWAP_SUCCESS; /* To break the loop */ + + return SWAP_AGAIN; } -/** - * page_referenced_file - referenced check for object-based rmap - * @page: the page we're checking references on. - * @memcg: target memory control group - * @vm_flags: collect encountered vma->vm_flags who actually referenced the page - * - * For an object-based mapped page, find all the places it is mapped and - * check/clear the referenced flag. This is done by following the page->mapping - * pointer, then walking the chain of vmas it holds. It returns the number - * of references it found. - * - * This function is only called from page_referenced for object-based pages. - */ -static int page_referenced_file(struct page *page, - struct mem_cgroup *memcg, - unsigned long *vm_flags) +static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) { - unsigned int mapcount; - struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct vm_area_struct *vma; - int referenced = 0; - - /* - * The caller's checks on page->mapping and !PageAnon have made - * sure that this is a file page: the check for page->mapping - * excludes the case just before it gets set on an anon page. - */ - BUG_ON(PageAnon(page)); - - /* - * The page lock not only makes sure that page->mapping cannot - * suddenly be NULLified by truncation, it makes sure that the - * structure at mapping cannot be freed and reused yet, - * so we can safely take mapping->i_mmap_mutex. - */ - BUG_ON(!PageLocked(page)); - - mutex_lock(&mapping->i_mmap_mutex); + struct page_referenced_arg *pra = arg; + struct mem_cgroup *memcg = pra->memcg; - /* - * i_mmap_mutex does not stabilize mapcount at all, but mapcount - * is more likely to be accurate if we note it after spinning. - */ - mapcount = page_mapcount(page); - - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - unsigned long address = vma_address(page, vma); - /* - * If we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups - */ - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - referenced += page_referenced_one(page, vma, address, - &mapcount, vm_flags); - if (!mapcount) - break; - } + if (!mm_match_cgroup(vma->vm_mm, memcg)) + return true; - mutex_unlock(&mapping->i_mmap_mutex); - return referenced; + return false; } /** @@ -850,44 +770,57 @@ int page_referenced(struct page *page, struct mem_cgroup *memcg, unsigned long *vm_flags) { - int referenced = 0; + int ret; int we_locked = 0; + struct page_referenced_arg pra = { + .mapcount = page_mapcount(page), + .memcg = memcg, + }; + struct rmap_walk_control rwc = { + .rmap_one = page_referenced_one, + .arg = (void *)&pra, + .anon_lock = page_lock_anon_vma_read, + }; *vm_flags = 0; - if (page_mapped(page) && page_rmapping(page)) { - if (!is_locked && (!PageAnon(page) || PageKsm(page))) { - we_locked = trylock_page(page); - if (!we_locked) { - referenced++; - goto out; - } - } - if (unlikely(PageKsm(page))) - referenced += page_referenced_ksm(page, memcg, - vm_flags); - else if (PageAnon(page)) - referenced += page_referenced_anon(page, memcg, - vm_flags); - else if (page->mapping) - referenced += page_referenced_file(page, memcg, - vm_flags); - if (we_locked) - unlock_page(page); - - if (page_test_and_clear_young(page_to_pfn(page))) - referenced++; + if (!page_mapped(page)) + return 0; + + if (!page_rmapping(page)) + return 0; + + if (!is_locked && (!PageAnon(page) || PageKsm(page))) { + we_locked = trylock_page(page); + if (!we_locked) + return 1; } -out: - return referenced; + + /* + * If we are reclaiming on behalf of a cgroup, skip + * counting on behalf of references from different + * cgroups + */ + if (memcg) { + rwc.invalid_vma = invalid_page_referenced_vma; + } + + ret = rmap_walk(page, &rwc); + *vm_flags = pra.vm_flags; + + if (we_locked) + unlock_page(page); + + return pra.referenced; } static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, - unsigned long address) + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; pte_t *pte; spinlock_t *ptl; int ret = 0; + int *cleaned = arg; pte = page_check_address(page, mm, address, &ptl, 1); if (!pte) @@ -906,44 +839,44 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); - if (ret) + if (ret) { mmu_notifier_invalidate_page(mm, address); + (*cleaned)++; + } out: - return ret; + return SWAP_AGAIN; } -static int page_mkclean_file(struct address_space *mapping, struct page *page) +static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct vm_area_struct *vma; - int ret = 0; - - BUG_ON(PageAnon(page)); + if (vma->vm_flags & VM_SHARED) + return false; - mutex_lock(&mapping->i_mmap_mutex); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - if (vma->vm_flags & VM_SHARED) { - unsigned long address = vma_address(page, vma); - ret += page_mkclean_one(page, vma, address); - } - } - mutex_unlock(&mapping->i_mmap_mutex); - return ret; + return true; } int page_mkclean(struct page *page) { - int ret = 0; + int cleaned = 0; + struct address_space *mapping; + struct rmap_walk_control rwc = { + .arg = (void *)&cleaned, + .rmap_one = page_mkclean_one, + .invalid_vma = invalid_mkclean_vma, + }; BUG_ON(!PageLocked(page)); - if (page_mapped(page)) { - struct address_space *mapping = page_mapping(page); - if (mapping) - ret = page_mkclean_file(mapping, page); - } + if (!page_mapped(page)) + return 0; - return ret; + mapping = page_mapping(page); + if (!mapping) + return 0; + + rmap_walk(page, &rwc); + + return cleaned; } EXPORT_SYMBOL_GPL(page_mkclean); @@ -963,9 +896,9 @@ void page_move_anon_rmap(struct page *page, { struct anon_vma *anon_vma = vma->anon_vma; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON(!anon_vma); - VM_BUG_ON(page->index != linear_page_index(vma, address)); + VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; page->mapping = (struct address_space *) anon_vma; @@ -1055,16 +988,22 @@ void do_page_add_anon_rmap(struct page *page, { int first = atomic_inc_and_test(&page->_mapcount); if (first) { - if (!PageTransHuge(page)) - __inc_zone_page_state(page, NR_ANON_PAGES); - else + /* + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption + * disabled. + */ + if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); } if (unlikely(PageKsm(page))) return; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); /* address might be in next vma when migration races vma_adjust */ if (first) __page_set_anon_rmap(page, vma, address, exclusive); @@ -1088,15 +1027,30 @@ void page_add_new_anon_rmap(struct page *page, VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); SetPageSwapBacked(page); atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ - if (!PageTransHuge(page)) - __inc_zone_page_state(page, NR_ANON_PAGES); - else + if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); __page_set_anon_rmap(page, vma, address, 1); - if (!mlocked_vma_newpage(vma, page)) - lru_cache_add_lru(page, LRU_ACTIVE_ANON); - else - add_page_to_unevictable_list(page); + + VM_BUG_ON_PAGE(PageLRU(page), page); + if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) { + SetPageActive(page); + lru_cache_add(page); + return; + } + + if (!TestSetPageMlocked(page)) { + /* + * We use the irq-unsafe __mod_zone_page_stat because this + * counter is not modified from interrupt context, and the pte + * lock is held(spinlock), which implies preemption disabled. + */ + __mod_zone_page_state(page_zone(page), NR_MLOCK, + hpage_nr_pages(page)); + count_vm_event(UNEVICTABLE_PGMLOCKED); + } + add_page_to_unevictable_list(page); } /** @@ -1113,7 +1067,7 @@ void page_add_file_rmap(struct page *page) mem_cgroup_begin_update_page_stat(page, &locked, &flags); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED); + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); } mem_cgroup_end_update_page_stat(page, &locked, &flags); } @@ -1126,7 +1080,6 @@ void page_add_file_rmap(struct page *page) */ void page_remove_rmap(struct page *page) { - struct address_space *mapping = page_mapping(page); bool anon = PageAnon(page); bool locked; unsigned long flags; @@ -1144,44 +1097,26 @@ void page_remove_rmap(struct page *page) goto out; /* - * Now that the last pte has gone, s390 must transfer dirty - * flag from storage key to struct page. We can usually skip - * this if the page is anon, so about to be freed; but perhaps - * not if it's in swapcache - there might be another pte slot - * containing the swap entry, but page not yet written to swap. - * - * And we can skip it on file pages, so long as the filesystem - * participates in dirty tracking (note that this is not only an - * optimization but also solves problems caused by dirty flag in - * storage key getting set by a write from inside kernel); but need to - * catch shm and tmpfs and ramfs pages which have been modified since - * creation by read fault. - * - * Note that mapping must be decided above, before decrementing - * mapcount (which luckily provides a barrier): once page is unmapped, - * it could be truncated and page->mapping reset to NULL at any moment. - * Note also that we are relying on page_mapping(page) to set mapping - * to &swapper_space when PageSwapCache(page). - */ - if (mapping && !mapping_cap_account_dirty(mapping) && - page_test_and_clear_dirty(page_to_pfn(page), 1)) - set_page_dirty(page); - /* * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED * and not charged by memcg for now. + * + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption disabled. */ if (unlikely(PageHuge(page))) goto out; if (anon) { mem_cgroup_uncharge_page(page); - if (!PageTransHuge(page)) - __dec_zone_page_state(page, NR_ANON_PAGES); - else + if (PageTransHuge(page)) __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + -hpage_nr_pages(page)); } else { __dec_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED); + mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); mem_cgroup_end_update_page_stat(page, &locked, &flags); } if (unlikely(PageMlocked(page))) @@ -1202,17 +1137,17 @@ out: } /* - * Subfunctions of try_to_unmap: try_to_unmap_one called - * repeatedly from try_to_unmap_ksm, try_to_unmap_anon or try_to_unmap_file. + * @arg: enum ttu_flags will be passed to this argument */ -int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, - unsigned long address, enum ttu_flags flags) +static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; pte_t *pte; pte_t pteval; spinlock_t *ptl; int ret = SWAP_AGAIN; + enum ttu_flags flags = (enum ttu_flags)arg; pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) @@ -1227,7 +1162,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED) goto out_mlock; - if (TTU_ACTION(flags) == TTU_MUNLOCK) + if (flags & TTU_MUNLOCK) goto out_unmap; } if (!(flags & TTU_IGNORE_ACCESS)) { @@ -1257,8 +1192,19 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } set_pte_at(mm, address, pte, swp_entry_to_pte(make_hwpoison_entry(page))); + } else if (pte_unused(pteval)) { + /* + * The guest indicated that the page content is of no + * interest anymore. Simply discard the pte, vmscan + * will take care of the rest. + */ + if (PageAnon(page)) + dec_mm_counter(mm, MM_ANONPAGES); + else + dec_mm_counter(mm, MM_FILEPAGES); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(page) }; + pte_t swp_pte; if (PageSwapCache(page)) { /* @@ -1284,13 +1230,16 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ - BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION); + BUG_ON(!(flags & TTU_MIGRATION)); entry = make_migration_entry(page, pte_write(pteval)); } - set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + set_pte_at(mm, address, pte, swp_pte); BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && - (TTU_ACTION(flags) == TTU_MIGRATION)) { + (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ swp_entry_t entry; entry = make_migration_entry(page, pte_write(pteval)); @@ -1303,7 +1252,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, out_unmap: pte_unmap_unlock(pte, ptl); - if (ret != SWAP_FAIL) + if (ret != SWAP_FAIL && !(flags & TTU_MUNLOCK)) mmu_notifier_invalidate_page(mm, address); out: return ret; @@ -1410,9 +1359,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, BUG_ON(!page || PageAnon(page)); if (locked_vma) { - mlock_vma_page(page); /* no-op if already mlocked */ - if (page == check_page) + if (page == check_page) { + /* we know we have check_page locked */ + mlock_vma_page(page); ret = SWAP_MLOCK; + } else if (trylock_page(page)) { + /* + * If we can lock the page, perform mlock. + * Otherwise leave the page alone, it will be + * eventually encountered again later. + */ + mlock_vma_page(page); + unlock_page(page); + } continue; /* don't unmap */ } @@ -1424,8 +1383,12 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, pteval = ptep_clear_flush(vma, address, pte); /* If nonlinear, store the file page offset in the pte. */ - if (page->index != linear_page_index(vma, address)) - set_pte_at(mm, address, pte, pgoff_to_pte(page->index)); + if (page->index != linear_page_index(vma, address)) { + pte_t ptfile = pgoff_to_pte(page->index); + if (pte_soft_dirty(pteval)) + ptfile = pte_file_mksoft_dirty(ptfile); + set_pte_at(mm, address, pte, ptfile); + } /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) @@ -1443,93 +1406,9 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, return ret; } -bool is_vma_temporary_stack(struct vm_area_struct *vma) +static int try_to_unmap_nonlinear(struct page *page, + struct address_space *mapping, void *arg) { - int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); - - if (!maybe_stack) - return false; - - if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == - VM_STACK_INCOMPLETE_SETUP) - return true; - - return false; -} - -/** - * try_to_unmap_anon - unmap or unlock anonymous page using the object-based - * rmap method - * @page: the page to unmap/unlock - * @flags: action and flags - * - * Find all the mappings of a page using the mapping pointer and the vma chains - * contained in the anon_vma struct it points to. - * - * This function is only called from try_to_unmap/try_to_munlock for - * anonymous pages. - * When called from try_to_munlock(), the mmap_sem of the mm containing the vma - * where the page was found will be held for write. So, we won't recheck - * vm_flags for that VMA. That should be OK, because that vma shouldn't be - * 'LOCKED. - */ -static int try_to_unmap_anon(struct page *page, enum ttu_flags flags) -{ - struct anon_vma *anon_vma; - pgoff_t pgoff; - struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; - - anon_vma = page_lock_anon_vma_read(page); - if (!anon_vma) - return ret; - - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - struct vm_area_struct *vma = avc->vma; - unsigned long address; - - /* - * During exec, a temporary VMA is setup and later moved. - * The VMA is moved under the anon_vma lock but not the - * page tables leading to a race where migration cannot - * find the migration ptes. Rather than increasing the - * locking requirements of exec(), migration skips - * temporary VMAs until after exec() completes. - */ - if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && - is_vma_temporary_stack(vma)) - continue; - - address = vma_address(page, vma); - ret = try_to_unmap_one(page, vma, address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) - break; - } - - page_unlock_anon_vma_read(anon_vma); - return ret; -} - -/** - * try_to_unmap_file - unmap/unlock file page using the object-based rmap method - * @page: the page to unmap/unlock - * @flags: action and flags - * - * Find all the mappings of a page using the mapping pointer and the vma chains - * contained in the address_space struct it points to. - * - * This function is only called from try_to_unmap/try_to_munlock for - * object-based pages. - * When called from try_to_munlock(), the mmap_sem of the mm containing the vma - * where the page was found will be held for write. So, we won't recheck - * vm_flags for that VMA. That should be OK, because that vma shouldn't be - * 'LOCKED. - */ -static int try_to_unmap_file(struct page *page, enum ttu_flags flags) -{ - struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; int ret = SWAP_AGAIN; unsigned long cursor; @@ -1537,27 +1416,9 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) unsigned long max_nl_size = 0; unsigned int mapcount; - mutex_lock(&mapping->i_mmap_mutex); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - unsigned long address = vma_address(page, vma); - ret = try_to_unmap_one(page, vma, address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) - goto out; - } - - if (list_empty(&mapping->i_mmap_nonlinear)) - goto out; - - /* - * We don't bother to try to find the munlocked page in nonlinears. - * It's costly. Instead, later, page reclaim logic may call - * try_to_unmap(TTU_MUNLOCK) and recover PG_mlocked lazily. - */ - if (TTU_ACTION(flags) == TTU_MUNLOCK) - goto out; + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.nonlinear) { cursor = (unsigned long) vma->vm_private_data; if (cursor > max_nl_cursor) max_nl_cursor = cursor; @@ -1567,8 +1428,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) } if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - ret = SWAP_FAIL; - goto out; + return SWAP_FAIL; } /* @@ -1580,7 +1440,8 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) */ mapcount = page_mapcount(page); if (!mapcount) - goto out; + return ret; + cond_resched(); max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; @@ -1588,10 +1449,11 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) max_nl_cursor = CLUSTER_SIZE; do { - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.nonlinear) { + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { + cursor = (unsigned long) vma->vm_private_data; - while ( cursor < max_nl_cursor && + while (cursor < max_nl_cursor && cursor < vma->vm_end - vma->vm_start) { if (try_to_unmap_cluster(cursor, &mapcount, vma, page) == SWAP_MLOCK) @@ -1599,7 +1461,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) cursor += CLUSTER_SIZE; vma->vm_private_data = (void *) cursor; if ((int)mapcount <= 0) - goto out; + return ret; } vma->vm_private_data = (void *) max_nl_cursor; } @@ -1614,11 +1476,34 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) */ list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) vma->vm_private_data = NULL; -out: - mutex_unlock(&mapping->i_mmap_mutex); + return ret; } +bool is_vma_temporary_stack(struct vm_area_struct *vma) +{ + int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); + + if (!maybe_stack) + return false; + + if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == + VM_STACK_INCOMPLETE_SETUP) + return true; + + return false; +} + +static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) +{ + return is_vma_temporary_stack(vma); +} + +static int page_not_mapped(struct page *page) +{ + return !page_mapped(page); +}; + /** * try_to_unmap - try to remove all page table mappings to a page * @page: the page to get unmapped @@ -1636,16 +1521,29 @@ out: int try_to_unmap(struct page *page, enum ttu_flags flags) { int ret; + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)flags, + .done = page_not_mapped, + .file_nonlinear = try_to_unmap_nonlinear, + .anon_lock = page_lock_anon_vma_read, + }; - BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageHuge(page) && PageTransHuge(page)); + VM_BUG_ON_PAGE(!PageHuge(page) && PageTransHuge(page), page); + + /* + * During exec, a temporary VMA is setup and later moved. + * The VMA is moved under the anon_vma lock but not the + * page tables leading to a race where migration cannot + * find the migration ptes. Rather than increasing the + * locking requirements of exec(), migration skips + * temporary VMAs until after exec() completes. + */ + if ((flags & TTU_MIGRATION) && !PageKsm(page) && PageAnon(page)) + rwc.invalid_vma = invalid_migration_vma; + + ret = rmap_walk(page, &rwc); - if (unlikely(PageKsm(page))) - ret = try_to_unmap_ksm(page, flags); - else if (PageAnon(page)) - ret = try_to_unmap_anon(page, flags); - else - ret = try_to_unmap_file(page, flags); if (ret != SWAP_MLOCK && !page_mapped(page)) ret = SWAP_SUCCESS; return ret; @@ -1668,38 +1566,43 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) */ int try_to_munlock(struct page *page) { - VM_BUG_ON(!PageLocked(page) || PageLRU(page)); + int ret; + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)TTU_MUNLOCK, + .done = page_not_mapped, + /* + * We don't bother to try to find the munlocked page in + * nonlinears. It's costly. Instead, later, page reclaim logic + * may call try_to_unmap() and recover PG_mlocked lazily. + */ + .file_nonlinear = NULL, + .anon_lock = page_lock_anon_vma_read, - if (unlikely(PageKsm(page))) - return try_to_unmap_ksm(page, TTU_MUNLOCK); - else if (PageAnon(page)) - return try_to_unmap_anon(page, TTU_MUNLOCK); - else - return try_to_unmap_file(page, TTU_MUNLOCK); + }; + + VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); + + ret = rmap_walk(page, &rwc); + return ret; } void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; + anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); - - anon_vma_free(anon_vma); } -#ifdef CONFIG_MIGRATION -/* - * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file(): - * Called by migrate.c to remove migration ptes, but might be used more later. - */ -static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +static struct anon_vma *rmap_walk_anon_lock(struct page *page, + struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; + + if (rwc->anon_lock) + return rwc->anon_lock(page); /* * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() @@ -1709,58 +1612,120 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, */ anon_vma = page_anon_vma(page); if (!anon_vma) - return ret; + return NULL; + anon_vma_lock_read(anon_vma); + return anon_vma; +} + +/* + * rmap_walk_anon - do something to anonymous page using the object-based + * rmap method + * @page: the page to be handled + * @rwc: control variable according to each walk type + * + * Find all the mappings of a page using the mapping pointer and the vma chains + * contained in the anon_vma struct it points to. + * + * When called from try_to_munlock(), the mmap_sem of the mm containing the vma + * where the page was found will be held for write. So, we won't recheck + * vm_flags for that VMA. That should be OK, because that vma shouldn't be + * LOCKED. + */ +static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) +{ + struct anon_vma *anon_vma; + pgoff_t pgoff = page_to_pgoff(page); + struct anon_vma_chain *avc; + int ret = SWAP_AGAIN; + + anon_vma = rmap_walk_anon_lock(page, rwc); + if (!anon_vma) + return ret; + anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); - ret = rmap_one(page, vma, address, arg); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + ret = rwc->rmap_one(page, vma, address, rwc->arg); if (ret != SWAP_AGAIN) break; + if (rwc->done && rwc->done(page)) + break; } anon_vma_unlock_read(anon_vma); return ret; } -static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +/* + * rmap_walk_file - do something to file page using the object-based rmap method + * @page: the page to be handled + * @rwc: control variable according to each walk type + * + * Find all the mappings of a page using the mapping pointer and the vma chains + * contained in the address_space struct it points to. + * + * When called from try_to_munlock(), the mmap_sem of the mm containing the vma + * where the page was found will be held for write. So, we won't recheck + * vm_flags for that VMA. That should be OK, because that vma shouldn't be + * LOCKED. + */ +static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) { struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page_to_pgoff(page); struct vm_area_struct *vma; int ret = SWAP_AGAIN; + /* + * The page lock not only makes sure that page->mapping cannot + * suddenly be NULLified by truncation, it makes sure that the + * structure at mapping cannot be freed and reused yet, + * so we can safely take mapping->i_mmap_mutex. + */ + VM_BUG_ON(!PageLocked(page)); + if (!mapping) return ret; mutex_lock(&mapping->i_mmap_mutex); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); - ret = rmap_one(page, vma, address, arg); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + ret = rwc->rmap_one(page, vma, address, rwc->arg); if (ret != SWAP_AGAIN) - break; + goto done; + if (rwc->done && rwc->done(page)) + goto done; } - /* - * No nonlinear handling: being always shared, nonlinear vmas - * never contain migration ptes. Decide what to do about this - * limitation to linear when we need rmap_walk() on nonlinear. - */ + + if (!rwc->file_nonlinear) + goto done; + + if (list_empty(&mapping->i_mmap_nonlinear)) + goto done; + + ret = rwc->file_nonlinear(page, mapping, rwc->arg); + +done: mutex_unlock(&mapping->i_mmap_mutex); return ret; } -int rmap_walk(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +int rmap_walk(struct page *page, struct rmap_walk_control *rwc) { - VM_BUG_ON(!PageLocked(page)); - if (unlikely(PageKsm(page))) - return rmap_walk_ksm(page, rmap_one, arg); + return rmap_walk_ksm(page, rwc); else if (PageAnon(page)) - return rmap_walk_anon(page, rmap_one, arg); + return rmap_walk_anon(page, rwc); else - return rmap_walk_file(page, rmap_one, arg); + return rmap_walk_file(page, rwc); } -#endif /* CONFIG_MIGRATION */ #ifdef CONFIG_HUGETLB_PAGE /* diff --git a/mm/shmem.c b/mm/shmem.c index 5dd56f6efdb..af68b15a8fc 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -25,11 +25,13 @@ #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> +#include <linux/ramfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/swap.h> +#include <linux/aio.h> static struct vfsmount *shm_mnt; @@ -43,7 +45,7 @@ static struct vfsmount *shm_mnt; #include <linux/xattr.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> -#include <linux/generic_acl.h> +#include <linux/posix_acl_xattr.h> #include <linux/mman.h> #include <linux/string.h> #include <linux/slab.h> @@ -78,11 +80,12 @@ static struct vfsmount *shm_mnt; #define SHORT_SYMLINK_LEN 128 /* - * shmem_fallocate and shmem_writepage communicate via inode->i_private - * (with i_mutex making sure that it has only one user at a time): - * we would prefer not to enlarge the shmem inode just for that. + * shmem_fallocate communicates with shmem_fault or shmem_writepage via + * inode->i_private (with i_mutex making sure that it has only one user at + * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { + wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ @@ -240,19 +243,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { void **pslot; - void *item = NULL; + void *item; VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); pslot = radix_tree_lookup_slot(&mapping->page_tree, index); - if (pslot) - item = radix_tree_deref_slot_protected(pslot, - &mapping->tree_lock); + if (!pslot) + return -ENOENT; + item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock); if (item != expected) return -ENOENT; - if (replacement) - radix_tree_replace_slot(pslot, replacement); - else - radix_tree_delete(&mapping->page_tree, index); + radix_tree_replace_slot(pslot, replacement); return 0; } @@ -283,8 +284,8 @@ static int shmem_add_to_page_cache(struct page *page, { int error; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageSwapBacked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); page_cache_get(page); page->mapping = mapping; @@ -329,85 +330,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) } /* - * Like find_get_pages, but collecting swap entries as well as pages. - */ -static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, - pgoff_t start, unsigned int nr_pages, - struct page **pages, pgoff_t *indices) -{ - unsigned int i; - unsigned int ret; - unsigned int nr_found; - - rcu_read_lock(); -restart: - nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - (void ***)pages, indices, start, nr_pages); - ret = 0; - for (i = 0; i < nr_found; i++) { - struct page *page; -repeat: - page = radix_tree_deref_slot((void **)pages[i]); - if (unlikely(!page)) - continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) - goto restart; - /* - * Otherwise, we must be storing a swap entry - * here as an exceptional entry: so return it - * without attempting to raise page count. - */ - goto export; - } - if (!page_cache_get_speculative(page)) - goto repeat; - - /* Has the page moved? */ - if (unlikely(page != *((void **)pages[i]))) { - page_cache_release(page); - goto repeat; - } -export: - indices[ret] = indices[i]; - pages[ret] = page; - ret++; - } - if (unlikely(!ret && nr_found)) - goto restart; - rcu_read_unlock(); - return ret; -} - -/* * Remove swap entry from radix tree, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { - int error; + void *old; spin_lock_irq(&mapping->tree_lock); - error = shmem_radix_tree_replace(mapping, index, radswap, NULL); + old = radix_tree_delete_item(&mapping->page_tree, index, radswap); spin_unlock_irq(&mapping->tree_lock); - if (!error) - free_swap_and_cache(radix_to_swp_entry(radswap)); - return error; -} - -/* - * Pagevec may contain swap entries, so shuffle up pages before releasing. - */ -static void shmem_deswap_pagevec(struct pagevec *pvec) -{ - int i, j; - - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) - pvec->pages[j++] = page; - } - pvec->nr = j; + if (old != radswap) + return -ENOENT; + free_swap_and_cache(radix_to_swp_entry(radswap)); + return 0; } /* @@ -428,12 +364,12 @@ void shmem_unlock_mapping(struct address_space *mapping) * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - PAGEVEC_SIZE, pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(pvec.pages, pvec.nr); pagevec_release(&pvec); cond_resched(); @@ -465,9 +401,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec, 0); index = start; while (index < end) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); if (!pvec.nr) break; mem_cgroup_uncharge_start(); @@ -490,13 +426,13 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, continue; if (!unfalloc || !PageUptodate(page)) { if (page->mapping == mapping) { - VM_BUG_ON(PageWriteback(page)); + VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -532,22 +468,20 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, return; index = start; - for ( ; ; ) { + while (index < end) { cond_resched(); - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + + pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.pages, indices); if (!pvec.nr) { - if (index == start || unfalloc) + /* If all gone or hole-punch or unfalloc, we're done */ + if (index == start || end != -1) break; + /* But if truncating, restart to make sure all gone */ index = start; continue; } - if ((index == start || unfalloc) && indices[0] >= end) { - shmem_deswap_pagevec(&pvec); - pagevec_release(&pvec); - break; - } mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -559,21 +493,30 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (radix_tree_exceptional_entry(page)) { if (unfalloc) continue; - nr_swaps_freed += !shmem_free_swap(mapping, - index, page); + if (shmem_free_swap(mapping, index, page)) { + /* Swap was replaced by page: retry */ + index--; + break; + } + nr_swaps_freed++; continue; } lock_page(page); if (!unfalloc || !PageUptodate(page)) { if (page->mapping == mapping) { - VM_BUG_ON(PageWriteback(page)); + VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); + } else { + /* Page was replaced by swap: retry */ + unlock_page(page); + index--; + break; } } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -619,10 +562,8 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) } setattr_copy(inode, attr); -#ifdef CONFIG_TMPFS_POSIX_ACL if (attr->ia_valid & ATTR_MODE) - error = generic_acl_chmod(inode); -#endif + error = posix_acl_chmod(inode, inode->i_mode); return error; } @@ -749,7 +690,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page) * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. */ - error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); + error = mem_cgroup_charge_file(page, current->mm, GFP_KERNEL); if (error) goto out; /* No radix_tree_preload: swap entry keeps a place for page in tree */ @@ -825,6 +766,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && + !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; @@ -1081,7 +1023,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, return -EFBIG; repeat: swap.val = 0; - page = find_lock_page(mapping, index); + page = find_lock_entry(mapping, index); if (radix_tree_exceptional_entry(page)) { swap = radix_to_swp_entry(page); page = NULL; @@ -1093,6 +1035,9 @@ repeat: goto failed; } + if (page && sgp == SGP_WRITE) + mark_page_accessed(page); + /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) @@ -1146,7 +1091,7 @@ repeat: goto failed; } - error = mem_cgroup_cache_charge(page, current->mm, + error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, @@ -1174,6 +1119,9 @@ repeat: shmem_recalc_inode(inode); spin_unlock(&info->lock); + if (sgp == SGP_WRITE) + mark_page_accessed(page); + delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); @@ -1198,13 +1146,16 @@ repeat: goto decused; } - SetPageSwapBacked(page); + __SetPageSwapBacked(page); __set_page_locked(page); - error = mem_cgroup_cache_charge(page, current->mm, + if (sgp == SGP_WRITE) + init_page_accessed(page); + + error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); if (error) goto decused; - error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, gfp, NULL); @@ -1295,10 +1246,68 @@ unlock: static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); int error; int ret = VM_FAULT_LOCKED; + /* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_mutex. So refrain from + * faulting pages into the hole while it's being punched. Although + * shmem_undo_range() does remove the additions, it may be unable to + * keep up, as each new page needs its own unmap_mapping_range() call, + * and the i_mmap tree grows ever slower to scan if new vmas are added. + * + * It does not matter if we sometimes reach this check just before the + * hole-punch begins, so that one fault then races with the punch: + * we just need to make racing faults a rare case. + * + * The implementation below would be much simpler if we just used a + * standard mutex or completion: but we cannot take i_mutex in fault, + * and bloating every shmem inode for this unlikely case would be sad. + */ + if (unlikely(inode->i_private)) { + struct shmem_falloc *shmem_falloc; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + shmem_falloc->waitq && + vmf->pgoff >= shmem_falloc->start && + vmf->pgoff < shmem_falloc->next) { + wait_queue_head_t *shmem_falloc_waitq; + DEFINE_WAIT(shmem_fault_wait); + + ret = VM_FAULT_NOPAGE; + if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && + !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { + /* It's polite to up mmap_sem if we can */ + up_read(&vma->vm_mm->mmap_sem); + ret = VM_FAULT_RETRY; + } + + shmem_falloc_waitq = shmem_falloc->waitq; + prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->i_lock); + schedule(); + + /* + * shmem_falloc_waitq points into the shmem_fallocate() + * stack of the hole-punching task: shmem_falloc_waitq + * is usually invalid by the time we reach here, but + * finish_wait() does not dereference it in that case; + * though i_lock needed lest racing with wake_up_all(). + */ + spin_lock(&inode->i_lock); + finish_wait(shmem_falloc_waitq, &shmem_fault_wait); + spin_unlock(&inode->i_lock); + return ret; + } + spin_unlock(&inode->i_lock); + } + error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); @@ -1313,14 +1322,14 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) #ifdef CONFIG_NUMA static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol); } static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) { - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); pgoff_t index; index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; @@ -1330,7 +1339,7 @@ static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, int shmem_lock(struct file *file, int lock, struct user_struct *user) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; @@ -1418,6 +1427,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->backing_dev_info == &shmem_backing_dev_info; +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; @@ -1463,13 +1477,17 @@ shmem_write_end(struct file *file, struct address_space *mapping, return copied; } -static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor) +static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct inode *inode = filp->f_path.dentry->d_inode; + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; pgoff_t index; unsigned long offset; enum sgp_type sgp = SGP_READ; + int error = 0; + ssize_t retval = 0; + loff_t *ppos = &iocb->ki_pos; /* * Might this read be for a stacking filesystem? Then when reading @@ -1497,10 +1515,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ break; } - desc->error = shmem_getpage(inode, index, &page, sgp, NULL); - if (desc->error) { - if (desc->error == -EINVAL) - desc->error = 0; + error = shmem_getpage(inode, index, &page, sgp, NULL); + if (error) { + if (error == -EINVAL) + error = 0; break; } if (page) @@ -1544,61 +1562,26 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... - * - * The actor routine returns how many bytes were actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). */ - ret = actor(desc, page, offset, nr); + ret = copy_page_to_iter(page, offset, nr, to); + retval += ret; offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; page_cache_release(page); - if (ret != nr || !desc->count) + if (!iov_iter_count(to)) break; - + if (ret < nr) { + error = -EFAULT; + break; + } cond_resched(); } *ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset; - file_accessed(filp); -} - -static ssize_t shmem_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; - - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; - - for (seg = 0; seg < nr_segs; seg++) { - read_descriptor_t desc; - - desc.written = 0; - desc.arg.buf = iov[seg].iov_base; - desc.count = iov[seg].iov_len; - if (desc.count == 0) - continue; - desc.error = 0; - do_shmem_file_read(filp, ppos, &desc, file_read_actor); - retval += desc.written; - if (desc.error) { - retval = retval ?: desc.error; - break; - } - if (desc.count > 0) - break; - } - return retval; + file_accessed(file); + return retval ? retval : error; } static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, @@ -1637,7 +1620,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - nr_pages = min(req_pages, pipe->buffers); + nr_pages = min(req_pages, spd.nr_pages_max); spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages); @@ -1730,7 +1713,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pagevec_init(&pvec, 0); pvec.nr = 1; /* start small: we may be there already */ while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) @@ -1757,7 +1740,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, break; } } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); @@ -1797,10 +1780,8 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) } } - if (offset >= 0 && offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } + if (offset >= 0) + offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); mutex_unlock(&inode->i_mutex); return offset; } @@ -1808,24 +1789,40 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) static long shmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct shmem_falloc shmem_falloc; pgoff_t start, index, end; int error; + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + mutex_lock(&inode->i_mutex); if (mode & FALLOC_FL_PUNCH_HOLE) { struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); + + shmem_falloc.waitq = &shmem_falloc_waitq; + shmem_falloc.start = unmap_start >> PAGE_SHIFT; + shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); shmem_truncate_range(inode, offset, offset + len - 1); /* No need to unmap again: hole-punching leaves COWed pages */ + + spin_lock(&inode->i_lock); + inode->i_private = NULL; + wake_up_all(&shmem_falloc_waitq); + spin_unlock(&inode->i_lock); error = 0; goto out; } @@ -1843,6 +1840,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, goto out; } + shmem_falloc.waitq = NULL; shmem_falloc.start = start; shmem_falloc.next = start; shmem_falloc.nr_falloced = 0; @@ -1938,30 +1936,49 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { + error = simple_acl_create(dir, inode); + if (error) + goto out_iput; error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); - if (error) { - if (error != -EOPNOTSUPP) { - iput(inode); - return error; - } - } -#ifdef CONFIG_TMPFS_POSIX_ACL - error = generic_acl_init(inode, dir); - if (error) { - iput(inode); - return error; - } -#else + if (error && error != -EOPNOTSUPP) + goto out_iput; + error = 0; -#endif dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = CURRENT_TIME; d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ } return error; +out_iput: + iput(inode); + return error; +} + +static int +shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + int error = -ENOSPC; + + inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE); + if (inode) { + error = security_inode_init_security(inode, dir, + NULL, + shmem_initxattrs, NULL); + if (error && error != -EOPNOTSUPP) + goto out_iput; + error = simple_acl_create(dir, inode); + if (error) + goto out_iput; + d_tmpfile(dentry, inode); + } + return error; +out_iput: + iput(inode); + return error; } static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) @@ -2193,8 +2210,8 @@ static int shmem_initxattrs(struct inode *inode, static const struct xattr_handler *shmem_xattr_handlers[] = { #ifdef CONFIG_TMPFS_POSIX_ACL - &generic_acl_access_handler, - &generic_acl_default_handler, + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, #endif NULL }; @@ -2351,7 +2368,7 @@ static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len, { if (*len < 3) { *len = 3; - return 255; + return FILEID_INVALID; } if (inode_unhashed(inode)) { @@ -2386,6 +2403,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, bool remount) { char *this_char, *value, *rest; + struct mempolicy *mpol = NULL; uid_t uid; gid_t gid; @@ -2414,7 +2432,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, printk(KERN_ERR "tmpfs: No value for mount option '%s'\n", this_char); - return 1; + goto error; } if (!strcmp(this_char,"size")) { @@ -2463,19 +2481,24 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, if (!gid_valid(sbinfo->gid)) goto bad_val; } else if (!strcmp(this_char,"mpol")) { - if (mpol_parse_str(value, &sbinfo->mpol)) + mpol_put(mpol); + mpol = NULL; + if (mpol_parse_str(value, &mpol)) goto bad_val; } else { printk(KERN_ERR "tmpfs: Bad mount option %s\n", this_char); - return 1; + goto error; } } + sbinfo->mpol = mpol; return 0; bad_val: printk(KERN_ERR "tmpfs: Bad value '%s' for mount option '%s'\n", value, this_char); +error: + mpol_put(mpol); return 1; } @@ -2487,6 +2510,7 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) unsigned long inodes; int error = -EINVAL; + config.mpol = NULL; if (shmem_parse_options(data, &config, true)) return error; @@ -2511,8 +2535,13 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) sbinfo->max_inodes = config.max_inodes; sbinfo->free_inodes = config.max_inodes - inodes; - mpol_put(sbinfo->mpol); - sbinfo->mpol = config.mpol; /* transfers initial ref */ + /* + * Preserve previous mempolicy unless mpol remount option was specified. + */ + if (config.mpol) { + mpol_put(sbinfo->mpol); + sbinfo->mpol = config.mpol; /* transfers initial ref */ + } out: spin_unlock(&sbinfo->stat_lock); return error; @@ -2545,6 +2574,7 @@ static void shmem_put_super(struct super_block *sb) struct shmem_sb_info *sbinfo = SHMEM_SB(sb); percpu_counter_destroy(&sbinfo->used_blocks); + mpol_put(sbinfo->mpol); kfree(sbinfo); sb->s_fs_info = NULL; } @@ -2572,13 +2602,15 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) * tmpfs instance, limiting inodes to one per page of lowmem; * but the internal instance is left unlimited. */ - if (!(sb->s_flags & MS_NOUSER)) { + if (!(sb->s_flags & MS_KERNMOUNT)) { sbinfo->max_blocks = shmem_default_max_blocks(); sbinfo->max_inodes = shmem_default_max_inodes(); if (shmem_parse_options(data, sbinfo, false)) { err = -EINVAL; goto failed; } + } else { + sb->s_flags |= MS_NOUSER; } sb->s_export_op = &shmem_export_ops; sb->s_flags |= MS_NOSEC; @@ -2677,13 +2709,13 @@ static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = shmem_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = shmem_file_read_iter, + .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = shmem_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif }; @@ -2695,6 +2727,7 @@ static const struct inode_operations shmem_inode_operations = { .getxattr = shmem_getxattr, .listxattr = shmem_listxattr, .removexattr = shmem_removexattr, + .set_acl = simple_set_acl, #endif }; @@ -2709,6 +2742,7 @@ static const struct inode_operations shmem_dir_inode_operations = { .rmdir = shmem_rmdir, .mknod = shmem_mknod, .rename = shmem_rename, + .tmpfile = shmem_tmpfile, #endif #ifdef CONFIG_TMPFS_XATTR .setxattr = shmem_setxattr, @@ -2718,6 +2752,7 @@ static const struct inode_operations shmem_dir_inode_operations = { #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, + .set_acl = simple_set_acl, #endif }; @@ -2730,6 +2765,7 @@ static const struct inode_operations shmem_special_inode_operations = { #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, + .set_acl = simple_set_acl, #endif }; @@ -2748,6 +2784,7 @@ static const struct super_operations shmem_ops = { static const struct vm_operations_struct shmem_vm_ops = { .fault = shmem_fault, + .map_pages = filemap_map_pages, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, @@ -2766,12 +2803,17 @@ static struct file_system_type shmem_fs_type = { .name = "tmpfs", .mount = shmem_mount, .kill_sb = kill_litter_super, + .fs_flags = FS_USERNS_MOUNT, }; int __init shmem_init(void) { int error; + /* If rootfs called this, don't re-init */ + if (shmem_inode_cachep) + return 0; + error = bdi_init(&shmem_backing_dev_info); if (error) goto out4; @@ -2786,8 +2828,7 @@ int __init shmem_init(void) goto out2; } - shm_mnt = vfs_kern_mount(&shmem_fs_type, MS_NOUSER, - shmem_fs_type.name, NULL); + shm_mnt = kern_mount(&shmem_fs_type); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); printk(KERN_ERR "Could not kern_mount tmpfs\n"); @@ -2817,12 +2858,11 @@ out4: * effectively equivalent, but much lighter weight. */ -#include <linux/ramfs.h> - static struct file_system_type shmem_fs_type = { .name = "tmpfs", .mount = ramfs_mount, .kill_sb = kill_litter_super, + .fs_flags = FS_USERNS_MOUNT, }; int __init shmem_init(void) @@ -2865,23 +2905,21 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); /* common code */ -/** - * shmem_file_setup - get an unlinked file living in tmpfs - * @name: name for dentry (to be seen in /proc/<pid>/maps - * @size: size to be set for the file - * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size - */ -struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) +static struct dentry_operations anon_ops = { + .d_dname = simple_dname +}; + +static struct file *__shmem_file_setup(const char *name, loff_t size, + unsigned long flags, unsigned int i_flags) { - int error; - struct file *file; + struct file *res; struct inode *inode; struct path path; - struct dentry *root; + struct super_block *sb; struct qstr this; if (IS_ERR(shm_mnt)) - return (void *)shm_mnt; + return ERR_CAST(shm_mnt); if (size < 0 || size > MAX_LFS_FILESIZE) return ERR_PTR(-EINVAL); @@ -2889,43 +2927,68 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags if (shmem_acct_size(flags, size)) return ERR_PTR(-ENOMEM); - error = -ENOMEM; + res = ERR_PTR(-ENOMEM); this.name = name; this.len = strlen(name); this.hash = 0; /* will go */ - root = shm_mnt->mnt_root; - path.dentry = d_alloc(root, &this); + sb = shm_mnt->mnt_sb; + path.dentry = d_alloc_pseudo(sb, &this); if (!path.dentry) goto put_memory; + d_set_d_op(path.dentry, &anon_ops); path.mnt = mntget(shm_mnt); - error = -ENOSPC; - inode = shmem_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); + res = ERR_PTR(-ENOSPC); + inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); if (!inode) goto put_dentry; + inode->i_flags |= i_flags; d_instantiate(path.dentry, inode); inode->i_size = size; clear_nlink(inode); /* It is unlinked */ -#ifndef CONFIG_MMU - error = ramfs_nommu_expand_for_mapping(inode, size); - if (error) + res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size)); + if (IS_ERR(res)) goto put_dentry; -#endif - error = -ENFILE; - file = alloc_file(&path, FMODE_WRITE | FMODE_READ, + res = alloc_file(&path, FMODE_WRITE | FMODE_READ, &shmem_file_operations); - if (!file) + if (IS_ERR(res)) goto put_dentry; - return file; + return res; put_dentry: path_put(&path); put_memory: shmem_unacct_size(flags, size); - return ERR_PTR(error); + return res; +} + +/** + * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be + * kernel internal. There will be NO LSM permission checks against the + * underlying inode. So users of this interface must do LSM checks at a + * higher layer. The one user is the big_key implementation. LSM checks + * are provided at the key level rather than the inode level. + * @name: name for dentry (to be seen in /proc/<pid>/maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags) +{ + return __shmem_file_setup(name, size, flags, S_PRIVATE); +} + +/** + * shmem_file_setup - get an unlinked file living in tmpfs + * @name: name for dentry (to be seen in /proc/<pid>/maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) +{ + return __shmem_file_setup(name, size, flags, 0); } EXPORT_SYMBOL_GPL(shmem_file_setup); diff --git a/mm/slab.c b/mm/slab.c index e7667a3584b..3070b929a1b 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -157,77 +157,22 @@ #define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN #endif -/* - * true if a page was allocated from pfmemalloc reserves for network-based - * swap - */ -static bool pfmemalloc_active __read_mostly; +#define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \ + <= SLAB_OBJ_MIN_SIZE) ? 1 : 0) -/* - * kmem_bufctl_t: - * - * Bufctl's are used for linking objs within a slab - * linked offsets. - * - * This implementation relies on "struct page" for locating the cache & - * slab an object belongs to. - * This allows the bufctl structure to be small (one int), but limits - * the number of objects a slab (not a cache) can contain when off-slab - * bufctls are used. The limit is the size of the largest general cache - * that does not use off-slab slabs. - * For 32bit archs with 4 kB pages, is this 56. - * This is not serious, as it is only for large objects, when it is unwise - * to have too many per slab. - * Note: This limit can be raised by introducing a general cache whose size - * is less than 512 (PAGE_SIZE<<3), but greater than 256. - */ +#if FREELIST_BYTE_INDEX +typedef unsigned char freelist_idx_t; +#else +typedef unsigned short freelist_idx_t; +#endif -typedef unsigned int kmem_bufctl_t; -#define BUFCTL_END (((kmem_bufctl_t)(~0U))-0) -#define BUFCTL_FREE (((kmem_bufctl_t)(~0U))-1) -#define BUFCTL_ACTIVE (((kmem_bufctl_t)(~0U))-2) -#define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-3) +#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1) /* - * struct slab_rcu - * - * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to - * arrange for kmem_freepages to be called via RCU. This is useful if - * we need to approach a kernel structure obliquely, from its address - * obtained without the usual locking. We can lock the structure to - * stabilize it and check it's still at the given address, only if we - * can be sure that the memory has not been meanwhile reused for some - * other kind of object (which our subsystem's lock might corrupt). - * - * rcu_read_lock before reading the address, then rcu_read_unlock after - * taking the spinlock within the structure expected at that address. - */ -struct slab_rcu { - struct rcu_head head; - struct kmem_cache *cachep; - void *addr; -}; - -/* - * struct slab - * - * Manages the objs in a slab. Placed either at the beginning of mem allocated - * for a slab, or allocated from an general cache. - * Slabs are chained into three list: fully used, partial, fully free slabs. + * true if a page was allocated from pfmemalloc reserves for network-based + * swap */ -struct slab { - union { - struct { - struct list_head list; - unsigned long colouroff; - void *s_mem; /* including colour offset */ - unsigned int inuse; /* num of objs active in slab */ - kmem_bufctl_t free; - unsigned short nodeid; - }; - struct slab_rcu __slab_cover_slab_rcu; - }; -}; +static bool pfmemalloc_active __read_mostly; /* * struct array_cache @@ -286,68 +231,27 @@ struct arraycache_init { }; /* - * The slab lists for all objects. - */ -struct kmem_list3 { - struct list_head slabs_partial; /* partial list first, better asm code */ - struct list_head slabs_full; - struct list_head slabs_free; - unsigned long free_objects; - unsigned int free_limit; - unsigned int colour_next; /* Per-node cache coloring */ - spinlock_t list_lock; - struct array_cache *shared; /* shared per node */ - struct array_cache **alien; /* on other nodes */ - unsigned long next_reap; /* updated without locking */ - int free_touched; /* updated without locking */ -}; - -/* * Need this for bootstrapping a per node allocator. */ #define NUM_INIT_LISTS (3 * MAX_NUMNODES) -static struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS]; +static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS]; #define CACHE_CACHE 0 #define SIZE_AC MAX_NUMNODES -#define SIZE_L3 (2 * MAX_NUMNODES) +#define SIZE_NODE (2 * MAX_NUMNODES) static int drain_freelist(struct kmem_cache *cache, - struct kmem_list3 *l3, int tofree); + struct kmem_cache_node *n, int tofree); static void free_block(struct kmem_cache *cachep, void **objpp, int len, int node); static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp); static void cache_reap(struct work_struct *unused); -/* - * This function must be completely optimized away if a constant is passed to - * it. Mostly the same as what is in linux/slab.h except it returns an index. - */ -static __always_inline int index_of(const size_t size) -{ - extern void __bad_size(void); - - if (__builtin_constant_p(size)) { - int i = 0; - -#define CACHE(x) \ - if (size <=x) \ - return i; \ - else \ - i++; -#include <linux/kmalloc_sizes.h> -#undef CACHE - __bad_size(); - } else - __bad_size(); - return 0; -} - static int slab_early_init = 1; -#define INDEX_AC index_of(sizeof(struct arraycache_init)) -#define INDEX_L3 index_of(sizeof(struct kmem_list3)) +#define INDEX_AC kmalloc_index(sizeof(struct arraycache_init)) +#define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node)) -static void kmem_list3_init(struct kmem_list3 *parent) +static void kmem_cache_node_init(struct kmem_cache_node *parent) { INIT_LIST_HEAD(&parent->slabs_full); INIT_LIST_HEAD(&parent->slabs_partial); @@ -363,7 +267,7 @@ static void kmem_list3_init(struct kmem_list3 *parent) #define MAKE_LIST(cachep, listp, slab, nodeid) \ do { \ INIT_LIST_HEAD(listp); \ - list_splice(&(cachep->nodelists[nodeid]->slab), listp); \ + list_splice(&(cachep->node[nodeid]->slab), listp); \ } while (0) #define MAKE_ALL_LISTS(cachep, ptr, nodeid) \ @@ -384,8 +288,8 @@ static void kmem_list3_init(struct kmem_list3 *parent) * OTOH the cpuarrays can contain lots of objects, * which could lock up otherwise freeable slabs. */ -#define REAPTIMEOUT_CPUC (2*HZ) -#define REAPTIMEOUT_LIST3 (4*HZ) +#define REAPTIMEOUT_AC (2*HZ) +#define REAPTIMEOUT_NODE (4*HZ) #if STATS #define STATS_INC_ACTIVE(x) ((x)->num_active++) @@ -482,6 +386,39 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #endif +#define OBJECT_FREE (0) +#define OBJECT_ACTIVE (1) + +#ifdef CONFIG_DEBUG_SLAB_LEAK + +static void set_obj_status(struct page *page, int idx, int val) +{ + int freelist_size; + char *status; + struct kmem_cache *cachep = page->slab_cache; + + freelist_size = cachep->num * sizeof(freelist_idx_t); + status = (char *)page->freelist + freelist_size; + status[idx] = val; +} + +static inline unsigned int get_obj_status(struct page *page, int idx) +{ + int freelist_size; + char *status; + struct kmem_cache *cachep = page->slab_cache; + + freelist_size = cachep->num * sizeof(freelist_idx_t); + status = (char *)page->freelist + freelist_size; + + return status[idx]; +} + +#else +static inline void set_obj_status(struct page *page, int idx, int val) {} + +#endif + /* * Do not go above this order unless 0 objects fit into the slab or * overridden on the command line. @@ -497,18 +434,10 @@ static inline struct kmem_cache *virt_to_cache(const void *obj) return page->slab_cache; } -static inline struct slab *virt_to_slab(const void *obj) -{ - struct page *page = virt_to_head_page(obj); - - VM_BUG_ON(!PageSlab(page)); - return page->slab_page; -} - -static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab, +static inline void *index_to_obj(struct kmem_cache *cache, struct page *page, unsigned int idx) { - return slab->s_mem + cache->size * idx; + return page->s_mem + cache->size * idx; } /* @@ -518,36 +447,12 @@ static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab, * reciprocal_divide(offset, cache->reciprocal_buffer_size) */ static inline unsigned int obj_to_index(const struct kmem_cache *cache, - const struct slab *slab, void *obj) + const struct page *page, void *obj) { - u32 offset = (obj - slab->s_mem); + u32 offset = (obj - page->s_mem); return reciprocal_divide(offset, cache->reciprocal_buffer_size); } -/* - * These are the default caches for kmalloc. Custom caches can have other sizes. - */ -struct cache_sizes malloc_sizes[] = { -#define CACHE(x) { .cs_size = (x) }, -#include <linux/kmalloc_sizes.h> - CACHE(ULONG_MAX) -#undef CACHE -}; -EXPORT_SYMBOL(malloc_sizes); - -/* Must match cache_sizes above. Out of line to keep cache footprint low. */ -struct cache_names { - char *name; - char *name_dma; -}; - -static struct cache_names __initdata cache_names[] = { -#define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" }, -#include <linux/kmalloc_sizes.h> - {NULL,} -#undef CACHE -}; - static struct arraycache_init initarray_generic = { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; @@ -586,15 +491,15 @@ static void slab_set_lock_classes(struct kmem_cache *cachep, int q) { struct array_cache **alc; - struct kmem_list3 *l3; + struct kmem_cache_node *n; int r; - l3 = cachep->nodelists[q]; - if (!l3) + n = cachep->node[q]; + if (!n) return; - lockdep_set_class(&l3->list_lock, l3_key); - alc = l3->alien; + lockdep_set_class(&n->list_lock, l3_key); + alc = n->alien; /* * FIXME: This check for BAD_ALIEN_MAGIC * should go away when common slab code is taught to @@ -625,28 +530,30 @@ static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep) static void init_node_lock_keys(int q) { - struct cache_sizes *s = malloc_sizes; + int i; if (slab_state < UP) return; - for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) { - struct kmem_list3 *l3; + for (i = 1; i <= KMALLOC_SHIFT_HIGH; i++) { + struct kmem_cache_node *n; + struct kmem_cache *cache = kmalloc_caches[i]; + + if (!cache) + continue; - l3 = s->cs_cachep->nodelists[q]; - if (!l3 || OFF_SLAB(s->cs_cachep)) + n = cache->node[q]; + if (!n || OFF_SLAB(cache)) continue; - slab_set_lock_classes(s->cs_cachep, &on_slab_l3_key, + slab_set_lock_classes(cache, &on_slab_l3_key, &on_slab_alc_key, q); } } static void on_slab_lock_classes_node(struct kmem_cache *cachep, int q) { - struct kmem_list3 *l3; - l3 = cachep->nodelists[q]; - if (!l3) + if (!cachep->node[q]) return; slab_set_lock_classes(cachep, &on_slab_l3_key, @@ -702,44 +609,50 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) return cachep->array[smp_processor_id()]; } -static inline struct kmem_cache *__find_general_cachep(size_t size, - gfp_t gfpflags) +static size_t calculate_freelist_size(int nr_objs, size_t align) { - struct cache_sizes *csizep = malloc_sizes; + size_t freelist_size; -#if DEBUG - /* This happens if someone tries to call - * kmem_cache_create(), or __kmalloc(), before - * the generic caches are initialized. - */ - BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL); -#endif - if (!size) - return ZERO_SIZE_PTR; + freelist_size = nr_objs * sizeof(freelist_idx_t); + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + freelist_size += nr_objs * sizeof(char); - while (size > csizep->cs_size) - csizep++; + if (align) + freelist_size = ALIGN(freelist_size, align); - /* - * Really subtle: The last entry with cs->cs_size==ULONG_MAX - * has cs_{dma,}cachep==NULL. Thus no special case - * for large kmalloc calls required. - */ -#ifdef CONFIG_ZONE_DMA - if (unlikely(gfpflags & GFP_DMA)) - return csizep->cs_dmacachep; -#endif - return csizep->cs_cachep; + return freelist_size; } -static struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags) +static int calculate_nr_objs(size_t slab_size, size_t buffer_size, + size_t idx_size, size_t align) { - return __find_general_cachep(size, gfpflags); -} + int nr_objs; + size_t remained_size; + size_t freelist_size; + int extra_space = 0; -static size_t slab_mgmt_size(size_t nr_objs, size_t align) -{ - return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align); + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + extra_space = sizeof(char); + /* + * Ignore padding for the initial guess. The padding + * is at most @align-1 bytes, and @buffer_size is at + * least @align. In the worst case, this result will + * be one greater than the number of objects that fit + * into the memory allocation when taking the padding + * into account. + */ + nr_objs = slab_size / (buffer_size + idx_size + extra_space); + + /* + * This calculated number will be either the right + * amount, or one greater than what we want. + */ + remained_size = slab_size - nr_objs * buffer_size; + freelist_size = calculate_freelist_size(nr_objs, align); + if (remained_size < freelist_size) + nr_objs--; + + return nr_objs; } /* @@ -758,8 +671,7 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size, * on it. For the latter case, the memory allocated for a * slab is used for: * - * - The struct slab - * - One kmem_bufctl_t for each object + * - One unsigned int for each object * - Padding to respect alignment of @align * - @buffer_size bytes for each object * @@ -772,32 +684,10 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size, mgmt_size = 0; nr_objs = slab_size / buffer_size; - if (nr_objs > SLAB_LIMIT) - nr_objs = SLAB_LIMIT; } else { - /* - * Ignore padding for the initial guess. The padding - * is at most @align-1 bytes, and @buffer_size is at - * least @align. In the worst case, this result will - * be one greater than the number of objects that fit - * into the memory allocation when taking the padding - * into account. - */ - nr_objs = (slab_size - sizeof(struct slab)) / - (buffer_size + sizeof(kmem_bufctl_t)); - - /* - * This calculated number will be either the right - * amount, or one greater than what we want. - */ - if (slab_mgmt_size(nr_objs, align) + nr_objs*buffer_size - > slab_size) - nr_objs--; - - if (nr_objs > SLAB_LIMIT) - nr_objs = SLAB_LIMIT; - - mgmt_size = slab_mgmt_size(nr_objs, align); + nr_objs = calculate_nr_objs(slab_size, buffer_size, + sizeof(freelist_idx_t), align); + mgmt_size = calculate_freelist_size(nr_objs, align); } *num = nr_objs; *left_over = slab_size - nr_objs*buffer_size - mgmt_size; @@ -812,7 +702,7 @@ static void __slab_error(const char *function, struct kmem_cache *cachep, printk(KERN_ERR "slab error in %s(): cache `%s': %s\n", function, cachep->name, msg); dump_stack(); - add_taint(TAINT_BAD_PAGE); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } #endif @@ -885,7 +775,7 @@ static void next_reap_node(void) * the CPUs getting into lockstep and contending for the global cache chain * lock. */ -static void __cpuinit start_cpu_timer(int cpu) +static void start_cpu_timer(int cpu) { struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu); @@ -927,10 +817,8 @@ static struct array_cache *alloc_arraycache(int node, int entries, return nc; } -static inline bool is_slab_pfmemalloc(struct slab *slabp) +static inline bool is_slab_pfmemalloc(struct page *page) { - struct page *page = virt_to_page(slabp->s_mem); - return PageSlabPfmemalloc(page); } @@ -938,29 +826,29 @@ static inline bool is_slab_pfmemalloc(struct slab *slabp) static void recheck_pfmemalloc_active(struct kmem_cache *cachep, struct array_cache *ac) { - struct kmem_list3 *l3 = cachep->nodelists[numa_mem_id()]; - struct slab *slabp; + struct kmem_cache_node *n = cachep->node[numa_mem_id()]; + struct page *page; unsigned long flags; if (!pfmemalloc_active) return; - spin_lock_irqsave(&l3->list_lock, flags); - list_for_each_entry(slabp, &l3->slabs_full, list) - if (is_slab_pfmemalloc(slabp)) + spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->slabs_full, lru) + if (is_slab_pfmemalloc(page)) goto out; - list_for_each_entry(slabp, &l3->slabs_partial, list) - if (is_slab_pfmemalloc(slabp)) + list_for_each_entry(page, &n->slabs_partial, lru) + if (is_slab_pfmemalloc(page)) goto out; - list_for_each_entry(slabp, &l3->slabs_free, list) - if (is_slab_pfmemalloc(slabp)) + list_for_each_entry(page, &n->slabs_free, lru) + if (is_slab_pfmemalloc(page)) goto out; pfmemalloc_active = false; out: - spin_unlock_irqrestore(&l3->list_lock, flags); + spin_unlock_irqrestore(&n->list_lock, flags); } static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, @@ -971,7 +859,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, /* Ensure the caller is allowed to use objects from PFMEMALLOC slab */ if (unlikely(is_obj_pfmemalloc(objp))) { - struct kmem_list3 *l3; + struct kmem_cache_node *n; if (gfp_pfmemalloc_allowed(flags)) { clear_obj_pfmemalloc(&objp); @@ -993,10 +881,10 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, * If there are empty slabs on the slabs_free list and we are * being forced to refill the cache, mark this one !pfmemalloc. */ - l3 = cachep->nodelists[numa_mem_id()]; - if (!list_empty(&l3->slabs_free) && force_refill) { - struct slab *slabp = virt_to_slab(objp); - ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem)); + n = cachep->node[numa_mem_id()]; + if (!list_empty(&n->slabs_free) && force_refill) { + struct page *page = virt_to_head_page(objp); + ClearPageSlabPfmemalloc(page); clear_obj_pfmemalloc(&objp); recheck_pfmemalloc_active(cachep, ac); return objp; @@ -1071,7 +959,7 @@ static int transfer_objects(struct array_cache *to, #ifndef CONFIG_NUMA #define drain_alien_cache(cachep, alien) do { } while (0) -#define reap_alien(cachep, l3) do { } while (0) +#define reap_alien(cachep, n) do { } while (0) static inline struct array_cache **alloc_alien_cache(int node, int limit, gfp_t gfp) { @@ -1143,33 +1031,33 @@ static void free_alien_cache(struct array_cache **ac_ptr) static void __drain_alien_cache(struct kmem_cache *cachep, struct array_cache *ac, int node) { - struct kmem_list3 *rl3 = cachep->nodelists[node]; + struct kmem_cache_node *n = cachep->node[node]; if (ac->avail) { - spin_lock(&rl3->list_lock); + spin_lock(&n->list_lock); /* * Stuff objects into the remote nodes shared array first. * That way we could avoid the overhead of putting the objects * into the free lists and getting them back later. */ - if (rl3->shared) - transfer_objects(rl3->shared, ac, ac->limit); + if (n->shared) + transfer_objects(n->shared, ac, ac->limit); free_block(cachep, ac->entry, ac->avail, node); ac->avail = 0; - spin_unlock(&rl3->list_lock); + spin_unlock(&n->list_lock); } } /* * Called from cache_reap() to regularly drain alien caches round robin. */ -static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3) +static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n) { int node = __this_cpu_read(slab_reap_node); - if (l3->alien) { - struct array_cache *ac = l3->alien[node]; + if (n->alien) { + struct array_cache *ac = n->alien[node]; if (ac && ac->avail && spin_trylock_irq(&ac->lock)) { __drain_alien_cache(cachep, ac, node); @@ -1197,9 +1085,8 @@ static void drain_alien_cache(struct kmem_cache *cachep, static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) { - struct slab *slabp = virt_to_slab(objp); - int nodeid = slabp->nodeid; - struct kmem_list3 *l3; + int nodeid = page_to_nid(virt_to_page(objp)); + struct kmem_cache_node *n; struct array_cache *alien = NULL; int node; @@ -1209,13 +1096,13 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) * Make sure we are not freeing a object from another node to the array * cache on this cpu. */ - if (likely(slabp->nodeid == node)) + if (likely(nodeid == node)) return 0; - l3 = cachep->nodelists[node]; + n = cachep->node[node]; STATS_INC_NODEFREES(cachep); - if (l3->alien && l3->alien[nodeid]) { - alien = l3->alien[nodeid]; + if (n->alien && n->alien[nodeid]) { + alien = n->alien[nodeid]; spin_lock(&alien->lock); if (unlikely(alien->avail == alien->limit)) { STATS_INC_ACOVERFLOW(cachep); @@ -1224,64 +1111,70 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) ac_put_obj(cachep, alien, objp); spin_unlock(&alien->lock); } else { - spin_lock(&(cachep->nodelists[nodeid])->list_lock); + spin_lock(&(cachep->node[nodeid])->list_lock); free_block(cachep, &objp, 1, nodeid); - spin_unlock(&(cachep->nodelists[nodeid])->list_lock); + spin_unlock(&(cachep->node[nodeid])->list_lock); } return 1; } #endif /* - * Allocates and initializes nodelists for a node on each slab cache, used for - * either memory or cpu hotplug. If memory is being hot-added, the kmem_list3 + * Allocates and initializes node for a node on each slab cache, used for + * either memory or cpu hotplug. If memory is being hot-added, the kmem_cache_node * will be allocated off-node since memory is not yet online for the new node. - * When hotplugging memory or a cpu, existing nodelists are not replaced if + * When hotplugging memory or a cpu, existing node are not replaced if * already in use. * * Must hold slab_mutex. */ -static int init_cache_nodelists_node(int node) +static int init_cache_node_node(int node) { struct kmem_cache *cachep; - struct kmem_list3 *l3; - const int memsize = sizeof(struct kmem_list3); + struct kmem_cache_node *n; + const int memsize = sizeof(struct kmem_cache_node); list_for_each_entry(cachep, &slab_caches, list) { /* - * Set up the size64 kmemlist for cpu before we can + * Set up the kmem_cache_node for cpu before we can * begin anything. Make sure some other cpu on this * node has not already allocated this */ - if (!cachep->nodelists[node]) { - l3 = kmalloc_node(memsize, GFP_KERNEL, node); - if (!l3) + if (!cachep->node[node]) { + n = kmalloc_node(memsize, GFP_KERNEL, node); + if (!n) return -ENOMEM; - kmem_list3_init(l3); - l3->next_reap = jiffies + REAPTIMEOUT_LIST3 + - ((unsigned long)cachep) % REAPTIMEOUT_LIST3; + kmem_cache_node_init(n); + n->next_reap = jiffies + REAPTIMEOUT_NODE + + ((unsigned long)cachep) % REAPTIMEOUT_NODE; /* - * The l3s don't come and go as CPUs come and - * go. slab_mutex is sufficient + * The kmem_cache_nodes don't come and go as CPUs + * come and go. slab_mutex is sufficient * protection here. */ - cachep->nodelists[node] = l3; + cachep->node[node] = n; } - spin_lock_irq(&cachep->nodelists[node]->list_lock); - cachep->nodelists[node]->free_limit = + spin_lock_irq(&cachep->node[node]->list_lock); + cachep->node[node]->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - spin_unlock_irq(&cachep->nodelists[node]->list_lock); + spin_unlock_irq(&cachep->node[node]->list_lock); } return 0; } -static void __cpuinit cpuup_canceled(long cpu) +static inline int slabs_tofree(struct kmem_cache *cachep, + struct kmem_cache_node *n) +{ + return (n->free_objects + cachep->num - 1) / cachep->num; +} + +static void cpuup_canceled(long cpu) { struct kmem_cache *cachep; - struct kmem_list3 *l3 = NULL; + struct kmem_cache_node *n = NULL; int node = cpu_to_mem(cpu); const struct cpumask *mask = cpumask_of_node(node); @@ -1293,34 +1186,34 @@ static void __cpuinit cpuup_canceled(long cpu) /* cpu is dead; no one can alloc from it. */ nc = cachep->array[cpu]; cachep->array[cpu] = NULL; - l3 = cachep->nodelists[node]; + n = cachep->node[node]; - if (!l3) + if (!n) goto free_array_cache; - spin_lock_irq(&l3->list_lock); + spin_lock_irq(&n->list_lock); - /* Free limit for this kmem_list3 */ - l3->free_limit -= cachep->batchcount; + /* Free limit for this kmem_cache_node */ + n->free_limit -= cachep->batchcount; if (nc) free_block(cachep, nc->entry, nc->avail, node); if (!cpumask_empty(mask)) { - spin_unlock_irq(&l3->list_lock); + spin_unlock_irq(&n->list_lock); goto free_array_cache; } - shared = l3->shared; + shared = n->shared; if (shared) { free_block(cachep, shared->entry, shared->avail, node); - l3->shared = NULL; + n->shared = NULL; } - alien = l3->alien; - l3->alien = NULL; + alien = n->alien; + n->alien = NULL; - spin_unlock_irq(&l3->list_lock); + spin_unlock_irq(&n->list_lock); kfree(shared); if (alien) { @@ -1336,17 +1229,17 @@ free_array_cache: * shrink each nodelist to its limit. */ list_for_each_entry(cachep, &slab_caches, list) { - l3 = cachep->nodelists[node]; - if (!l3) + n = cachep->node[node]; + if (!n) continue; - drain_freelist(cachep, l3, l3->free_objects); + drain_freelist(cachep, n, slabs_tofree(cachep, n)); } } -static int __cpuinit cpuup_prepare(long cpu) +static int cpuup_prepare(long cpu) { struct kmem_cache *cachep; - struct kmem_list3 *l3 = NULL; + struct kmem_cache_node *n = NULL; int node = cpu_to_mem(cpu); int err; @@ -1354,9 +1247,9 @@ static int __cpuinit cpuup_prepare(long cpu) * We need to do this right in the beginning since * alloc_arraycache's are going to use this list. * kmalloc_node allows us to add the slab to the right - * kmem_list3 and not this cpu's kmem_list3 + * kmem_cache_node and not this cpu's kmem_cache_node */ - err = init_cache_nodelists_node(node); + err = init_cache_node_node(node); if (err < 0) goto bad; @@ -1391,25 +1284,25 @@ static int __cpuinit cpuup_prepare(long cpu) } } cachep->array[cpu] = nc; - l3 = cachep->nodelists[node]; - BUG_ON(!l3); + n = cachep->node[node]; + BUG_ON(!n); - spin_lock_irq(&l3->list_lock); - if (!l3->shared) { + spin_lock_irq(&n->list_lock); + if (!n->shared) { /* * We are serialised from CPU_DEAD or * CPU_UP_CANCELLED by the cpucontrol lock */ - l3->shared = shared; + n->shared = shared; shared = NULL; } #ifdef CONFIG_NUMA - if (!l3->alien) { - l3->alien = alien; + if (!n->alien) { + n->alien = alien; alien = NULL; } #endif - spin_unlock_irq(&l3->list_lock); + spin_unlock_irq(&n->list_lock); kfree(shared); free_alien_cache(alien); if (cachep->flags & SLAB_DEBUG_OBJECTS) @@ -1426,7 +1319,7 @@ bad: return -ENOMEM; } -static int __cpuinit cpuup_callback(struct notifier_block *nfb, +static int cpuup_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { long cpu = (long)hcpu; @@ -1464,9 +1357,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, case CPU_DEAD_FROZEN: /* * Even if all the cpus of a node are down, we don't free the - * kmem_list3 of any cache. This to avoid a race between + * kmem_cache_node of any cache. This to avoid a race between * cpu_down, and a kmalloc allocation from another cpu for - * memory from the node of the cpu going down. The list3 + * memory from the node of the cpu going down. The node * structure is usually allocated from kmem_cache_create() and * gets destroyed at kmem_cache_destroy(). */ @@ -1482,7 +1375,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, return notifier_from_errno(err); } -static struct notifier_block __cpuinitdata cpucache_notifier = { +static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 }; @@ -1494,22 +1387,22 @@ static struct notifier_block __cpuinitdata cpucache_notifier = { * * Must hold slab_mutex. */ -static int __meminit drain_cache_nodelists_node(int node) +static int __meminit drain_cache_node_node(int node) { struct kmem_cache *cachep; int ret = 0; list_for_each_entry(cachep, &slab_caches, list) { - struct kmem_list3 *l3; + struct kmem_cache_node *n; - l3 = cachep->nodelists[node]; - if (!l3) + n = cachep->node[node]; + if (!n) continue; - drain_freelist(cachep, l3, l3->free_objects); + drain_freelist(cachep, n, slabs_tofree(cachep, n)); - if (!list_empty(&l3->slabs_full) || - !list_empty(&l3->slabs_partial)) { + if (!list_empty(&n->slabs_full) || + !list_empty(&n->slabs_partial)) { ret = -EBUSY; break; } @@ -1531,12 +1424,12 @@ static int __meminit slab_memory_callback(struct notifier_block *self, switch (action) { case MEM_GOING_ONLINE: mutex_lock(&slab_mutex); - ret = init_cache_nodelists_node(nid); + ret = init_cache_node_node(nid); mutex_unlock(&slab_mutex); break; case MEM_GOING_OFFLINE: mutex_lock(&slab_mutex); - ret = drain_cache_nodelists_node(nid); + ret = drain_cache_node_node(nid); mutex_unlock(&slab_mutex); break; case MEM_ONLINE: @@ -1551,49 +1444,49 @@ out: #endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */ /* - * swap the static kmem_list3 with kmalloced memory + * swap the static kmem_cache_node with kmalloced memory */ -static void __init init_list(struct kmem_cache *cachep, struct kmem_list3 *list, +static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *list, int nodeid) { - struct kmem_list3 *ptr; + struct kmem_cache_node *ptr; - ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_NOWAIT, nodeid); + ptr = kmalloc_node(sizeof(struct kmem_cache_node), GFP_NOWAIT, nodeid); BUG_ON(!ptr); - memcpy(ptr, list, sizeof(struct kmem_list3)); + memcpy(ptr, list, sizeof(struct kmem_cache_node)); /* * Do not assume that spinlocks can be initialized via memcpy: */ spin_lock_init(&ptr->list_lock); MAKE_ALL_LISTS(cachep, ptr, nodeid); - cachep->nodelists[nodeid] = ptr; + cachep->node[nodeid] = ptr; } /* - * For setting up all the kmem_list3s for cache whose buffer_size is same as - * size of kmem_list3. + * For setting up all the kmem_cache_node for cache whose buffer_size is same as + * size of kmem_cache_node. */ -static void __init set_up_list3s(struct kmem_cache *cachep, int index) +static void __init set_up_node(struct kmem_cache *cachep, int index) { int node; for_each_online_node(node) { - cachep->nodelists[node] = &initkmem_list3[index + node]; - cachep->nodelists[node]->next_reap = jiffies + - REAPTIMEOUT_LIST3 + - ((unsigned long)cachep) % REAPTIMEOUT_LIST3; + cachep->node[node] = &init_kmem_cache_node[index + node]; + cachep->node[node]->next_reap = jiffies + + REAPTIMEOUT_NODE + + ((unsigned long)cachep) % REAPTIMEOUT_NODE; } } /* * The memory after the last cpu cache pointer is used for the - * the nodelists pointer. + * the node pointer. */ -static void setup_nodelists_pointer(struct kmem_cache *cachep) +static void setup_node_pointer(struct kmem_cache *cachep) { - cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids]; + cachep->node = (struct kmem_cache_node **)&cachep->array[nr_cpu_ids]; } /* @@ -1602,20 +1495,20 @@ static void setup_nodelists_pointer(struct kmem_cache *cachep) */ void __init kmem_cache_init(void) { - struct cache_sizes *sizes; - struct cache_names *names; int i; + BUILD_BUG_ON(sizeof(((struct page *)NULL)->lru) < + sizeof(struct rcu_head)); kmem_cache = &kmem_cache_boot; - setup_nodelists_pointer(kmem_cache); + setup_node_pointer(kmem_cache); if (num_possible_nodes() == 1) use_alien_caches = 0; for (i = 0; i < NUM_INIT_LISTS; i++) - kmem_list3_init(&initkmem_list3[i]); + kmem_cache_node_init(&init_kmem_cache_node[i]); - set_up_list3s(kmem_cache, CACHE_CACHE); + set_up_node(kmem_cache, CACHE_CACHE); /* * Fragmentation resistance on low memory - only use bigger @@ -1631,7 +1524,7 @@ void __init kmem_cache_init(void) * kmem_cache structures of all caches, except kmem_cache itself: * kmem_cache is statically allocated. * Initially an __init data area is used for the head array and the - * kmem_list3 structures, it's replaced with a kmalloc allocated + * kmem_cache_node structures, it's replaced with a kmalloc allocated * array at the end of the bootstrap. * 2) Create the first kmalloc cache. * The struct kmem_cache for the new cache is allocated normally. @@ -1640,7 +1533,7 @@ void __init kmem_cache_init(void) * head arrays. * 4) Replace the __init data head arrays for kmem_cache and the first * kmalloc cache with kmalloc allocated arrays. - * 5) Replace the __init data for kmem_list3 for kmem_cache and + * 5) Replace the __init data for kmem_cache_node for kmem_cache and * the other cache's with kmalloc allocated memory. * 6) Resize the head arrays of the kmalloc caches to their final sizes. */ @@ -1652,50 +1545,28 @@ void __init kmem_cache_init(void) */ create_boot_cache(kmem_cache, "kmem_cache", offsetof(struct kmem_cache, array[nr_cpu_ids]) + - nr_node_ids * sizeof(struct kmem_list3 *), + nr_node_ids * sizeof(struct kmem_cache_node *), SLAB_HWCACHE_ALIGN); list_add(&kmem_cache->list, &slab_caches); /* 2+3) create the kmalloc caches */ - sizes = malloc_sizes; - names = cache_names; /* * Initialize the caches that provide memory for the array cache and the - * kmem_list3 structures first. Without this, further allocations will + * kmem_cache_node structures first. Without this, further allocations will * bug. */ - sizes[INDEX_AC].cs_cachep = create_kmalloc_cache(names[INDEX_AC].name, - sizes[INDEX_AC].cs_size, ARCH_KMALLOC_FLAGS); + kmalloc_caches[INDEX_AC] = create_kmalloc_cache("kmalloc-ac", + kmalloc_size(INDEX_AC), ARCH_KMALLOC_FLAGS); - if (INDEX_AC != INDEX_L3) - sizes[INDEX_L3].cs_cachep = - create_kmalloc_cache(names[INDEX_L3].name, - sizes[INDEX_L3].cs_size, ARCH_KMALLOC_FLAGS); + if (INDEX_AC != INDEX_NODE) + kmalloc_caches[INDEX_NODE] = + create_kmalloc_cache("kmalloc-node", + kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS); slab_early_init = 0; - while (sizes->cs_size != ULONG_MAX) { - /* - * For performance, all the general caches are L1 aligned. - * This should be particularly beneficial on SMP boxes, as it - * eliminates "false sharing". - * Note for systems short on memory removing the alignment will - * allow tighter packing of the smaller caches. - */ - if (!sizes->cs_cachep) - sizes->cs_cachep = create_kmalloc_cache(names->name, - sizes->cs_size, ARCH_KMALLOC_FLAGS); - -#ifdef CONFIG_ZONE_DMA - sizes->cs_dmacachep = create_kmalloc_cache( - names->name_dma, sizes->cs_size, - SLAB_CACHE_DMA|ARCH_KMALLOC_FLAGS); -#endif - sizes++; - names++; - } /* 4) Replace the bootstrap head arrays */ { struct array_cache *ptr; @@ -1713,36 +1584,35 @@ void __init kmem_cache_init(void) ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT); - BUG_ON(cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep) + BUG_ON(cpu_cache_get(kmalloc_caches[INDEX_AC]) != &initarray_generic.cache); - memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep), + memcpy(ptr, cpu_cache_get(kmalloc_caches[INDEX_AC]), sizeof(struct arraycache_init)); /* * Do not assume that spinlocks can be initialized via memcpy: */ spin_lock_init(&ptr->lock); - malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] = - ptr; + kmalloc_caches[INDEX_AC]->array[smp_processor_id()] = ptr; } - /* 5) Replace the bootstrap kmem_list3's */ + /* 5) Replace the bootstrap kmem_cache_node */ { int nid; for_each_online_node(nid) { - init_list(kmem_cache, &initkmem_list3[CACHE_CACHE + nid], nid); + init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid); - init_list(malloc_sizes[INDEX_AC].cs_cachep, - &initkmem_list3[SIZE_AC + nid], nid); + init_list(kmalloc_caches[INDEX_AC], + &init_kmem_cache_node[SIZE_AC + nid], nid); - if (INDEX_AC != INDEX_L3) { - init_list(malloc_sizes[INDEX_L3].cs_cachep, - &initkmem_list3[SIZE_L3 + nid], nid); + if (INDEX_AC != INDEX_NODE) { + init_list(kmalloc_caches[INDEX_NODE], + &init_kmem_cache_node[SIZE_NODE + nid], nid); } } } - slab_state = UP; + create_kmalloc_caches(ARCH_KMALLOC_FLAGS); } void __init kmem_cache_init_late(void) @@ -1773,7 +1643,7 @@ void __init kmem_cache_init_late(void) #ifdef CONFIG_NUMA /* * Register a memory hotplug callback that initializes and frees - * nodelists. + * node. */ hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI); #endif @@ -1803,10 +1673,16 @@ __initcall(cpucache_init); static noinline void slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) { - struct kmem_list3 *l3; - struct slab *slabp; +#if DEBUG + struct kmem_cache_node *n; + struct page *page; unsigned long flags; int node; + static DEFINE_RATELIMIT_STATE(slab_oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slab_oom_rs)) + return; printk(KERN_WARNING "SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n", @@ -1818,24 +1694,24 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) unsigned long active_objs = 0, num_objs = 0, free_objects = 0; unsigned long active_slabs = 0, num_slabs = 0; - l3 = cachep->nodelists[node]; - if (!l3) + n = cachep->node[node]; + if (!n) continue; - spin_lock_irqsave(&l3->list_lock, flags); - list_for_each_entry(slabp, &l3->slabs_full, list) { + spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->slabs_full, lru) { active_objs += cachep->num; active_slabs++; } - list_for_each_entry(slabp, &l3->slabs_partial, list) { - active_objs += slabp->inuse; + list_for_each_entry(page, &n->slabs_partial, lru) { + active_objs += page->active; active_slabs++; } - list_for_each_entry(slabp, &l3->slabs_free, list) + list_for_each_entry(page, &n->slabs_free, lru) num_slabs++; - free_objects += l3->free_objects; - spin_unlock_irqrestore(&l3->list_lock, flags); + free_objects += n->free_objects; + spin_unlock_irqrestore(&n->list_lock, flags); num_slabs += active_slabs; num_objs = num_slabs * cachep->num; @@ -1844,6 +1720,7 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) node, active_slabs, num_slabs, active_objs, num_objs, free_objects); } +#endif } /* @@ -1853,28 +1730,23 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) * did not request dmaable memory, we might get it, but that * would be relatively rare and ignorable. */ -static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) +static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, + int nodeid) { struct page *page; int nr_pages; - int i; - -#ifndef CONFIG_MMU - /* - * Nommu uses slab's for process anonymous memory allocations, and thus - * requires __GFP_COMP to properly refcount higher order allocations - */ - flags |= __GFP_COMP; -#endif flags |= cachep->allocflags; if (cachep->flags & SLAB_RECLAIM_ACCOUNT) flags |= __GFP_RECLAIMABLE; + if (memcg_charge_slab(cachep, flags, cachep->gfporder)) + return NULL; + page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder); if (!page) { - if (!(flags & __GFP_NOWARN) && printk_ratelimit()) - slab_out_of_memory(cachep, flags, nodeid); + memcg_uncharge_slab(cachep, cachep->gfporder); + slab_out_of_memory(cachep, flags, nodeid); return NULL; } @@ -1889,13 +1761,9 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) else add_zone_page_state(page_zone(page), NR_SLAB_UNRECLAIMABLE, nr_pages); - for (i = 0; i < nr_pages; i++) { - __SetPageSlab(page + i); - - if (page->pfmemalloc) - SetPageSlabPfmemalloc(page + i); - } - memcg_bind_pages(cachep, cachep->gfporder); + __SetPageSlab(page); + if (page->pfmemalloc) + SetPageSlabPfmemalloc(page); if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) { kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid); @@ -1906,17 +1774,15 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) kmemcheck_mark_unallocated_pages(page, nr_pages); } - return page_address(page); + return page; } /* * Interface to system's page release. */ -static void kmem_freepages(struct kmem_cache *cachep, void *addr) +static void kmem_freepages(struct kmem_cache *cachep, struct page *page) { - unsigned long i = (1 << cachep->gfporder); - struct page *page = virt_to_page(addr); - const unsigned long nr_freed = i; + const unsigned long nr_freed = (1 << cachep->gfporder); kmemcheck_free_shadow(page, cachep->gfporder); @@ -1926,27 +1792,28 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) else sub_zone_page_state(page_zone(page), NR_SLAB_UNRECLAIMABLE, nr_freed); - while (i--) { - BUG_ON(!PageSlab(page)); - __ClearPageSlabPfmemalloc(page); - __ClearPageSlab(page); - page++; - } - memcg_release_pages(cachep, cachep->gfporder); + BUG_ON(!PageSlab(page)); + __ClearPageSlabPfmemalloc(page); + __ClearPageSlab(page); + page_mapcount_reset(page); + page->mapping = NULL; + if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; - free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder); + __free_pages(page, cachep->gfporder); + memcg_uncharge_slab(cachep, cachep->gfporder); } static void kmem_rcu_free(struct rcu_head *head) { - struct slab_rcu *slab_rcu = (struct slab_rcu *)head; - struct kmem_cache *cachep = slab_rcu->cachep; + struct kmem_cache *cachep; + struct page *page; - kmem_freepages(cachep, slab_rcu->addr); - if (OFF_SLAB(cachep)) - kmem_cache_free(cachep->slabp_cache, slab_rcu); + page = container_of(head, struct page, rcu_head); + cachep = page->slab_cache; + + kmem_freepages(cachep, page); } #if DEBUG @@ -2040,11 +1907,9 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines) } if (cachep->flags & SLAB_STORE_USER) { - printk(KERN_ERR "Last user: [<%p>]", - *dbg_userword(cachep, objp)); - print_symbol("(%s)", - (unsigned long)*dbg_userword(cachep, objp)); - printk("\n"); + printk(KERN_ERR "Last user: [<%p>](%pSR)\n", + *dbg_userword(cachep, objp), + *dbg_userword(cachep, objp)); } realobj = (char *)objp + obj_offset(cachep); size = cachep->object_size; @@ -2097,19 +1962,19 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) /* Print some data about the neighboring objects, if they * exist: */ - struct slab *slabp = virt_to_slab(objp); + struct page *page = virt_to_head_page(objp); unsigned int objnr; - objnr = obj_to_index(cachep, slabp, objp); + objnr = obj_to_index(cachep, page, objp); if (objnr) { - objp = index_to_obj(cachep, slabp, objnr - 1); + objp = index_to_obj(cachep, page, objnr - 1); realobj = (char *)objp + obj_offset(cachep); printk(KERN_ERR "Prev obj: start=%p, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } if (objnr + 1 < cachep->num) { - objp = index_to_obj(cachep, slabp, objnr + 1); + objp = index_to_obj(cachep, page, objnr + 1); realobj = (char *)objp + obj_offset(cachep); printk(KERN_ERR "Next obj: start=%p, len=%d\n", realobj, size); @@ -2120,11 +1985,12 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) #endif #if DEBUG -static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp) +static void slab_destroy_debugcheck(struct kmem_cache *cachep, + struct page *page) { int i; for (i = 0; i < cachep->num; i++) { - void *objp = index_to_obj(cachep, slabp, i); + void *objp = index_to_obj(cachep, page, i); if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC @@ -2149,7 +2015,8 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab } } #else -static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp) +static void slab_destroy_debugcheck(struct kmem_cache *cachep, + struct page *page) { } #endif @@ -2157,29 +2024,40 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab /** * slab_destroy - destroy and release all objects in a slab * @cachep: cache pointer being destroyed - * @slabp: slab pointer being destroyed + * @page: page pointer being destroyed * * Destroy all the objs in a slab, and release the mem back to the system. * Before calling the slab must have been unlinked from the cache. The * cache-lock is not held/needed. */ -static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp) +static void slab_destroy(struct kmem_cache *cachep, struct page *page) { - void *addr = slabp->s_mem - slabp->colouroff; + void *freelist; - slab_destroy_debugcheck(cachep, slabp); + freelist = page->freelist; + slab_destroy_debugcheck(cachep, page); if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) { - struct slab_rcu *slab_rcu; + struct rcu_head *head; + + /* + * RCU free overloads the RCU head over the LRU. + * slab_page has been overloeaded over the LRU, + * however it is not used from now on so that + * we can use it safely. + */ + head = (void *)&page->rcu_head; + call_rcu(head, kmem_rcu_free); - slab_rcu = (struct slab_rcu *)slabp; - slab_rcu->cachep = cachep; - slab_rcu->addr = addr; - call_rcu(&slab_rcu->head, kmem_rcu_free); } else { - kmem_freepages(cachep, addr); - if (OFF_SLAB(cachep)) - kmem_cache_free(cachep->slabp_cache, slabp); + kmem_freepages(cachep, page); } + + /* + * From now on, we don't use freelist + * although actual page can be freed in rcu context + */ + if (OFF_SLAB(cachep)) + kmem_cache_free(cachep->freelist_cache, freelist); } /** @@ -2210,14 +2088,21 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, if (!num) continue; + /* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */ + if (num > SLAB_OBJ_MAX_NUM) + break; + if (flags & CFLGS_OFF_SLAB) { + size_t freelist_size_per_obj = sizeof(freelist_idx_t); /* * Max number of objs-per-slab for caches which * use off-slab slabs. Needed to avoid a possible * looping condition in cache_grow(). */ - offslab_limit = size - sizeof(struct slab); - offslab_limit /= sizeof(kmem_bufctl_t); + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + freelist_size_per_obj += sizeof(char); + offslab_limit = size; + offslab_limit /= freelist_size_per_obj; if (num > offslab_limit) break; @@ -2260,7 +2145,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) if (slab_state == DOWN) { /* * Note: Creation of first cache (kmem_cache). - * The setup_list3s is taken care + * The setup_node is taken care * of by the caller of __kmem_cache_create */ cachep->array[smp_processor_id()] = &initarray_generic.cache; @@ -2274,13 +2159,13 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) cachep->array[smp_processor_id()] = &initarray_generic.cache; /* - * If the cache that's used by kmalloc(sizeof(kmem_list3)) is - * the second cache, then we need to set up all its list3s, + * If the cache that's used by kmalloc(sizeof(kmem_cache_node)) is + * the second cache, then we need to set up all its node/, * otherwise the creation of further caches will BUG(). */ - set_up_list3s(cachep, SIZE_AC); - if (INDEX_AC == INDEX_L3) - slab_state = PARTIAL_L3; + set_up_node(cachep, SIZE_AC); + if (INDEX_AC == INDEX_NODE) + slab_state = PARTIAL_NODE; else slab_state = PARTIAL_ARRAYCACHE; } else { @@ -2289,22 +2174,22 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) kmalloc(sizeof(struct arraycache_init), gfp); if (slab_state == PARTIAL_ARRAYCACHE) { - set_up_list3s(cachep, SIZE_L3); - slab_state = PARTIAL_L3; + set_up_node(cachep, SIZE_NODE); + slab_state = PARTIAL_NODE; } else { int node; for_each_online_node(node) { - cachep->nodelists[node] = - kmalloc_node(sizeof(struct kmem_list3), + cachep->node[node] = + kmalloc_node(sizeof(struct kmem_cache_node), gfp, node); - BUG_ON(!cachep->nodelists[node]); - kmem_list3_init(cachep->nodelists[node]); + BUG_ON(!cachep->node[node]); + kmem_cache_node_init(cachep->node[node]); } } } - cachep->nodelists[numa_mem_id()]->next_reap = - jiffies + REAPTIMEOUT_LIST3 + - ((unsigned long)cachep) % REAPTIMEOUT_LIST3; + cachep->node[numa_mem_id()]->next_reap = + jiffies + REAPTIMEOUT_NODE + + ((unsigned long)cachep) % REAPTIMEOUT_NODE; cpu_cache_get(cachep)->avail = 0; cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES; @@ -2339,7 +2224,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) int __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) { - size_t left_over, slab_size, ralign; + size_t left_over, freelist_size, ralign; gfp_t gfp; int err; size_t size = cachep->size; @@ -2405,7 +2290,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) else gfp = GFP_NOWAIT; - setup_nodelists_pointer(cachep); + setup_node_pointer(cachep); #if DEBUG /* @@ -2428,7 +2313,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) size += BYTES_PER_WORD; } #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) - if (size >= malloc_sizes[INDEX_L3 + 1].cs_size + if (size >= kmalloc_size(INDEX_NODE + 1) && cachep->object_size > cache_line_size() && ALIGN(size, cachep->align) < PAGE_SIZE) { cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align); @@ -2443,7 +2328,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) * it too early on. Always use on-slab management when * SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak) */ - if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init && + if ((size >= (PAGE_SIZE >> 5)) && !slab_early_init && !(flags & SLAB_NOLEAKTRACE)) /* * Size is large, assume best to place the slab management obj @@ -2452,28 +2337,32 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) flags |= CFLGS_OFF_SLAB; size = ALIGN(size, cachep->align); + /* + * We should restrict the number of objects in a slab to implement + * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition. + */ + if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE) + size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align); left_over = calculate_slab_order(cachep, size, cachep->align, flags); if (!cachep->num) return -E2BIG; - slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t) - + sizeof(struct slab), cachep->align); + freelist_size = calculate_freelist_size(cachep->num, cachep->align); /* * If the slab has been placed off-slab, and we have enough space then * move it on-slab. This is at the expense of any extra colouring. */ - if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) { + if (flags & CFLGS_OFF_SLAB && left_over >= freelist_size) { flags &= ~CFLGS_OFF_SLAB; - left_over -= slab_size; + left_over -= freelist_size; } if (flags & CFLGS_OFF_SLAB) { /* really off slab. No need for manual alignment */ - slab_size = - cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab); + freelist_size = calculate_freelist_size(cachep->num, 0); #ifdef CONFIG_PAGE_POISONING /* If we're going to use the generic kernel_map_pages() @@ -2490,24 +2379,24 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) if (cachep->colour_off < cachep->align) cachep->colour_off = cachep->align; cachep->colour = left_over / cachep->colour_off; - cachep->slab_size = slab_size; + cachep->freelist_size = freelist_size; cachep->flags = flags; - cachep->allocflags = 0; + cachep->allocflags = __GFP_COMP; if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA)) cachep->allocflags |= GFP_DMA; cachep->size = size; cachep->reciprocal_buffer_size = reciprocal_value(size); if (flags & CFLGS_OFF_SLAB) { - cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u); + cachep->freelist_cache = kmalloc_slab(freelist_size, 0u); /* - * This is a possibility for one of the malloc_sizes caches. + * This is a possibility for one of the kmalloc_{dma,}_caches. * But since we go off slab only for object size greater than - * PAGE_SIZE/8, and malloc_sizes gets created in ascending order, - * this should not happen at all. + * PAGE_SIZE/8, and kmalloc_{dma,}_caches get created + * in ascending order,this should not happen at all. * But leave a BUG_ON for some lucky dude. */ - BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache)); + BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache)); } err = setup_cpu_cache(cachep, gfp); @@ -2545,7 +2434,7 @@ static void check_spinlock_acquired(struct kmem_cache *cachep) { #ifdef CONFIG_SMP check_irq_off(); - assert_spin_locked(&cachep->nodelists[numa_mem_id()]->list_lock); + assert_spin_locked(&cachep->node[numa_mem_id()]->list_lock); #endif } @@ -2553,7 +2442,7 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node) { #ifdef CONFIG_SMP check_irq_off(); - assert_spin_locked(&cachep->nodelists[node]->list_lock); + assert_spin_locked(&cachep->node[node]->list_lock); #endif } @@ -2564,7 +2453,7 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node) #define check_spinlock_acquired_node(x, y) do { } while(0) #endif -static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, +static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, struct array_cache *ac, int force, int node); @@ -2576,29 +2465,29 @@ static void do_drain(void *arg) check_irq_off(); ac = cpu_cache_get(cachep); - spin_lock(&cachep->nodelists[node]->list_lock); + spin_lock(&cachep->node[node]->list_lock); free_block(cachep, ac->entry, ac->avail, node); - spin_unlock(&cachep->nodelists[node]->list_lock); + spin_unlock(&cachep->node[node]->list_lock); ac->avail = 0; } static void drain_cpu_caches(struct kmem_cache *cachep) { - struct kmem_list3 *l3; + struct kmem_cache_node *n; int node; on_each_cpu(do_drain, cachep, 1); check_irq_on(); for_each_online_node(node) { - l3 = cachep->nodelists[node]; - if (l3 && l3->alien) - drain_alien_cache(cachep, l3->alien); + n = cachep->node[node]; + if (n && n->alien) + drain_alien_cache(cachep, n->alien); } for_each_online_node(node) { - l3 = cachep->nodelists[node]; - if (l3) - drain_array(cachep, l3, l3->shared, 1, node); + n = cachep->node[node]; + if (n) + drain_array(cachep, n, n->shared, 1, node); } } @@ -2609,88 +2498,66 @@ static void drain_cpu_caches(struct kmem_cache *cachep) * Returns the actual number of slabs released. */ static int drain_freelist(struct kmem_cache *cache, - struct kmem_list3 *l3, int tofree) + struct kmem_cache_node *n, int tofree) { struct list_head *p; int nr_freed; - struct slab *slabp; + struct page *page; nr_freed = 0; - while (nr_freed < tofree && !list_empty(&l3->slabs_free)) { + while (nr_freed < tofree && !list_empty(&n->slabs_free)) { - spin_lock_irq(&l3->list_lock); - p = l3->slabs_free.prev; - if (p == &l3->slabs_free) { - spin_unlock_irq(&l3->list_lock); + spin_lock_irq(&n->list_lock); + p = n->slabs_free.prev; + if (p == &n->slabs_free) { + spin_unlock_irq(&n->list_lock); goto out; } - slabp = list_entry(p, struct slab, list); + page = list_entry(p, struct page, lru); #if DEBUG - BUG_ON(slabp->inuse); + BUG_ON(page->active); #endif - list_del(&slabp->list); + list_del(&page->lru); /* * Safe to drop the lock. The slab is no longer linked * to the cache. */ - l3->free_objects -= cache->num; - spin_unlock_irq(&l3->list_lock); - slab_destroy(cache, slabp); + n->free_objects -= cache->num; + spin_unlock_irq(&n->list_lock); + slab_destroy(cache, page); nr_freed++; } out: return nr_freed; } -/* Called with slab_mutex held to protect against cpu hotplug */ -static int __cache_shrink(struct kmem_cache *cachep) +int __kmem_cache_shrink(struct kmem_cache *cachep) { int ret = 0, i = 0; - struct kmem_list3 *l3; + struct kmem_cache_node *n; drain_cpu_caches(cachep); check_irq_on(); for_each_online_node(i) { - l3 = cachep->nodelists[i]; - if (!l3) + n = cachep->node[i]; + if (!n) continue; - drain_freelist(cachep, l3, l3->free_objects); + drain_freelist(cachep, n, slabs_tofree(cachep, n)); - ret += !list_empty(&l3->slabs_full) || - !list_empty(&l3->slabs_partial); + ret += !list_empty(&n->slabs_full) || + !list_empty(&n->slabs_partial); } return (ret ? 1 : 0); } -/** - * kmem_cache_shrink - Shrink a cache. - * @cachep: The cache to shrink. - * - * Releases as many slabs as possible for a cache. - * To help debugging, a zero exit status indicates all slabs were released. - */ -int kmem_cache_shrink(struct kmem_cache *cachep) -{ - int ret; - BUG_ON(!cachep || in_interrupt()); - - get_online_cpus(); - mutex_lock(&slab_mutex); - ret = __cache_shrink(cachep); - mutex_unlock(&slab_mutex); - put_online_cpus(); - return ret; -} -EXPORT_SYMBOL(kmem_cache_shrink); - int __kmem_cache_shutdown(struct kmem_cache *cachep) { int i; - struct kmem_list3 *l3; - int rc = __cache_shrink(cachep); + struct kmem_cache_node *n; + int rc = __kmem_cache_shrink(cachep); if (rc) return rc; @@ -2698,13 +2565,13 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep) for_each_online_cpu(i) kfree(cachep->array[i]); - /* NUMA: free the list3 structures */ + /* NUMA: free the node structures */ for_each_online_node(i) { - l3 = cachep->nodelists[i]; - if (l3) { - kfree(l3->shared); - free_alien_cache(l3->alien); - kfree(l3); + n = cachep->node[i]; + if (n) { + kfree(n->shared); + free_alien_cache(n->alien); + kfree(n); } } return 0; @@ -2712,59 +2579,58 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep) /* * Get the memory for a slab management obj. - * For a slab cache when the slab descriptor is off-slab, slab descriptors - * always come from malloc_sizes caches. The slab descriptor cannot - * come from the same cache which is getting created because, - * when we are searching for an appropriate cache for these - * descriptors in kmem_cache_create, we search through the malloc_sizes array. - * If we are creating a malloc_sizes cache here it would not be visible to - * kmem_find_general_cachep till the initialization is complete. - * Hence we cannot have slabp_cache same as the original cache. + * + * For a slab cache when the slab descriptor is off-slab, the + * slab descriptor can't come from the same cache which is being created, + * Because if it is the case, that means we defer the creation of + * the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point. + * And we eventually call down to __kmem_cache_create(), which + * in turn looks up in the kmalloc_{dma,}_caches for the disired-size one. + * This is a "chicken-and-egg" problem. + * + * So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches, + * which are all initialized during kmem_cache_init(). */ -static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp, - int colour_off, gfp_t local_flags, - int nodeid) +static void *alloc_slabmgmt(struct kmem_cache *cachep, + struct page *page, int colour_off, + gfp_t local_flags, int nodeid) { - struct slab *slabp; + void *freelist; + void *addr = page_address(page); if (OFF_SLAB(cachep)) { /* Slab management obj is off-slab. */ - slabp = kmem_cache_alloc_node(cachep->slabp_cache, + freelist = kmem_cache_alloc_node(cachep->freelist_cache, local_flags, nodeid); - /* - * If the first object in the slab is leaked (it's allocated - * but no one has a reference to it), we want to make sure - * kmemleak does not treat the ->s_mem pointer as a reference - * to the object. Otherwise we will not report the leak. - */ - kmemleak_scan_area(&slabp->list, sizeof(struct list_head), - local_flags); - if (!slabp) + if (!freelist) return NULL; } else { - slabp = objp + colour_off; - colour_off += cachep->slab_size; + freelist = addr + colour_off; + colour_off += cachep->freelist_size; } - slabp->inuse = 0; - slabp->colouroff = colour_off; - slabp->s_mem = objp + colour_off; - slabp->nodeid = nodeid; - slabp->free = 0; - return slabp; + page->active = 0; + page->s_mem = addr + colour_off; + return freelist; +} + +static inline freelist_idx_t get_free_obj(struct page *page, unsigned int idx) +{ + return ((freelist_idx_t *)page->freelist)[idx]; } -static inline kmem_bufctl_t *slab_bufctl(struct slab *slabp) +static inline void set_free_obj(struct page *page, + unsigned int idx, freelist_idx_t val) { - return (kmem_bufctl_t *) (slabp + 1); + ((freelist_idx_t *)(page->freelist))[idx] = val; } static void cache_init_objs(struct kmem_cache *cachep, - struct slab *slabp) + struct page *page) { int i; for (i = 0; i < cachep->num; i++) { - void *objp = index_to_obj(cachep, slabp, i); + void *objp = index_to_obj(cachep, page, i); #if DEBUG /* need to poison the objs? */ if (cachep->flags & SLAB_POISON) @@ -2800,9 +2666,9 @@ static void cache_init_objs(struct kmem_cache *cachep, if (cachep->ctor) cachep->ctor(objp); #endif - slab_bufctl(slabp)[i] = i + 1; + set_obj_status(page, i, OBJECT_FREE); + set_free_obj(page, i, i); } - slab_bufctl(slabp)[i - 1] = BUFCTL_END; } static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags) @@ -2815,41 +2681,41 @@ static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags) } } -static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp, +static void *slab_get_obj(struct kmem_cache *cachep, struct page *page, int nodeid) { - void *objp = index_to_obj(cachep, slabp, slabp->free); - kmem_bufctl_t next; + void *objp; - slabp->inuse++; - next = slab_bufctl(slabp)[slabp->free]; + objp = index_to_obj(cachep, page, get_free_obj(page, page->active)); + page->active++; #if DEBUG - slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE; - WARN_ON(slabp->nodeid != nodeid); + WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid); #endif - slabp->free = next; return objp; } -static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, +static void slab_put_obj(struct kmem_cache *cachep, struct page *page, void *objp, int nodeid) { - unsigned int objnr = obj_to_index(cachep, slabp, objp); - + unsigned int objnr = obj_to_index(cachep, page, objp); #if DEBUG + unsigned int i; + /* Verify that the slab belongs to the intended node */ - WARN_ON(slabp->nodeid != nodeid); + WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid); - if (slab_bufctl(slabp)[objnr] + 1 <= SLAB_LIMIT + 1) { - printk(KERN_ERR "slab: double free detected in cache " - "'%s', objp %p\n", cachep->name, objp); - BUG(); + /* Verify double free bug */ + for (i = page->active; i < cachep->num; i++) { + if (get_free_obj(page, i) == objnr) { + printk(KERN_ERR "slab: double free detected in cache " + "'%s', objp %p\n", cachep->name, objp); + BUG(); + } } #endif - slab_bufctl(slabp)[objnr] = slabp->free; - slabp->free = objnr; - slabp->inuse--; + page->active--; + set_free_obj(page, page->active, objnr); } /* @@ -2857,23 +2723,11 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, * for the slab allocator to be able to lookup the cache and slab of a * virtual address for kfree, ksize, and slab debugging. */ -static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, - void *addr) +static void slab_map_pages(struct kmem_cache *cache, struct page *page, + void *freelist) { - int nr_pages; - struct page *page; - - page = virt_to_page(addr); - - nr_pages = 1; - if (likely(!PageCompound(page))) - nr_pages <<= cache->gfporder; - - do { - page->slab_cache = cache; - page->slab_page = slab; - page++; - } while (--nr_pages); + page->slab_cache = cache; + page->freelist = freelist; } /* @@ -2881,12 +2735,12 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, * 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, void *objp) + gfp_t flags, int nodeid, struct page *page) { - struct slab *slabp; + void *freelist; size_t offset; gfp_t local_flags; - struct kmem_list3 *l3; + struct kmem_cache_node *n; /* * Be lazy and only check for valid flags here, keeping it out of the @@ -2895,17 +2749,17 @@ static int cache_grow(struct kmem_cache *cachep, BUG_ON(flags & GFP_SLAB_BUG_MASK); local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); - /* Take the l3 list lock to change the colour_next on this node */ + /* Take the node list lock to change the colour_next on this node */ check_irq_off(); - l3 = cachep->nodelists[nodeid]; - spin_lock(&l3->list_lock); + n = cachep->node[nodeid]; + spin_lock(&n->list_lock); /* Get colour for the slab, and cal the next value. */ - offset = l3->colour_next; - l3->colour_next++; - if (l3->colour_next >= cachep->colour) - l3->colour_next = 0; - spin_unlock(&l3->list_lock); + offset = n->colour_next; + n->colour_next++; + if (n->colour_next >= cachep->colour) + n->colour_next = 0; + spin_unlock(&n->list_lock); offset *= cachep->colour_off; @@ -2924,34 +2778,34 @@ static int cache_grow(struct kmem_cache *cachep, * Get mem for the objs. Attempt to allocate a physical page from * 'nodeid'. */ - if (!objp) - objp = kmem_getpages(cachep, local_flags, nodeid); - if (!objp) + if (!page) + page = kmem_getpages(cachep, local_flags, nodeid); + if (!page) goto failed; /* Get slab management. */ - slabp = alloc_slabmgmt(cachep, objp, offset, + freelist = alloc_slabmgmt(cachep, page, offset, local_flags & ~GFP_CONSTRAINT_MASK, nodeid); - if (!slabp) + if (!freelist) goto opps1; - slab_map_pages(cachep, slabp, objp); + slab_map_pages(cachep, page, freelist); - cache_init_objs(cachep, slabp); + cache_init_objs(cachep, page); if (local_flags & __GFP_WAIT) local_irq_disable(); check_irq_off(); - spin_lock(&l3->list_lock); + spin_lock(&n->list_lock); /* Make slab active. */ - list_add_tail(&slabp->list, &(l3->slabs_free)); + list_add_tail(&page->lru, &(n->slabs_free)); STATS_INC_GROWN(cachep); - l3->free_objects += cachep->num; - spin_unlock(&l3->list_lock); + n->free_objects += cachep->num; + spin_unlock(&n->list_lock); return 1; opps1: - kmem_freepages(cachep, objp); + kmem_freepages(cachep, page); failed: if (local_flags & __GFP_WAIT) local_irq_disable(); @@ -2999,9 +2853,8 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj) static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, unsigned long caller) { - struct page *page; unsigned int objnr; - struct slab *slabp; + struct page *page; BUG_ON(virt_to_cache(objp) != cachep); @@ -3009,8 +2862,6 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, kfree_debugcheck(objp); page = virt_to_head_page(objp); - slabp = page->slab_page; - if (cachep->flags & SLAB_RED_ZONE) { verify_redzone_free(cachep, objp); *dbg_redzone1(cachep, objp) = RED_INACTIVE; @@ -3019,14 +2870,12 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, if (cachep->flags & SLAB_STORE_USER) *dbg_userword(cachep, objp) = (void *)caller; - objnr = obj_to_index(cachep, slabp, objp); + objnr = obj_to_index(cachep, page, objp); BUG_ON(objnr >= cachep->num); - BUG_ON(objp != index_to_obj(cachep, slabp, objnr)); + BUG_ON(objp != index_to_obj(cachep, page, objnr)); -#ifdef CONFIG_DEBUG_SLAB_LEAK - slab_bufctl(slabp)[objnr] = BUFCTL_FREE; -#endif + set_obj_status(page, objnr, OBJECT_FREE); if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { @@ -3043,40 +2892,16 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, return objp; } -static void check_slabp(struct kmem_cache *cachep, struct slab *slabp) -{ - kmem_bufctl_t i; - int entries = 0; - - /* Check slab's freelist to see if this obj is there. */ - for (i = slabp->free; i != BUFCTL_END; i = slab_bufctl(slabp)[i]) { - entries++; - if (entries > cachep->num || i >= cachep->num) - goto bad; - } - if (entries != cachep->num - slabp->inuse) { -bad: - printk(KERN_ERR "slab: Internal list corruption detected in " - "cache '%s'(%d), slabp %p(%d). Tainted(%s). Hexdump:\n", - cachep->name, cachep->num, slabp, slabp->inuse, - print_tainted()); - print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, slabp, - sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t), - 1); - BUG(); - } -} #else #define kfree_debugcheck(x) do { } while(0) #define cache_free_debugcheck(x,objp,z) (objp) -#define check_slabp(x,y) do { } while(0) #endif static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags, bool force_refill) { int batchcount; - struct kmem_list3 *l3; + struct kmem_cache_node *n; struct array_cache *ac; int node; @@ -3095,31 +2920,30 @@ retry: */ batchcount = BATCHREFILL_LIMIT; } - l3 = cachep->nodelists[node]; + n = cachep->node[node]; - BUG_ON(ac->avail > 0 || !l3); - spin_lock(&l3->list_lock); + BUG_ON(ac->avail > 0 || !n); + spin_lock(&n->list_lock); /* See if we can refill from the shared array */ - if (l3->shared && transfer_objects(ac, l3->shared, batchcount)) { - l3->shared->touched = 1; + if (n->shared && transfer_objects(ac, n->shared, batchcount)) { + n->shared->touched = 1; goto alloc_done; } while (batchcount > 0) { struct list_head *entry; - struct slab *slabp; + struct page *page; /* Get slab alloc is to come from. */ - entry = l3->slabs_partial.next; - if (entry == &l3->slabs_partial) { - l3->free_touched = 1; - entry = l3->slabs_free.next; - if (entry == &l3->slabs_free) + entry = n->slabs_partial.next; + if (entry == &n->slabs_partial) { + n->free_touched = 1; + entry = n->slabs_free.next; + if (entry == &n->slabs_free) goto must_grow; } - slabp = list_entry(entry, struct slab, list); - check_slabp(cachep, slabp); + page = list_entry(entry, struct page, lru); check_spinlock_acquired(cachep); /* @@ -3127,30 +2951,29 @@ retry: * there must be at least one object available for * allocation. */ - BUG_ON(slabp->inuse >= cachep->num); + BUG_ON(page->active >= cachep->num); - while (slabp->inuse < cachep->num && batchcount--) { + while (page->active < cachep->num && batchcount--) { STATS_INC_ALLOCED(cachep); STATS_INC_ACTIVE(cachep); STATS_SET_HIGH(cachep); - ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp, + ac_put_obj(cachep, ac, slab_get_obj(cachep, page, node)); } - check_slabp(cachep, slabp); /* move slabp to correct slabp list: */ - list_del(&slabp->list); - if (slabp->free == BUFCTL_END) - list_add(&slabp->list, &l3->slabs_full); + list_del(&page->lru); + if (page->active == cachep->num) + list_add(&page->lru, &n->slabs_full); else - list_add(&slabp->list, &l3->slabs_partial); + list_add(&page->lru, &n->slabs_partial); } must_grow: - l3->free_objects -= ac->avail; + n->free_objects -= ac->avail; alloc_done: - spin_unlock(&l3->list_lock); + spin_unlock(&n->list_lock); if (unlikely(!ac->avail)) { int x; @@ -3186,6 +3009,8 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, gfp_t flags, void *objp, unsigned long caller) { + struct page *page; + if (!objp) return objp; if (cachep->flags & SLAB_POISON) { @@ -3216,16 +3041,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, *dbg_redzone1(cachep, objp) = RED_ACTIVE; *dbg_redzone2(cachep, objp) = RED_ACTIVE; } -#ifdef CONFIG_DEBUG_SLAB_LEAK - { - struct slab *slabp; - unsigned objnr; - slabp = virt_to_head_page(objp)->slab_page; - objnr = (unsigned)(objp - slabp->s_mem) / cachep->size; - slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE; - } -#endif + page = virt_to_head_page(objp); + set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE); objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) cachep->ctor(objp); @@ -3293,7 +3111,7 @@ out: #ifdef CONFIG_NUMA /* - * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY. + * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set. * * If we are in_interrupt, then process context, including cpusets and * mempolicy, may not apply and should not be used for allocation policy. @@ -3308,7 +3126,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) nid_alloc = cpuset_slab_spread_node(); else if (current->mempolicy) - nid_alloc = slab_node(); + nid_alloc = mempolicy_slab_node(); if (nid_alloc != nid_here) return ____cache_alloc_node(cachep, flags, nid_alloc); return NULL; @@ -3317,7 +3135,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) /* * 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 + * available node 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. @@ -3339,8 +3157,8 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); - zonelist = node_zonelist(slab_node(), flags); + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist = node_zonelist(mempolicy_slab_node(), flags); retry: /* @@ -3351,8 +3169,8 @@ retry: nid = zone_to_nid(zone); if (cpuset_zone_allowed_hardwall(zone, flags) && - cache->nodelists[nid] && - cache->nodelists[nid]->free_objects) { + cache->node[nid] && + cache->node[nid]->free_objects) { obj = ____cache_alloc_node(cache, flags | GFP_THISNODE, nid); if (obj) @@ -3367,18 +3185,20 @@ retry: * We may trigger various forms of reclaim on the allowed * set and go into memory reserves if necessary. */ + struct page *page; + if (local_flags & __GFP_WAIT) local_irq_enable(); kmem_flagcheck(cache, flags); - obj = kmem_getpages(cache, local_flags, numa_mem_id()); + page = kmem_getpages(cache, local_flags, numa_mem_id()); if (local_flags & __GFP_WAIT) local_irq_disable(); - if (obj) { + if (page) { /* * Insert into the appropriate per node queues */ - nid = page_to_nid(virt_to_page(obj)); - if (cache_grow(cache, flags, nid, obj)) { + nid = page_to_nid(page); + if (cache_grow(cache, flags, nid, page)) { obj = ____cache_alloc_node(cache, flags | GFP_THISNODE, nid); if (!obj) @@ -3395,7 +3215,7 @@ retry: } } - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj)) + if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return obj; } @@ -3407,51 +3227,50 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { struct list_head *entry; - struct slab *slabp; - struct kmem_list3 *l3; + struct page *page; + struct kmem_cache_node *n; void *obj; int x; - l3 = cachep->nodelists[nodeid]; - BUG_ON(!l3); + VM_BUG_ON(nodeid > num_online_nodes()); + n = cachep->node[nodeid]; + BUG_ON(!n); retry: check_irq_off(); - spin_lock(&l3->list_lock); - entry = l3->slabs_partial.next; - if (entry == &l3->slabs_partial) { - l3->free_touched = 1; - entry = l3->slabs_free.next; - if (entry == &l3->slabs_free) + spin_lock(&n->list_lock); + entry = n->slabs_partial.next; + if (entry == &n->slabs_partial) { + n->free_touched = 1; + entry = n->slabs_free.next; + if (entry == &n->slabs_free) goto must_grow; } - slabp = list_entry(entry, struct slab, list); + page = list_entry(entry, struct page, lru); check_spinlock_acquired_node(cachep, nodeid); - check_slabp(cachep, slabp); STATS_INC_NODEALLOCS(cachep); STATS_INC_ACTIVE(cachep); STATS_SET_HIGH(cachep); - BUG_ON(slabp->inuse == cachep->num); + BUG_ON(page->active == cachep->num); - obj = slab_get_obj(cachep, slabp, nodeid); - check_slabp(cachep, slabp); - l3->free_objects--; + obj = slab_get_obj(cachep, page, nodeid); + n->free_objects--; /* move slabp to correct slabp list: */ - list_del(&slabp->list); + list_del(&page->lru); - if (slabp->free == BUFCTL_END) - list_add(&slabp->list, &l3->slabs_full); + if (page->active == cachep->num) + list_add(&page->lru, &n->slabs_full); else - list_add(&slabp->list, &l3->slabs_partial); + list_add(&page->lru, &n->slabs_partial); - spin_unlock(&l3->list_lock); + spin_unlock(&n->list_lock); goto done; must_grow: - spin_unlock(&l3->list_lock); + spin_unlock(&n->list_lock); x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL); if (x) goto retry; @@ -3462,18 +3281,6 @@ done: return obj; } -/** - * kmem_cache_alloc_node - Allocate an object on the specified node - * @cachep: The cache to allocate from. - * @flags: See kmalloc(). - * @nodeid: node number of the target node. - * @caller: return address of caller, used for debug information - * - * 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. - */ static __always_inline void * slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, unsigned long caller) @@ -3497,7 +3304,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, if (nodeid == NUMA_NO_NODE) nodeid = slab_node; - if (unlikely(!cachep->nodelists[nodeid])) { + if (unlikely(!cachep->node[nodeid])) { /* Node not bootstrapped yet */ ptr = fallback_alloc(cachep, flags); goto out; @@ -3522,11 +3329,11 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags, flags); - if (likely(ptr)) + if (likely(ptr)) { kmemcheck_slab_alloc(cachep, flags, ptr, cachep->object_size); - - if (unlikely((flags & __GFP_ZERO) && ptr)) - memset(ptr, 0, cachep->object_size); + if (unlikely(flags & __GFP_ZERO)) + memset(ptr, 0, cachep->object_size); + } return ptr; } @@ -3536,7 +3343,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags) { void *objp; - if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) { + if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) { objp = alternate_node_alloc(cache, flags); if (objp) goto out; @@ -3587,61 +3394,59 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) flags); prefetchw(objp); - if (likely(objp)) + if (likely(objp)) { kmemcheck_slab_alloc(cachep, flags, objp, cachep->object_size); - - if (unlikely((flags & __GFP_ZERO) && objp)) - memset(objp, 0, cachep->object_size); + if (unlikely(flags & __GFP_ZERO)) + memset(objp, 0, cachep->object_size); + } return objp; } /* - * Caller needs to acquire correct kmem_list's list_lock + * Caller needs to acquire correct kmem_cache_node's list_lock */ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects, int node) { int i; - struct kmem_list3 *l3; + struct kmem_cache_node *n; for (i = 0; i < nr_objects; i++) { void *objp; - struct slab *slabp; + struct page *page; clear_obj_pfmemalloc(&objpp[i]); objp = objpp[i]; - slabp = virt_to_slab(objp); - l3 = cachep->nodelists[node]; - list_del(&slabp->list); + page = virt_to_head_page(objp); + n = cachep->node[node]; + list_del(&page->lru); check_spinlock_acquired_node(cachep, node); - check_slabp(cachep, slabp); - slab_put_obj(cachep, slabp, objp, node); + slab_put_obj(cachep, page, objp, node); STATS_DEC_ACTIVE(cachep); - l3->free_objects++; - check_slabp(cachep, slabp); + n->free_objects++; /* fixup slab chains */ - if (slabp->inuse == 0) { - if (l3->free_objects > l3->free_limit) { - l3->free_objects -= cachep->num; + if (page->active == 0) { + if (n->free_objects > n->free_limit) { + n->free_objects -= cachep->num; /* No need to drop any previously held * lock here, even if we have a off-slab slab * descriptor it is guaranteed to come from * a different cache, refer to comments before * alloc_slabmgmt. */ - slab_destroy(cachep, slabp); + slab_destroy(cachep, page); } else { - list_add(&slabp->list, &l3->slabs_free); + list_add(&page->lru, &n->slabs_free); } } else { /* Unconditionally move a slab to the end of the * partial list on free - maximum time for the * other objects to be freed, too. */ - list_add_tail(&slabp->list, &l3->slabs_partial); + list_add_tail(&page->lru, &n->slabs_partial); } } } @@ -3649,7 +3454,7 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects, static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) { int batchcount; - struct kmem_list3 *l3; + struct kmem_cache_node *n; int node = numa_mem_id(); batchcount = ac->batchcount; @@ -3657,10 +3462,10 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) BUG_ON(!batchcount || batchcount > ac->avail); #endif check_irq_off(); - l3 = cachep->nodelists[node]; - spin_lock(&l3->list_lock); - if (l3->shared) { - struct array_cache *shared_array = l3->shared; + n = cachep->node[node]; + spin_lock(&n->list_lock); + if (n->shared) { + struct array_cache *shared_array = n->shared; int max = shared_array->limit - shared_array->avail; if (max) { if (batchcount > max) @@ -3679,12 +3484,12 @@ free_done: int i = 0; struct list_head *p; - p = l3->slabs_free.next; - while (p != &(l3->slabs_free)) { - struct slab *slabp; + p = n->slabs_free.next; + while (p != &(n->slabs_free)) { + struct page *page; - slabp = list_entry(p, struct slab, list); - BUG_ON(slabp->inuse); + page = list_entry(p, struct page, lru); + BUG_ON(page->active); i++; p = p->next; @@ -3692,7 +3497,7 @@ free_done: STATS_SET_FREEABLE(cachep, i); } #endif - spin_unlock(&l3->list_lock); + spin_unlock(&n->list_lock); ac->avail -= batchcount; memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail); } @@ -3767,6 +3572,17 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace); #endif #ifdef CONFIG_NUMA +/** + * kmem_cache_alloc_node - Allocate an object on the specified node + * @cachep: The cache to allocate from. + * @flags: See kmalloc(). + * @nodeid: node number of the target node. + * + * 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) { void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); @@ -3802,7 +3618,7 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller) { struct kmem_cache *cachep; - cachep = kmem_find_general_cachep(size, flags); + cachep = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; return kmem_cache_alloc_node_trace(cachep, flags, node, size); @@ -3842,12 +3658,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, struct kmem_cache *cachep; void *ret; - /* If you want to save a few bytes .text space: replace - * __ with kmem_. - * Then kmalloc uses the uninlined functions instead of the inline - * functions. - */ - cachep = __find_general_cachep(size, flags); + cachep = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; ret = slab_alloc(cachep, flags, caller); @@ -3936,12 +3747,12 @@ void kfree(const void *objp) EXPORT_SYMBOL(kfree); /* - * This initializes kmem_list3 or resizes various caches for all nodes. + * This initializes kmem_cache_node or resizes various caches for all nodes. */ -static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) +static int alloc_kmem_cache_node(struct kmem_cache *cachep, gfp_t gfp) { int node; - struct kmem_list3 *l3; + struct kmem_cache_node *n; struct array_cache *new_shared; struct array_cache **new_alien = NULL; @@ -3964,43 +3775,43 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) } } - l3 = cachep->nodelists[node]; - if (l3) { - struct array_cache *shared = l3->shared; + n = cachep->node[node]; + if (n) { + struct array_cache *shared = n->shared; - spin_lock_irq(&l3->list_lock); + spin_lock_irq(&n->list_lock); if (shared) free_block(cachep, shared->entry, shared->avail, node); - l3->shared = new_shared; - if (!l3->alien) { - l3->alien = new_alien; + n->shared = new_shared; + if (!n->alien) { + n->alien = new_alien; new_alien = NULL; } - l3->free_limit = (1 + nr_cpus_node(node)) * + n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - spin_unlock_irq(&l3->list_lock); + spin_unlock_irq(&n->list_lock); kfree(shared); free_alien_cache(new_alien); continue; } - l3 = kmalloc_node(sizeof(struct kmem_list3), gfp, node); - if (!l3) { + n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node); + if (!n) { free_alien_cache(new_alien); kfree(new_shared); goto fail; } - kmem_list3_init(l3); - l3->next_reap = jiffies + REAPTIMEOUT_LIST3 + - ((unsigned long)cachep) % REAPTIMEOUT_LIST3; - l3->shared = new_shared; - l3->alien = new_alien; - l3->free_limit = (1 + nr_cpus_node(node)) * + kmem_cache_node_init(n); + n->next_reap = jiffies + REAPTIMEOUT_NODE + + ((unsigned long)cachep) % REAPTIMEOUT_NODE; + n->shared = new_shared; + n->alien = new_alien; + n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - cachep->nodelists[node] = l3; + cachep->node[node] = n; } return 0; @@ -4009,13 +3820,13 @@ fail: /* Cache is not active yet. Roll back what we did */ node--; while (node >= 0) { - if (cachep->nodelists[node]) { - l3 = cachep->nodelists[node]; + if (cachep->node[node]) { + n = cachep->node[node]; - kfree(l3->shared); - free_alien_cache(l3->alien); - kfree(l3); - cachep->nodelists[node] = NULL; + kfree(n->shared); + free_alien_cache(n->alien); + kfree(n); + cachep->node[node] = NULL; } node--; } @@ -4075,13 +3886,13 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, struct array_cache *ccold = new->new[i]; if (!ccold) continue; - spin_lock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock); + spin_lock_irq(&cachep->node[cpu_to_mem(i)]->list_lock); free_block(cachep, ccold->entry, ccold->avail, cpu_to_mem(i)); - spin_unlock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock); + spin_unlock_irq(&cachep->node[cpu_to_mem(i)]->list_lock); kfree(ccold); } kfree(new); - return alloc_kmemlist(cachep, gfp); + return alloc_kmem_cache_node(cachep, gfp); } static int do_tune_cpucache(struct kmem_cache *cachep, int limit, @@ -4101,7 +3912,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, VM_BUG_ON(!mutex_is_locked(&slab_mutex)); for_each_memcg_cache_index(i) { - c = cache_from_memcg(cachep, i); + c = cache_from_memcg_idx(cachep, i); if (c) /* return value determined by the parent cache only */ __do_tune_cpucache(c, limit, batchcount, shared, gfp); @@ -4178,11 +3989,11 @@ skip_setup: } /* - * Drain an array if it contains any elements taking the l3 lock only if - * necessary. Note that the l3 listlock also protects the array_cache + * Drain an array if it contains any elements taking the node lock only if + * necessary. Note that the node listlock also protects the array_cache * if drain_array() is used on the shared array. */ -static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, +static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, struct array_cache *ac, int force, int node) { int tofree; @@ -4192,7 +4003,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, if (ac->touched && !force) { ac->touched = 0; } else { - spin_lock_irq(&l3->list_lock); + spin_lock_irq(&n->list_lock); if (ac->avail) { tofree = force ? ac->avail : (ac->limit + 4) / 5; if (tofree > ac->avail) @@ -4202,7 +4013,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, memmove(ac->entry, &(ac->entry[tofree]), sizeof(void *) * ac->avail); } - spin_unlock_irq(&l3->list_lock); + spin_unlock_irq(&n->list_lock); } } @@ -4221,7 +4032,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, static void cache_reap(struct work_struct *w) { struct kmem_cache *searchp; - struct kmem_list3 *l3; + struct kmem_cache_node *n; int node = numa_mem_id(); struct delayed_work *work = to_delayed_work(w); @@ -4233,33 +4044,33 @@ static void cache_reap(struct work_struct *w) check_irq_on(); /* - * We only take the l3 lock if absolutely necessary and we + * We only take the node lock if absolutely necessary and we * have established with reasonable certainty that * we can do some work if the lock was obtained. */ - l3 = searchp->nodelists[node]; + n = searchp->node[node]; - reap_alien(searchp, l3); + reap_alien(searchp, n); - drain_array(searchp, l3, cpu_cache_get(searchp), 0, node); + drain_array(searchp, n, cpu_cache_get(searchp), 0, node); /* * These are racy checks but it does not matter * if we skip one check or scan twice. */ - if (time_after(l3->next_reap, jiffies)) + if (time_after(n->next_reap, jiffies)) goto next; - l3->next_reap = jiffies + REAPTIMEOUT_LIST3; + n->next_reap = jiffies + REAPTIMEOUT_NODE; - drain_array(searchp, l3, l3->shared, 0, node); + drain_array(searchp, n, n->shared, 0, node); - if (l3->free_touched) - l3->free_touched = 0; + if (n->free_touched) + n->free_touched = 0; else { int freed; - freed = drain_freelist(searchp, l3, (l3->free_limit + + freed = drain_freelist(searchp, n, (n->free_limit + 5 * searchp->num - 1) / (5 * searchp->num)); STATS_ADD_REAPED(searchp, freed); } @@ -4271,13 +4082,13 @@ next: next_reap_node(); out: /* Set up the next iteration */ - schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_CPUC)); + schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_AC)); } #ifdef CONFIG_SLABINFO void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) { - struct slab *slabp; + struct page *page; unsigned long active_objs; unsigned long num_objs; unsigned long active_slabs = 0; @@ -4285,42 +4096,42 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) const char *name; char *error = NULL; int node; - struct kmem_list3 *l3; + struct kmem_cache_node *n; active_objs = 0; num_slabs = 0; for_each_online_node(node) { - l3 = cachep->nodelists[node]; - if (!l3) + n = cachep->node[node]; + if (!n) continue; check_irq_on(); - spin_lock_irq(&l3->list_lock); + spin_lock_irq(&n->list_lock); - list_for_each_entry(slabp, &l3->slabs_full, list) { - if (slabp->inuse != cachep->num && !error) + list_for_each_entry(page, &n->slabs_full, lru) { + if (page->active != cachep->num && !error) error = "slabs_full accounting error"; active_objs += cachep->num; active_slabs++; } - list_for_each_entry(slabp, &l3->slabs_partial, list) { - if (slabp->inuse == cachep->num && !error) - error = "slabs_partial inuse accounting error"; - if (!slabp->inuse && !error) - error = "slabs_partial/inuse accounting error"; - active_objs += slabp->inuse; + list_for_each_entry(page, &n->slabs_partial, lru) { + if (page->active == cachep->num && !error) + error = "slabs_partial accounting error"; + if (!page->active && !error) + error = "slabs_partial accounting error"; + active_objs += page->active; active_slabs++; } - list_for_each_entry(slabp, &l3->slabs_free, list) { - if (slabp->inuse && !error) - error = "slabs_free/inuse accounting error"; + list_for_each_entry(page, &n->slabs_free, lru) { + if (page->active && !error) + error = "slabs_free accounting error"; num_slabs++; } - free_objects += l3->free_objects; - if (l3->shared) - shared_avail += l3->shared->avail; + free_objects += n->free_objects; + if (n->shared) + shared_avail += n->shared->avail; - spin_unlock_irq(&l3->list_lock); + spin_unlock_irq(&n->list_lock); } num_slabs += active_slabs; num_objs = num_slabs * cachep->num; @@ -4346,7 +4157,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep) { #if STATS - { /* list3 stats */ + { /* node stats */ unsigned long high = cachep->high_mark; unsigned long allocs = cachep->num_allocations; unsigned long grown = cachep->grown; @@ -4465,15 +4276,18 @@ static inline int add_caller(unsigned long *n, unsigned long v) return 1; } -static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s) +static void handle_slab(unsigned long *n, struct kmem_cache *c, + struct page *page) { void *p; int i; + if (n[0] == n[1]) return; - for (i = 0, p = s->s_mem; i < c->num; i++, p += c->size) { - if (slab_bufctl(s)[i] != BUFCTL_ACTIVE) + for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) { + if (get_obj_status(page, i) != OBJECT_ACTIVE) continue; + if (!add_caller(n, (unsigned long)*dbg_userword(c, p))) return; } @@ -4498,10 +4312,10 @@ static void show_symbol(struct seq_file *m, unsigned long address) static int leaks_show(struct seq_file *m, void *p) { struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list); - struct slab *slabp; - struct kmem_list3 *l3; + struct page *page; + struct kmem_cache_node *n; const char *name; - unsigned long *n = m->private; + unsigned long *x = m->private; int node; int i; @@ -4512,63 +4326,53 @@ static int leaks_show(struct seq_file *m, void *p) /* OK, we can do it */ - n[1] = 0; + x[1] = 0; for_each_online_node(node) { - l3 = cachep->nodelists[node]; - if (!l3) + n = cachep->node[node]; + if (!n) continue; check_irq_on(); - spin_lock_irq(&l3->list_lock); + spin_lock_irq(&n->list_lock); - list_for_each_entry(slabp, &l3->slabs_full, list) - handle_slab(n, cachep, slabp); - list_for_each_entry(slabp, &l3->slabs_partial, list) - handle_slab(n, cachep, slabp); - spin_unlock_irq(&l3->list_lock); + list_for_each_entry(page, &n->slabs_full, lru) + handle_slab(x, cachep, page); + list_for_each_entry(page, &n->slabs_partial, lru) + handle_slab(x, cachep, page); + spin_unlock_irq(&n->list_lock); } name = cachep->name; - if (n[0] == n[1]) { + if (x[0] == x[1]) { /* Increase the buffer size */ mutex_unlock(&slab_mutex); - m->private = kzalloc(n[0] * 4 * sizeof(unsigned long), GFP_KERNEL); + m->private = kzalloc(x[0] * 4 * sizeof(unsigned long), GFP_KERNEL); if (!m->private) { /* Too bad, we are really out */ - m->private = n; + m->private = x; mutex_lock(&slab_mutex); return -ENOMEM; } - *(unsigned long *)m->private = n[0] * 2; - kfree(n); + *(unsigned long *)m->private = x[0] * 2; + kfree(x); mutex_lock(&slab_mutex); /* Now make sure this entry will be retried */ m->count = m->size; return 0; } - for (i = 0; i < n[1]; i++) { - seq_printf(m, "%s: %lu ", name, n[2*i+3]); - show_symbol(m, n[2*i+2]); + for (i = 0; i < x[1]; i++) { + seq_printf(m, "%s: %lu ", name, x[2*i+3]); + show_symbol(m, x[2*i+2]); seq_putc(m, '\n'); } return 0; } -static void *s_next(struct seq_file *m, void *p, loff_t *pos) -{ - return seq_list_next(p, &slab_caches, pos); -} - -static void s_stop(struct seq_file *m, void *p) -{ - mutex_unlock(&slab_mutex); -} - static const struct seq_operations slabstats_op = { .start = leaks_start, - .next = s_next, - .stop = s_stop, + .next = slab_next, + .stop = slab_stop, .show = leaks_show, }; diff --git a/mm/slab.h b/mm/slab.h index 34a98d64219..961a3fb1f5a 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -16,7 +16,7 @@ enum slab_state { DOWN, /* No slab functionality yet */ PARTIAL, /* SLUB: kmem_cache_node available */ PARTIAL_ARRAYCACHE, /* SLAB: kmalloc size for arraycache available */ - PARTIAL_L3, /* SLAB: kmalloc size for l3 struct available */ + PARTIAL_NODE, /* SLAB: kmalloc size for node struct available */ UP, /* Slab caches usable but not all extras yet */ FULL /* Everything is working */ }; @@ -35,6 +35,15 @@ extern struct kmem_cache *kmem_cache; unsigned long calculate_alignment(unsigned long flags, unsigned long align, unsigned long size); +#ifndef CONFIG_SLOB +/* Kmalloc array related functions */ +void create_kmalloc_caches(unsigned long); + +/* Find the kmalloc slab corresponding for a certain size */ +struct kmem_cache *kmalloc_slab(size_t, gfp_t); +#endif + + /* Functions provided by the slab allocators */ extern int __kmem_cache_create(struct kmem_cache *, unsigned long flags); @@ -46,12 +55,12 @@ extern void create_boot_cache(struct kmem_cache *, const char *name, struct mem_cgroup; #ifdef CONFIG_SLUB struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)); +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)); #else static inline struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)) +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { return NULL; } #endif @@ -82,6 +91,8 @@ __kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS) int __kmem_cache_shutdown(struct kmem_cache *); +int __kmem_cache_shrink(struct kmem_cache *); +void slab_kmem_cache_release(struct kmem_cache *); struct seq_file; struct file; @@ -110,28 +121,6 @@ static inline bool is_root_cache(struct kmem_cache *s) return !s->memcg_params || s->memcg_params->is_root_cache; } -static inline bool cache_match_memcg(struct kmem_cache *cachep, - struct mem_cgroup *memcg) -{ - return (is_root_cache(cachep) && !memcg) || - (cachep->memcg_params->memcg == memcg); -} - -static inline void memcg_bind_pages(struct kmem_cache *s, int order) -{ - if (!is_root_cache(s)) - atomic_add(1 << order, &s->memcg_params->nr_pages); -} - -static inline void memcg_release_pages(struct kmem_cache *s, int order) -{ - if (is_root_cache(s)) - return; - - if (atomic_sub_and_test((1 << order), &s->memcg_params->nr_pages)) - mem_cgroup_destroy_cache(s); -} - static inline bool slab_equal_or_root(struct kmem_cache *s, struct kmem_cache *p) { @@ -151,9 +140,36 @@ static inline const char *cache_name(struct kmem_cache *s) return s->name; } -static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx) +/* + * Note, we protect with RCU only the memcg_caches array, not per-memcg caches. + * That said the caller must assure the memcg's cache won't go away. Since once + * created a memcg's cache is destroyed only along with the root cache, it is + * true if we are going to allocate from the cache or hold a reference to the + * root cache by other means. Otherwise, we should hold either the slab_mutex + * or the memcg's slab_caches_mutex while calling this function and accessing + * the returned value. + */ +static inline struct kmem_cache * +cache_from_memcg_idx(struct kmem_cache *s, int idx) { - return s->memcg_params->memcg_caches[idx]; + struct kmem_cache *cachep; + struct memcg_cache_params *params; + + if (!s->memcg_params) + return NULL; + + rcu_read_lock(); + params = rcu_dereference(s->memcg_params); + cachep = params->memcg_caches[idx]; + rcu_read_unlock(); + + /* + * Make sure we will access the up-to-date value. The code updating + * memcg_caches issues a write barrier to match this (see + * memcg_register_cache()). + */ + smp_read_barrier_depends(); + return cachep; } static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) @@ -162,24 +178,29 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) return s; return s->memcg_params->root_cache; } -#else -static inline bool is_root_cache(struct kmem_cache *s) -{ - return true; -} -static inline bool cache_match_memcg(struct kmem_cache *cachep, - struct mem_cgroup *memcg) +static __always_inline int memcg_charge_slab(struct kmem_cache *s, + gfp_t gfp, int order) { - return true; + if (!memcg_kmem_enabled()) + return 0; + if (is_root_cache(s)) + return 0; + return __memcg_charge_slab(s, gfp, order); } -static inline void memcg_bind_pages(struct kmem_cache *s, int order) +static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) { + if (!memcg_kmem_enabled()) + return; + if (is_root_cache(s)) + return; + __memcg_uncharge_slab(s, order); } - -static inline void memcg_release_pages(struct kmem_cache *s, int order) +#else +static inline bool is_root_cache(struct kmem_cache *s) { + return true; } static inline bool slab_equal_or_root(struct kmem_cache *s, @@ -193,7 +214,8 @@ static inline const char *cache_name(struct kmem_cache *s) return s->name; } -static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx) +static inline struct kmem_cache * +cache_from_memcg_idx(struct kmem_cache *s, int idx) { return NULL; } @@ -202,6 +224,15 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) { return s; } + +static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order) +{ + return 0; +} + +static inline void memcg_uncharge_slab(struct kmem_cache *s, int order) +{ +} #endif static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) @@ -230,3 +261,38 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) return s; } #endif + + +/* + * The slab lists for all objects. + */ +struct kmem_cache_node { + spinlock_t list_lock; + +#ifdef CONFIG_SLAB + struct list_head slabs_partial; /* partial list first, better asm code */ + struct list_head slabs_full; + struct list_head slabs_free; + unsigned long free_objects; + unsigned int free_limit; + unsigned int colour_next; /* Per-node cache coloring */ + struct array_cache *shared; /* shared per node */ + struct array_cache **alien; /* on other nodes */ + unsigned long next_reap; /* updated without locking */ + int free_touched; /* updated without locking */ +#endif + +#ifdef CONFIG_SLUB + unsigned long nr_partial; + struct list_head partial; +#ifdef CONFIG_SLUB_DEBUG + atomic_long_t nr_slabs; + atomic_long_t total_objects; + struct list_head full; +#endif +#endif + +}; + +void *slab_next(struct seq_file *m, void *p, loff_t *pos); +void slab_stop(struct seq_file *m, void *p); diff --git a/mm/slab_common.c b/mm/slab_common.c index 3f3cd97d3fd..d31c4bacc6a 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -19,6 +19,7 @@ #include <asm/tlbflush.h> #include <asm/page.h> #include <linux/memcontrol.h> +#include <trace/events/kmem.h> #include "slab.h" @@ -28,8 +29,7 @@ DEFINE_MUTEX(slab_mutex); struct kmem_cache *kmem_cache; #ifdef CONFIG_DEBUG_VM -static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, - size_t size) +static int kmem_cache_sanity_check(const char *name, size_t size) { struct kmem_cache *s = NULL; @@ -55,27 +55,22 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, continue; } - /* - * For simplicity, we won't check this in the list of memcg - * caches. We have control over memcg naming, and if there - * aren't duplicates in the global list, there won't be any - * duplicates in the memcg lists as well. - */ - if (!memcg && !strcmp(s->name, name)) { +#if !defined(CONFIG_SLUB) + if (!strcmp(s->name, name)) { pr_err("%s (%s): Cache name already exists.\n", __func__, name); dump_stack(); s = NULL; return -EINVAL; } +#endif } WARN_ON(strchr(name, ' ')); /* It confuses parsers */ return 0; } #else -static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg, - const char *name, size_t size) +static inline int kmem_cache_sanity_check(const char *name, size_t size) { return 0; } @@ -136,6 +131,45 @@ unsigned long calculate_alignment(unsigned long flags, return ALIGN(align, sizeof(void *)); } +static struct kmem_cache * +do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *), + struct mem_cgroup *memcg, struct kmem_cache *root_cache) +{ + struct kmem_cache *s; + int err; + + err = -ENOMEM; + s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); + if (!s) + goto out; + + s->name = name; + s->object_size = object_size; + s->size = size; + s->align = align; + s->ctor = ctor; + + err = memcg_alloc_cache_params(memcg, s, root_cache); + if (err) + goto out_free_cache; + + err = __kmem_cache_create(s, flags); + if (err) + goto out_free_cache; + + s->refcount = 1; + list_add(&s->list, &slab_caches); +out: + if (err) + return ERR_PTR(err); + return s; + +out_free_cache: + memcg_free_cache_params(s); + kfree(s); + goto out; +} /* * kmem_cache_create - Create a cache. @@ -161,20 +195,22 @@ unsigned long calculate_alignment(unsigned long flags, * cacheline. This can be beneficial if you're counting cycles as closely * as davem. */ - struct kmem_cache * -kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *), - struct kmem_cache *parent_cache) +kmem_cache_create(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { - struct kmem_cache *s = NULL; - int err = 0; + struct kmem_cache *s; + char *cache_name; + int err; get_online_cpus(); + get_online_mems(); + mutex_lock(&slab_mutex); - if (!kmem_cache_sanity_check(memcg, name, size) == 0) - goto out_locked; + err = kmem_cache_sanity_check(name, size); + if (err) + goto out_unlock; /* * Some allocators will constraint the set of valid flags to a subset @@ -184,47 +220,31 @@ kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size, */ flags &= CACHE_CREATE_MASK; - s = __kmem_cache_alias(memcg, name, size, align, flags, ctor); + s = __kmem_cache_alias(name, size, align, flags, ctor); if (s) - goto out_locked; - - s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); - if (s) { - s->object_size = s->size = size; - s->align = calculate_alignment(flags, align, size); - s->ctor = ctor; - - if (memcg_register_cache(memcg, s, parent_cache)) { - kmem_cache_free(kmem_cache, s); - err = -ENOMEM; - goto out_locked; - } + goto out_unlock; - s->name = kstrdup(name, GFP_KERNEL); - if (!s->name) { - kmem_cache_free(kmem_cache, s); - err = -ENOMEM; - goto out_locked; - } - - err = __kmem_cache_create(s, flags); - if (!err) { - s->refcount = 1; - list_add(&s->list, &slab_caches); - memcg_cache_list_add(memcg, s); - } else { - kfree(s->name); - kmem_cache_free(kmem_cache, s); - } - } else + cache_name = kstrdup(name, GFP_KERNEL); + if (!cache_name) { err = -ENOMEM; + goto out_unlock; + } + + s = do_kmem_cache_create(cache_name, size, size, + calculate_alignment(flags, align, size), + flags, ctor, NULL, NULL); + if (IS_ERR(s)) { + err = PTR_ERR(s); + kfree(cache_name); + } -out_locked: +out_unlock: mutex_unlock(&slab_mutex); + + put_online_mems(); put_online_cpus(); if (err) { - if (flags & SLAB_PANIC) panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n", name, err); @@ -233,54 +253,148 @@ out_locked: name, err); dump_stack(); } - return NULL; } + return s; +} +EXPORT_SYMBOL(kmem_cache_create); + +#ifdef CONFIG_MEMCG_KMEM +/* + * memcg_create_kmem_cache - Create a cache for a memory cgroup. + * @memcg: The memory cgroup the new cache is for. + * @root_cache: The parent of the new cache. + * @memcg_name: The name of the memory cgroup (used for naming the new cache). + * + * This function attempts to create a kmem cache that will serve allocation + * requests going from @memcg to @root_cache. The new cache inherits properties + * from its parent. + */ +struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache, + const char *memcg_name) +{ + struct kmem_cache *s = NULL; + char *cache_name; + + get_online_cpus(); + get_online_mems(); + + mutex_lock(&slab_mutex); + + cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, + memcg_cache_id(memcg), memcg_name); + if (!cache_name) + goto out_unlock; + + s = do_kmem_cache_create(cache_name, root_cache->object_size, + root_cache->size, root_cache->align, + root_cache->flags, root_cache->ctor, + memcg, root_cache); + if (IS_ERR(s)) { + kfree(cache_name); + s = NULL; + } + +out_unlock: + mutex_unlock(&slab_mutex); + + put_online_mems(); + put_online_cpus(); return s; } -struct kmem_cache * -kmem_cache_create(const char *name, size_t size, size_t align, - unsigned long flags, void (*ctor)(void *)) +static int memcg_cleanup_cache_params(struct kmem_cache *s) +{ + int rc; + + if (!s->memcg_params || + !s->memcg_params->is_root_cache) + return 0; + + mutex_unlock(&slab_mutex); + rc = __memcg_cleanup_cache_params(s); + mutex_lock(&slab_mutex); + + return rc; +} +#else +static int memcg_cleanup_cache_params(struct kmem_cache *s) { - return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL); + return 0; } -EXPORT_SYMBOL(kmem_cache_create); +#endif /* CONFIG_MEMCG_KMEM */ -void kmem_cache_destroy(struct kmem_cache *s) +void slab_kmem_cache_release(struct kmem_cache *s) { - /* Destroy all the children caches if we aren't a memcg cache */ - kmem_cache_destroy_memcg_children(s); + kfree(s->name); + kmem_cache_free(kmem_cache, s); +} +void kmem_cache_destroy(struct kmem_cache *s) +{ get_online_cpus(); + get_online_mems(); + mutex_lock(&slab_mutex); + s->refcount--; - if (!s->refcount) { - list_del(&s->list); - - if (!__kmem_cache_shutdown(s)) { - mutex_unlock(&slab_mutex); - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); - - memcg_release_cache(s); - kfree(s->name); - kmem_cache_free(kmem_cache, s); - } else { - list_add(&s->list, &slab_caches); - mutex_unlock(&slab_mutex); - printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n", - s->name); - dump_stack(); - } - } else { - mutex_unlock(&slab_mutex); + if (s->refcount) + goto out_unlock; + + if (memcg_cleanup_cache_params(s) != 0) + goto out_unlock; + + if (__kmem_cache_shutdown(s) != 0) { + printk(KERN_ERR "kmem_cache_destroy %s: " + "Slab cache still has objects\n", s->name); + dump_stack(); + goto out_unlock; } + + list_del(&s->list); + + mutex_unlock(&slab_mutex); + if (s->flags & SLAB_DESTROY_BY_RCU) + rcu_barrier(); + + memcg_free_cache_params(s); +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_remove(s); +#else + slab_kmem_cache_release(s); +#endif + goto out; + +out_unlock: + mutex_unlock(&slab_mutex); +out: + put_online_mems(); put_online_cpus(); } EXPORT_SYMBOL(kmem_cache_destroy); +/** + * kmem_cache_shrink - Shrink a cache. + * @cachep: The cache to shrink. + * + * Releases as many slabs as possible for a cache. + * To help debugging, a zero exit status indicates all slabs were released. + */ +int kmem_cache_shrink(struct kmem_cache *cachep) +{ + int ret; + + get_online_cpus(); + get_online_mems(); + ret = __kmem_cache_shrink(cachep); + put_online_mems(); + put_online_cpus(); + return ret; +} +EXPORT_SYMBOL(kmem_cache_shrink); + int slab_is_available(void) { return slab_state >= UP; @@ -299,7 +413,7 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz err = __kmem_cache_create(s, flags); if (err) - panic("Creation of kmalloc slab %s size=%zd failed. Reason %d\n", + panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n", name, size, err); s->refcount = -1; /* Exempt from merging for now */ @@ -319,10 +433,218 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size, return s; } +struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +EXPORT_SYMBOL(kmalloc_caches); + +#ifdef CONFIG_ZONE_DMA +struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; +EXPORT_SYMBOL(kmalloc_dma_caches); +#endif + +/* + * Conversion table for small slabs sizes / 8 to the index in the + * kmalloc array. This is necessary for slabs < 192 since we have non power + * of two cache sizes there. The size of larger slabs can be determined using + * fls. + */ +static s8 size_index[24] = { + 3, /* 8 */ + 4, /* 16 */ + 5, /* 24 */ + 5, /* 32 */ + 6, /* 40 */ + 6, /* 48 */ + 6, /* 56 */ + 6, /* 64 */ + 1, /* 72 */ + 1, /* 80 */ + 1, /* 88 */ + 1, /* 96 */ + 7, /* 104 */ + 7, /* 112 */ + 7, /* 120 */ + 7, /* 128 */ + 2, /* 136 */ + 2, /* 144 */ + 2, /* 152 */ + 2, /* 160 */ + 2, /* 168 */ + 2, /* 176 */ + 2, /* 184 */ + 2 /* 192 */ +}; + +static inline int size_index_elem(size_t bytes) +{ + return (bytes - 1) / 8; +} + +/* + * Find the kmem_cache structure that serves a given size of + * allocation + */ +struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) +{ + int index; + + if (unlikely(size > KMALLOC_MAX_SIZE)) { + WARN_ON_ONCE(!(flags & __GFP_NOWARN)); + return NULL; + } + + if (size <= 192) { + if (!size) + return ZERO_SIZE_PTR; + + index = size_index[size_index_elem(size)]; + } else + index = fls(size - 1); + +#ifdef CONFIG_ZONE_DMA + if (unlikely((flags & GFP_DMA))) + return kmalloc_dma_caches[index]; + +#endif + return kmalloc_caches[index]; +} + +/* + * Create the kmalloc array. Some of the regular kmalloc arrays + * may already have been created because they were needed to + * enable allocations for slab creation. + */ +void __init create_kmalloc_caches(unsigned long flags) +{ + int i; + + /* + * Patch up the size_index table if we have strange large alignment + * requirements for the kmalloc array. This is only the case for + * MIPS it seems. The standard arches will not generate any code here. + * + * Largest permitted alignment is 256 bytes due to the way we + * handle the index determination for the smaller caches. + * + * Make sure that nothing crazy happens if someone starts tinkering + * around with ARCH_KMALLOC_MINALIGN + */ + BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 || + (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1))); + + for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) { + int elem = size_index_elem(i); + + if (elem >= ARRAY_SIZE(size_index)) + break; + size_index[elem] = KMALLOC_SHIFT_LOW; + } + + if (KMALLOC_MIN_SIZE >= 64) { + /* + * The 96 byte size cache is not used if the alignment + * is 64 byte. + */ + for (i = 64 + 8; i <= 96; i += 8) + size_index[size_index_elem(i)] = 7; + + } + + if (KMALLOC_MIN_SIZE >= 128) { + /* + * The 192 byte sized cache is not used if the alignment + * is 128 byte. Redirect kmalloc to use the 256 byte cache + * instead. + */ + for (i = 128 + 8; i <= 192; i += 8) + size_index[size_index_elem(i)] = 8; + } + for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { + if (!kmalloc_caches[i]) { + kmalloc_caches[i] = create_kmalloc_cache(NULL, + 1 << i, flags); + } + + /* + * Caches that are not of the two-to-the-power-of size. + * These have to be created immediately after the + * earlier power of two caches + */ + if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6) + kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags); + + if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7) + kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags); + } + + /* Kmalloc array is now usable */ + slab_state = UP; + + for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { + struct kmem_cache *s = kmalloc_caches[i]; + char *n; + + if (s) { + n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i)); + + BUG_ON(!n); + s->name = n; + } + } + +#ifdef CONFIG_ZONE_DMA + for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { + struct kmem_cache *s = kmalloc_caches[i]; + + if (s) { + int size = kmalloc_size(i); + char *n = kasprintf(GFP_NOWAIT, + "dma-kmalloc-%d", size); + + BUG_ON(!n); + kmalloc_dma_caches[i] = create_kmalloc_cache(n, + size, SLAB_CACHE_DMA | flags); + } + } +#endif +} #endif /* !CONFIG_SLOB */ +/* + * To avoid unnecessary overhead, we pass through large allocation requests + * directly to the page allocator. We use __GFP_COMP, because we will need to + * know the allocation order to free the pages properly in kfree. + */ +void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) +{ + void *ret; + struct page *page; + + flags |= __GFP_COMP; + page = alloc_kmem_pages(flags, order); + ret = page ? page_address(page) : NULL; + kmemleak_alloc(ret, size, 1, flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_order); + +#ifdef CONFIG_TRACING +void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +{ + void *ret = kmalloc_order(size, flags, order); + trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_order_trace); +#endif #ifdef CONFIG_SLABINFO + +#ifdef CONFIG_SLAB +#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR) +#else +#define SLABINFO_RIGHTS S_IRUSR +#endif + void print_slabinfo_header(struct seq_file *m) { /* @@ -357,12 +679,12 @@ static void *s_start(struct seq_file *m, loff_t *pos) return seq_list_start(&slab_caches, *pos); } -static void *s_next(struct seq_file *m, void *p, loff_t *pos) +void *slab_next(struct seq_file *m, void *p, loff_t *pos) { return seq_list_next(p, &slab_caches, pos); } -static void s_stop(struct seq_file *m, void *p) +void slab_stop(struct seq_file *m, void *p) { mutex_unlock(&slab_mutex); } @@ -378,7 +700,7 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info) return; for_each_memcg_cache_index(i) { - c = cache_from_memcg(s, i); + c = cache_from_memcg_idx(s, i); if (!c) continue; @@ -439,8 +761,8 @@ static int s_show(struct seq_file *m, void *p) */ static const struct seq_operations slabinfo_op = { .start = s_start, - .next = s_next, - .stop = s_stop, + .next = slab_next, + .stop = slab_stop, .show = s_show, }; @@ -459,7 +781,8 @@ static const struct file_operations proc_slabinfo_operations = { static int __init slab_proc_init(void) { - proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations); + proc_create("slabinfo", SLABINFO_RIGHTS, NULL, + &proc_slabinfo_operations); return 0; } module_init(slab_proc_init); diff --git a/mm/slob.c b/mm/slob.c index a99fdf7a090..21980e0f39a 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -111,18 +111,18 @@ static inline int slob_page_free(struct page *sp) static void set_slob_page_free(struct page *sp, struct list_head *list) { - list_add(&sp->list, list); + list_add(&sp->lru, list); __SetPageSlobFree(sp); } static inline void clear_slob_page_free(struct page *sp) { - list_del(&sp->list); + list_del(&sp->lru); __ClearPageSlobFree(sp); } #define SLOB_UNIT sizeof(slob_t) -#define SLOB_UNITS(size) (((size) + SLOB_UNIT - 1)/SLOB_UNIT) +#define SLOB_UNITS(size) DIV_ROUND_UP(size, SLOB_UNIT) /* * struct slob_rcu is inserted at the tail of allocated slob blocks, which @@ -282,7 +282,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) spin_lock_irqsave(&slob_lock, flags); /* Iterate through each partially free page, try to find room */ - list_for_each_entry(sp, slob_list, list) { + list_for_each_entry(sp, slob_list, lru) { #ifdef CONFIG_NUMA /* * If there's a node specification, search for a partial @@ -296,7 +296,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) continue; /* Attempt to alloc */ - prev = sp->list.prev; + prev = sp->lru.prev; b = slob_page_alloc(sp, size, align); if (!b) continue; @@ -322,7 +322,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) spin_lock_irqsave(&slob_lock, flags); sp->units = SLOB_UNITS(PAGE_SIZE); sp->freelist = b; - INIT_LIST_HEAD(&sp->list); + INIT_LIST_HEAD(&sp->lru); set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE)); set_slob_page_free(sp, slob_list); b = slob_page_alloc(sp, size, align); @@ -360,7 +360,7 @@ static void slob_free(void *block, int size) clear_slob_page_free(sp); spin_unlock_irqrestore(&slob_lock, flags); __ClearPageSlab(sp); - reset_page_mapcount(sp); + page_mapcount_reset(sp); slob_free_pages(b, 0); return; } @@ -462,11 +462,11 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) return ret; } -void *__kmalloc_node(size_t size, gfp_t gfp, int node) +void *__kmalloc(size_t size, gfp_t gfp) { - return __do_kmalloc_node(size, gfp, node, _RET_IP_); + return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, _RET_IP_); } -EXPORT_SYMBOL(__kmalloc_node); +EXPORT_SYMBOL(__kmalloc); #ifdef CONFIG_TRACING void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller) @@ -534,7 +534,7 @@ int __kmem_cache_create(struct kmem_cache *c, unsigned long flags) return 0; } -void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) +void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) { void *b; @@ -554,13 +554,33 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) flags, node); } - if (c->ctor) + if (b && c->ctor) c->ctor(b); kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags); return b; } +EXPORT_SYMBOL(slob_alloc_node); + +void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) +{ + return slob_alloc_node(cachep, flags, NUMA_NO_NODE); +} +EXPORT_SYMBOL(kmem_cache_alloc); + +#ifdef CONFIG_NUMA +void *__kmalloc_node(size_t size, gfp_t gfp, int node) +{ + return __do_kmalloc_node(size, gfp, node, _RET_IP_); +} +EXPORT_SYMBOL(__kmalloc_node); + +void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t gfp, int node) +{ + return slob_alloc_node(cachep, gfp, node); +} EXPORT_SYMBOL(kmem_cache_alloc_node); +#endif static void __kmem_cache_free(void *b, int size) { @@ -600,11 +620,10 @@ int __kmem_cache_shutdown(struct kmem_cache *c) return 0; } -int kmem_cache_shrink(struct kmem_cache *d) +int __kmem_cache_shrink(struct kmem_cache *d) { return 0; } -EXPORT_SYMBOL(kmem_cache_shrink); struct kmem_cache kmem_cache_boot = { .name = "kmem_cache", diff --git a/mm/slub.c b/mm/slub.c index ba2ca53f6c3..73004808537 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include "slab.h" #include <linux/proc_fs.h> +#include <linux/notifier.h> #include <linux/seq_file.h> #include <linux/kmemcheck.h> #include <linux/cpu.h> @@ -122,6 +123,15 @@ static inline int kmem_cache_debug(struct kmem_cache *s) #endif } +static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) +{ +#ifdef CONFIG_SLUB_CPU_PARTIAL + return !kmem_cache_debug(s); +#else + return false; +#endif +} + /* * Issues still to be resolved: * @@ -145,7 +155,7 @@ static inline int kmem_cache_debug(struct kmem_cache *s) /* * Maximum number of desirable partial slabs. * The existence of more partial slabs makes kmem_cache_shrink - * sort the partial list by the number of objects in the. + * sort the partial list by the number of objects in use. */ #define MAX_PARTIAL 10 @@ -200,21 +210,22 @@ enum track_item { TRACK_ALLOC, TRACK_FREE }; #ifdef CONFIG_SYSFS static int sysfs_slab_add(struct kmem_cache *); static int sysfs_slab_alias(struct kmem_cache *, const char *); -static void sysfs_slab_remove(struct kmem_cache *); static void memcg_propagate_slab_attrs(struct kmem_cache *s); #else static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; } static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p) { return 0; } -static inline void sysfs_slab_remove(struct kmem_cache *s) { } - static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { } #endif static inline void stat(const struct kmem_cache *s, enum stat_item si) { #ifdef CONFIG_SLUB_STATS - __this_cpu_inc(s->cpu_slab->stat[si]); + /* + * The rmw is racy on a preemptible kernel but this is acceptable, so + * avoid this_cpu_add()'s irq-disable overhead. + */ + raw_cpu_inc(s->cpu_slab->stat[si]); #endif } @@ -345,6 +356,21 @@ static __always_inline void slab_unlock(struct page *page) __bit_spin_unlock(PG_locked, &page->flags); } +static inline void set_page_slub_counters(struct page *page, unsigned long counters_new) +{ + struct page tmp; + tmp.counters = counters_new; + /* + * page->counters can cover frozen/inuse/objects as well + * as page->_count. If we assign to ->counters directly + * we run the risk of losing updates to page->_count, so + * be careful and only assign to the fields we need. + */ + page->frozen = tmp.frozen; + page->inuse = tmp.inuse; + page->objects = tmp.objects; +} + /* Interrupts must be disabled (for the fallback code to work right) */ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page, void *freelist_old, unsigned long counters_old, @@ -363,9 +389,10 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page #endif { slab_lock(page); - if (page->freelist == freelist_old && page->counters == counters_old) { + if (page->freelist == freelist_old && + page->counters == counters_old) { page->freelist = freelist_new; - page->counters = counters_new; + set_page_slub_counters(page, counters_new); slab_unlock(page); return 1; } @@ -376,7 +403,7 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page stat(s, CMPXCHG_DOUBLE_FAIL); #ifdef SLUB_DEBUG_CMPXCHG - printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name); + pr_info("%s %s: cmpxchg double redo ", n, s->name); #endif return 0; @@ -401,9 +428,10 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, local_irq_save(flags); slab_lock(page); - if (page->freelist == freelist_old && page->counters == counters_old) { + if (page->freelist == freelist_old && + page->counters == counters_old) { page->freelist = freelist_new; - page->counters = counters_new; + set_page_slub_counters(page, counters_new); slab_unlock(page); local_irq_restore(flags); return 1; @@ -416,7 +444,7 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, stat(s, CMPXCHG_DOUBLE_FAIL); #ifdef SLUB_DEBUG_CMPXCHG - printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name); + pr_info("%s %s: cmpxchg double redo ", n, s->name); #endif return 0; @@ -518,14 +546,14 @@ static void print_track(const char *s, struct track *t) if (!t->addr) return; - printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n", - s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid); + pr_err("INFO: %s in %pS age=%lu cpu=%u pid=%d\n", + s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid); #ifdef CONFIG_STACKTRACE { int i; for (i = 0; i < TRACK_ADDRS_COUNT; i++) if (t->addrs[i]) - printk(KERN_ERR "\t%pS\n", (void *)t->addrs[i]); + pr_err("\t%pS\n", (void *)t->addrs[i]); else break; } @@ -543,37 +571,37 @@ static void print_tracking(struct kmem_cache *s, void *object) static void print_page_info(struct page *page) { - printk(KERN_ERR "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n", - page, page->objects, page->inuse, page->freelist, page->flags); + pr_err("INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n", + page, page->objects, page->inuse, page->freelist, page->flags); } static void slab_bug(struct kmem_cache *s, char *fmt, ...) { + struct va_format vaf; va_list args; - char buf[100]; va_start(args, fmt); - vsnprintf(buf, sizeof(buf), fmt, args); - va_end(args); - printk(KERN_ERR "========================================" - "=====================================\n"); - printk(KERN_ERR "BUG %s (%s): %s\n", s->name, print_tainted(), buf); - printk(KERN_ERR "----------------------------------------" - "-------------------------------------\n\n"); + vaf.fmt = fmt; + vaf.va = &args; + pr_err("=============================================================================\n"); + pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf); + pr_err("-----------------------------------------------------------------------------\n\n"); - add_taint(TAINT_BAD_PAGE); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + va_end(args); } static void slab_fix(struct kmem_cache *s, char *fmt, ...) { + struct va_format vaf; va_list args; - char buf[100]; va_start(args, fmt); - vsnprintf(buf, sizeof(buf), fmt, args); + vaf.fmt = fmt; + vaf.va = &args; + pr_err("FIX %s: %pV\n", s->name, &vaf); va_end(args); - printk(KERN_ERR "FIX %s: %s\n", s->name, buf); } static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) @@ -585,8 +613,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) print_page_info(page); - printk(KERN_ERR "INFO: Object 0x%p @offset=%tu fp=0x%p\n\n", - p, p - addr, get_freepointer(s, p)); + pr_err("INFO: Object 0x%p @offset=%tu fp=0x%p\n\n", + p, p - addr, get_freepointer(s, p)); if (p > addr + 16) print_section("Bytes b4 ", p - 16, 16); @@ -619,7 +647,8 @@ static void object_err(struct kmem_cache *s, struct page *page, print_trailer(s, page, object); } -static void slab_err(struct kmem_cache *s, struct page *page, const char *fmt, ...) +static void slab_err(struct kmem_cache *s, struct page *page, + const char *fmt, ...) { va_list args; char buf[100]; @@ -668,7 +697,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, end--; slab_bug(s, "%s overwritten", what); - printk(KERN_ERR "INFO: 0x%p-0x%p. First byte 0x%x instead of 0x%x\n", + pr_err("INFO: 0x%p-0x%p. First byte 0x%x instead of 0x%x\n", fault, end - 1, fault[0], value); print_trailer(s, page, object); @@ -778,7 +807,8 @@ static int check_object(struct kmem_cache *s, struct page *page, } else { if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) { check_bytes_and_report(s, page, p, "Alignment padding", - endobject, POISON_INUSE, s->inuse - s->object_size); + endobject, POISON_INUSE, + s->inuse - s->object_size); } } @@ -863,7 +893,6 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search) object_err(s, page, object, "Freechain corrupt"); set_freepointer(s, object, NULL); - break; } else { slab_err(s, page, "Freepointer corrupt"); page->freelist = NULL; @@ -901,14 +930,15 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, int alloc) { if (s->flags & SLAB_TRACE) { - printk(KERN_INFO "TRACE %s %s 0x%p inuse=%d fp=0x%p\n", + pr_info("TRACE %s %s 0x%p inuse=%d fp=0x%p\n", s->name, alloc ? "alloc" : "free", object, page->inuse, page->freelist); if (!alloc) - print_section("Object ", (void *)object, s->object_size); + print_section("Object ", (void *)object, + s->object_size); dump_stack(); } @@ -918,6 +948,16 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, * Hooks for other subsystems that check memory allocations. In a typical * production configuration these hooks all should produce no code at all. */ +static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags) +{ + kmemleak_alloc(ptr, size, 1, flags); +} + +static inline void kfree_hook(const void *x) +{ + kmemleak_free(x); +} + static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags) { flags &= gfp_allowed_mask; @@ -927,7 +967,8 @@ static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags) return should_failslab(s->object_size, flags, s->flags); } -static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object) +static inline void slab_post_alloc_hook(struct kmem_cache *s, + gfp_t flags, void *object) { flags &= gfp_allowed_mask; kmemcheck_slab_alloc(s, flags, object, slab_ksize(s)); @@ -939,7 +980,7 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) kmemleak_free_recursive(x, s->flags); /* - * Trouble is that we may no longer disable interupts in the fast path + * Trouble is that we may no longer disable interrupts in the fast path * So in order to make the debug calls that expect irqs to be * disabled we need to disable interrupts temporarily. */ @@ -959,8 +1000,6 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) /* * Tracking of fully allocated slabs for debugging purposes. - * - * list_lock must be held. */ static void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) @@ -968,17 +1007,16 @@ static void add_full(struct kmem_cache *s, if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_add(&page->lru, &n->full); } -/* - * list_lock must be held. - */ -static void remove_full(struct kmem_cache *s, struct page *page) +static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_del(&page->lru); } @@ -1005,7 +1043,7 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects) * dilemma by deferring the increment of the count during * bootstrap (see early_kmem_cache_node_alloc). */ - if (n) { + if (likely(n)) { atomic_long_inc(&n->nr_slabs); atomic_long_add(objects, &n->total_objects); } @@ -1029,7 +1067,8 @@ static void setup_object_debug(struct kmem_cache *s, struct page *page, init_tracking(s, object); } -static noinline int alloc_debug_processing(struct kmem_cache *s, struct page *page, +static noinline int alloc_debug_processing(struct kmem_cache *s, + struct page *page, void *object, unsigned long addr) { if (!check_slab(s, page)) @@ -1094,9 +1133,8 @@ static noinline struct kmem_cache_node *free_debug_processing( slab_err(s, page, "Attempt to free object(0x%p) " "outside of slab", object); } else if (!page->slab_cache) { - printk(KERN_ERR - "SLUB <none>: no slab for object 0x%p.\n", - object); + pr_err("SLUB <none>: no slab for object 0x%p.\n", + object); dump_stack(); } else object_err(s, page, object, @@ -1179,8 +1217,8 @@ static int __init setup_slub_debug(char *str) slub_debug |= SLAB_FAILSLAB; break; default: - printk(KERN_ERR "slub_debug option '%c' " - "unknown. skipped\n", *str); + pr_err("slub_debug option '%c' unknown. skipped\n", + *str); } } @@ -1200,8 +1238,8 @@ static unsigned long kmem_cache_flags(unsigned long object_size, /* * Enable debugging if selected on the kernel commandline. */ - if (slub_debug && (!slub_debug_slabs || - !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))) + if (slub_debug && (!slub_debug_slabs || (name && + !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))) flags |= slub_debug; return flags; @@ -1223,7 +1261,8 @@ static inline int check_object(struct kmem_cache *s, struct page *page, void *object, u8 val) { return 1; } static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) {} -static inline void remove_full(struct kmem_cache *s, struct page *page) {} +static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, + struct page *page) {} static inline unsigned long kmem_cache_flags(unsigned long object_size, unsigned long flags, const char *name, void (*ctor)(void *)) @@ -1243,30 +1282,56 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) {} +static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags) +{ + kmemleak_alloc(ptr, size, 1, flags); +} + +static inline void kfree_hook(const void *x) +{ + kmemleak_free(x); +} + static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags) { return 0; } static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, - void *object) {} + void *object) +{ + kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, + flags & gfp_allowed_mask); +} -static inline void slab_free_hook(struct kmem_cache *s, void *x) {} +static inline void slab_free_hook(struct kmem_cache *s, void *x) +{ + kmemleak_free_recursive(x, s->flags); +} #endif /* CONFIG_SLUB_DEBUG */ /* * Slab allocation and freeing */ -static inline struct page *alloc_slab_page(gfp_t flags, int node, - struct kmem_cache_order_objects oo) +static inline struct page *alloc_slab_page(struct kmem_cache *s, + gfp_t flags, int node, struct kmem_cache_order_objects oo) { + struct page *page; int order = oo_order(oo); flags |= __GFP_NOTRACK; + if (memcg_charge_slab(s, flags, order)) + return NULL; + if (node == NUMA_NO_NODE) - return alloc_pages(flags, order); + page = alloc_pages(flags, order); else - return alloc_pages_exact_node(node, flags, order); + page = alloc_pages_exact_node(node, flags, order); + + if (!page) + memcg_uncharge_slab(s, order); + + return page; } static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -1288,14 +1353,15 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) */ alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; - page = alloc_slab_page(alloc_gfp, node, oo); + page = alloc_slab_page(s, alloc_gfp, node, oo); if (unlikely(!page)) { oo = s->min; + alloc_gfp = flags; /* * Allocation may have failed due to fragmentation. * Try a lower order alloc if possible */ - page = alloc_slab_page(flags, node, oo); + page = alloc_slab_page(s, alloc_gfp, node, oo); if (page) stat(s, ORDER_FALLBACK); @@ -1305,7 +1371,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { int pages = 1 << oo_order(oo); - kmemcheck_alloc_shadow(page, oo_order(oo), flags, node); + kmemcheck_alloc_shadow(page, oo_order(oo), alloc_gfp, node); /* * Objects from caches that have a constructor don't get @@ -1356,7 +1422,6 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) order = compound_order(page); inc_slabs_node(s, page_to_nid(page), page->objects); - memcg_bind_pages(s, order); page->slab_cache = s; __SetPageSlab(page); if (page->pfmemalloc) @@ -1407,11 +1472,11 @@ static void __free_slab(struct kmem_cache *s, struct page *page) __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); - memcg_release_pages(s, order); - reset_page_mapcount(page); + page_mapcount_reset(page); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += pages; - __free_memcg_kmem_pages(page, order); + __free_pages(page, order); + memcg_uncharge_slab(s, order); } #define need_reserve_slab_rcu \ @@ -1460,11 +1525,9 @@ static void discard_slab(struct kmem_cache *s, struct page *page) /* * Management of partially allocated slabs. - * - * list_lock must be held. */ -static inline void add_partial(struct kmem_cache_node *n, - struct page *page, int tail) +static inline void +__add_partial(struct kmem_cache_node *n, struct page *page, int tail) { n->nr_partial++; if (tail == DEACTIVATE_TO_TAIL) @@ -1473,32 +1536,43 @@ static inline void add_partial(struct kmem_cache_node *n, list_add(&page->lru, &n->partial); } -/* - * list_lock must be held. - */ -static inline void remove_partial(struct kmem_cache_node *n, - struct page *page) +static inline void add_partial(struct kmem_cache_node *n, + struct page *page, int tail) +{ + lockdep_assert_held(&n->list_lock); + __add_partial(n, page, tail); +} + +static inline void +__remove_partial(struct kmem_cache_node *n, struct page *page) { list_del(&page->lru); n->nr_partial--; } +static inline void remove_partial(struct kmem_cache_node *n, + struct page *page) +{ + lockdep_assert_held(&n->list_lock); + __remove_partial(n, page); +} + /* * Remove slab from the partial list, freeze it and * return the pointer to the freelist. * * Returns a list of objects or NULL if it fails. - * - * Must hold list_lock since we modify the partial list. */ static inline void *acquire_slab(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page, - int mode) + int mode, int *objects) { void *freelist; unsigned long counters; struct page new; + lockdep_assert_held(&n->list_lock); + /* * Zap the freelist and set the frozen bit. * The old freelist is the list of objects for the @@ -1507,6 +1581,7 @@ static inline void *acquire_slab(struct kmem_cache *s, freelist = page->freelist; counters = page->counters; new.counters = counters; + *objects = new.objects - new.inuse; if (mode) { new.inuse = page->objects; new.freelist = NULL; @@ -1528,7 +1603,7 @@ static inline void *acquire_slab(struct kmem_cache *s, return freelist; } -static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); +static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags); /* @@ -1539,6 +1614,8 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, { struct page *page, *page2; void *object = NULL; + int available = 0; + int objects; /* * Racy check. If we mistakenly see no partial slabs then we @@ -1552,25 +1629,25 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, spin_lock(&n->list_lock); list_for_each_entry_safe(page, page2, &n->partial, lru) { void *t; - int available; if (!pfmemalloc_match(page, flags)) continue; - t = acquire_slab(s, n, page, object == NULL); + t = acquire_slab(s, n, page, object == NULL, &objects); if (!t) break; + available += objects; if (!object) { c->page = page; stat(s, ALLOC_FROM_PARTIAL); object = t; - available = page->objects - page->inuse; } else { - available = put_cpu_partial(s, page, 0); + put_cpu_partial(s, page, 0); stat(s, CPU_PARTIAL_NODE); } - if (kmem_cache_debug(s) || available > s->cpu_partial / 2) + if (!kmem_cache_has_cpu_partial(s) + || available > s->cpu_partial / 2) break; } @@ -1615,8 +1692,8 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, return NULL; do { - cpuset_mems_cookie = get_mems_allowed(); - zonelist = node_zonelist(slab_node(), flags); + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist = node_zonelist(mempolicy_slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1627,19 +1704,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, object = get_partial_node(s, n, c, flags); if (object) { /* - * Return the object even if - * put_mems_allowed indicated that - * the cpuset mems_allowed was - * updated in parallel. It's a - * harmless race between the alloc - * and the cpuset update. + * Don't check read_mems_allowed_retry() + * here - if mems_allowed was updated in + * parallel, that was a harmless race + * between allocation and the cpuset + * update */ - put_mems_allowed(cpuset_mems_cookie); return object; } } } - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); #endif return NULL; } @@ -1651,7 +1726,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, struct kmem_cache_cpu *c) { void *object; - int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node; + int searchnode = (node == NUMA_NO_NODE) ? numa_mem_id() : node; object = get_partial_node(s, get_node(s, searchnode), c, flags); if (object || node != NUMA_NO_NODE) @@ -1701,19 +1776,19 @@ static inline void note_cmpxchg_failure(const char *n, #ifdef SLUB_DEBUG_CMPXCHG unsigned long actual_tid = __this_cpu_read(s->cpu_slab->tid); - printk(KERN_INFO "%s %s: cmpxchg redo ", n, s->name); + pr_info("%s %s: cmpxchg redo ", n, s->name); #ifdef CONFIG_PREEMPT if (tid_to_cpu(tid) != tid_to_cpu(actual_tid)) - printk("due to cpu change %d -> %d\n", + pr_warn("due to cpu change %d -> %d\n", tid_to_cpu(tid), tid_to_cpu(actual_tid)); else #endif if (tid_to_event(tid) != tid_to_event(actual_tid)) - printk("due to cpu running other code. Event %ld->%ld\n", + pr_warn("due to cpu running other code. Event %ld->%ld\n", tid_to_event(tid), tid_to_event(actual_tid)); else - printk("for unknown reason: actual=%lx was=%lx target=%lx\n", + pr_warn("for unknown reason: actual=%lx was=%lx target=%lx\n", actual_tid, tid, next_tid(tid)); #endif stat(s, CMPXCHG_DOUBLE_CPU_FAIL); @@ -1730,7 +1805,8 @@ static void init_kmem_cache_cpus(struct kmem_cache *s) /* * Remove the cpu slab */ -static void deactivate_slab(struct kmem_cache *s, struct page *page, void *freelist) +static void deactivate_slab(struct kmem_cache *s, struct page *page, + void *freelist) { enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE }; struct kmem_cache_node *n = get_node(s, page_to_nid(page)); @@ -1805,7 +1881,7 @@ redo: new.frozen = 0; - if (!new.inuse && n->nr_partial > s->min_partial) + if (!new.inuse && n->nr_partial >= s->min_partial) m = M_FREE; else if (new.freelist) { m = M_PARTIAL; @@ -1839,7 +1915,7 @@ redo: else if (l == M_FULL) - remove_full(s, page); + remove_full(s, n, page); if (m == M_PARTIAL) { @@ -1881,6 +1957,7 @@ redo: static void unfreeze_partials(struct kmem_cache *s, struct kmem_cache_cpu *c) { +#ifdef CONFIG_SLUB_CPU_PARTIAL struct kmem_cache_node *n = NULL, *n2 = NULL; struct page *page, *discard_page = NULL; @@ -1915,7 +1992,7 @@ static void unfreeze_partials(struct kmem_cache *s, new.freelist, new.counters, "unfreezing slab")); - if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) { + if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) { page->next = discard_page; discard_page = page; } else { @@ -1935,6 +2012,7 @@ static void unfreeze_partials(struct kmem_cache *s, discard_slab(s, page); stat(s, FREE_SLAB); } +#endif } /* @@ -1946,8 +2024,9 @@ static void unfreeze_partials(struct kmem_cache *s, * If we did not find a slot then simply move all the partials to the * per node partial list. */ -static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) +static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) { +#ifdef CONFIG_SLUB_CPU_PARTIAL struct page *oldpage; int pages; int pobjects; @@ -1983,8 +2062,9 @@ static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) page->pobjects = pobjects; page->next = oldpage; - } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage); - return pobjects; + } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) + != oldpage); +#endif } static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) @@ -2041,17 +2121,25 @@ static void flush_all(struct kmem_cache *s) static inline int node_match(struct page *page, int node) { #ifdef CONFIG_NUMA - if (node != NUMA_NO_NODE && page_to_nid(page) != node) + if (!page || (node != NUMA_NO_NODE && page_to_nid(page) != node)) return 0; #endif return 1; } +#ifdef CONFIG_SLUB_DEBUG static int count_free(struct page *page) { return page->objects - page->inuse; } +static inline unsigned long node_nr_objs(struct kmem_cache_node *n) +{ + return atomic_long_read(&n->total_objects); +} +#endif /* CONFIG_SLUB_DEBUG */ + +#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS) static unsigned long count_partial(struct kmem_cache_node *n, int (*get_count)(struct page *)) { @@ -2065,31 +2153,28 @@ static unsigned long count_partial(struct kmem_cache_node *n, spin_unlock_irqrestore(&n->list_lock, flags); return x; } - -static inline unsigned long node_nr_objs(struct kmem_cache_node *n) -{ -#ifdef CONFIG_SLUB_DEBUG - return atomic_long_read(&n->total_objects); -#else - return 0; -#endif -} +#endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ static noinline void slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) { +#ifdef CONFIG_SLUB_DEBUG + static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); int node; - printk(KERN_WARNING - "SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n", + if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slub_oom_rs)) + return; + + pr_warn("SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n", nid, gfpflags); - printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, " - "default order: %d, min order: %d\n", s->name, s->object_size, - s->size, oo_order(s->oo), oo_order(s->min)); + pr_warn(" cache: %s, object size: %d, buffer size: %d, default order: %d, min order: %d\n", + s->name, s->object_size, s->size, oo_order(s->oo), + oo_order(s->min)); if (oo_order(s->min) > get_order(s->object_size)) - printk(KERN_WARNING " %s debugging increased min order, use " - "slub_debug=O to disable.\n", s->name); + pr_warn(" %s debugging increased min order, use slub_debug=O to disable.\n", + s->name); for_each_online_node(node) { struct kmem_cache_node *n = get_node(s, node); @@ -2104,10 +2189,10 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) nr_slabs = node_nr_slabs(n); nr_objs = node_nr_objs(n); - printk(KERN_WARNING - " node %d: slabs: %ld, objs: %ld, free: %ld\n", + pr_warn(" node %d: slabs: %ld, objs: %ld, free: %ld\n", node, nr_slabs, nr_objs, nr_free); } +#endif } static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, @@ -2124,7 +2209,7 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, page = new_slab(s, flags, node); if (page) { - c = __this_cpu_ptr(s->cpu_slab); + c = raw_cpu_ptr(s->cpu_slab); if (c->page) flush_slab(s, c); @@ -2153,8 +2238,8 @@ static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags) } /* - * Check the page->freelist of a page and either transfer the freelist to the per cpu freelist - * or deactivate the page. + * Check the page->freelist of a page and either transfer the freelist to the + * per cpu freelist or deactivate the page. * * The page is still frozen if the return value is not NULL. * @@ -2249,8 +2334,6 @@ redo: if (freelist) goto load_freelist; - stat(s, ALLOC_SLOWPATH); - freelist = get_freelist(s, page); if (!freelist) { @@ -2286,9 +2369,7 @@ new_slab: freelist = new_slab_objects(s, gfpflags, node, &c); if (unlikely(!freelist)) { - if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) - slab_out_of_memory(s, gfpflags, node); - + slab_out_of_memory(s, gfpflags, node); local_irq_restore(flags); return NULL; } @@ -2298,7 +2379,8 @@ new_slab: goto load_freelist; /* Only entered in the debug case */ - if (kmem_cache_debug(s) && !alloc_debug_processing(s, page, freelist, addr)) + if (kmem_cache_debug(s) && + !alloc_debug_processing(s, page, freelist, addr)) goto new_slab; /* Slab failed checks. Next slab needed */ deactivate_slab(s, page, get_freepointer(s, freelist)); @@ -2331,14 +2413,19 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, s = memcg_kmem_get_cache(s, gfpflags); redo: - /* * Must read kmem_cache cpu data via this cpu ptr. Preemption is * enabled. We may switch back and forth between cpus while * reading from one cpu area. That does not matter as long * as we end up on the original cpu again when doing the cmpxchg. + * + * Preemption is disabled for the retrieval of the tid because that + * must occur from the current processor. We cannot allow rescheduling + * on a different processor between the determination of the pointer + * and the retrieval of the tid. */ - c = __this_cpu_ptr(s->cpu_slab); + preempt_disable(); + c = this_cpu_ptr(s->cpu_slab); /* * The transaction ids are globally unique per cpu and per operation on @@ -2347,27 +2434,29 @@ redo: * linked list in between. */ tid = c->tid; - barrier(); + preempt_enable(); object = c->freelist; page = c->page; - if (unlikely(!object || !node_match(page, node))) + if (unlikely(!object || !node_match(page, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); - - else { + stat(s, ALLOC_SLOWPATH); + } else { void *next_object = get_freepointer_safe(s, object); /* * The cmpxchg will only match if there was no additional * operation and if we are on the right processor. * - * The cmpxchg does the following atomically (without lock semantics!) + * The cmpxchg does the following atomically (without lock + * semantics!) * 1. Relocate first pointer to the current per cpu area. * 2. Verify that tid and freelist have not been changed * 3. If they were not changed replace tid and freelist * - * Since this is without lock semantics the protection is only against - * code executing on this cpu *not* from access by other cpus. + * Since this is without lock semantics the protection is only + * against code executing on this cpu *not* from access by + * other cpus. */ if (unlikely(!this_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, @@ -2399,7 +2488,8 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { void *ret = slab_alloc(s, gfpflags, _RET_IP_); - trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags); + trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, + s->size, gfpflags); return ret; } @@ -2413,14 +2503,6 @@ void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) return ret; } EXPORT_SYMBOL(kmem_cache_alloc_trace); - -void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) -{ - void *ret = kmalloc_order(size, flags, order); - trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags); - return ret; -} -EXPORT_SYMBOL(kmalloc_order_trace); #endif #ifdef CONFIG_NUMA @@ -2488,15 +2570,17 @@ static void __slab_free(struct kmem_cache *s, struct page *page, new.inuse--; if ((!new.inuse || !prior) && !was_frozen) { - if (!kmem_cache_debug(s) && !prior) + if (kmem_cache_has_cpu_partial(s) && !prior) { /* - * Slab was on no list before and will be partially empty - * We can defer the list move and instead freeze it. + * Slab was on no list before and will be + * partially empty + * We can defer the list move and instead + * freeze it. */ new.frozen = 1; - else { /* Needs to be taken off a list */ + } else { /* Needs to be taken off a list */ n = get_node(s, page_to_nid(page)); /* @@ -2536,15 +2620,16 @@ static void __slab_free(struct kmem_cache *s, struct page *page, return; } - if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) + if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) goto slab_empty; /* * Objects left in the slab. If it was not on the partial list before * then add it. */ - if (kmem_cache_debug(s) && unlikely(!prior)) { - remove_full(s, page); + if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) { + if (kmem_cache_debug(s)) + remove_full(s, n, page); add_partial(n, page, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } @@ -2558,9 +2643,10 @@ slab_empty: */ remove_partial(n, page); stat(s, FREE_REMOVE_PARTIAL); - } else + } else { /* Slab must be on the full list */ - remove_full(s, page); + remove_full(s, n, page); + } spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); @@ -2594,10 +2680,11 @@ redo: * data is retrieved via this pointer. If we are on the same cpu * during the cmpxchg then the free will succedd. */ - c = __this_cpu_ptr(s->cpu_slab); + preempt_disable(); + c = this_cpu_ptr(s->cpu_slab); tid = c->tid; - barrier(); + preempt_enable(); if (likely(page == c->page)) { set_freepointer(s, object, c->freelist); @@ -2775,7 +2862,7 @@ init_kmem_cache_node(struct kmem_cache_node *n) static inline int alloc_kmem_cache_cpus(struct kmem_cache *s) { BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE < - SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu)); + KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu)); /* * Must align to double word boundary for the double cmpxchg @@ -2799,8 +2886,8 @@ static struct kmem_cache *kmem_cache_node; * slab on the node for this slabcache. There are no concurrent accesses * possible. * - * Note that this function only works on the kmalloc_node_cache - * when allocating for the kmalloc_node_cache. This is used for bootstrapping + * Note that this function only works on the kmem_cache_node + * when allocating for the kmem_cache_node. This is used for bootstrapping * memory on a fresh node that has no slab structures yet. */ static void early_kmem_cache_node_alloc(int node) @@ -2814,10 +2901,8 @@ static void early_kmem_cache_node_alloc(int node) BUG_ON(!page); if (page_to_nid(page) != node) { - printk(KERN_ERR "SLUB: Unable to allocate memory from " - "node %d\n", node); - printk(KERN_ERR "SLUB: Allocating a useless per node structure " - "in order to be able to continue\n"); + pr_err("SLUB: Unable to allocate memory from node %d\n", node); + pr_err("SLUB: Allocating a useless per node structure in order to be able to continue\n"); } n = page->freelist; @@ -2833,7 +2918,11 @@ static void early_kmem_cache_node_alloc(int node) init_kmem_cache_node(n); inc_slabs_node(kmem_cache_node, node, page->objects); - add_partial(n, page, DEACTIVATE_TO_HEAD); + /* + * No locks need to be taken here as it has just been + * initialized and there is no concurrent access. + */ + __add_partial(n, page, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -2982,7 +3071,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) s->allocflags |= __GFP_COMP; if (s->flags & SLAB_CACHE_DMA) - s->allocflags |= SLUB_DMA; + s->allocflags |= GFP_DMA; if (s->flags & SLAB_RECLAIM_ACCOUNT) s->allocflags |= __GFP_RECLAIMABLE; @@ -3048,10 +3137,10 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags) * A) The number of objects from per cpu partial slabs dumped to the * per node list when we reach the limit. * B) The number of objects in cpu partial slabs to extract from the - * per node list when we run out of per cpu objects. We only fetch 50% - * to keep some capacity around for frees. + * per node list when we run out of per cpu objects. We only fetch + * 50% to keep some capacity around for frees. */ - if (kmem_cache_debug(s)) + if (!kmem_cache_has_cpu_partial(s)) s->cpu_partial = 0; else if (s->size >= PAGE_SIZE) s->cpu_partial = 2; @@ -3076,8 +3165,8 @@ error: if (flags & SLAB_PANIC) panic("Cannot create slab %s size=%lu realsize=%u " "order=%u offset=%u flags=%lx\n", - s->name, (unsigned long)s->size, s->size, oo_order(s->oo), - s->offset, flags); + s->name, (unsigned long)s->size, s->size, + oo_order(s->oo), s->offset, flags); return -EINVAL; } @@ -3098,8 +3187,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, for_each_object(p, s, addr, page->objects) { if (!test_bit(slab_index(p, s, addr), map)) { - printk(KERN_ERR "INFO: Object 0x%p @offset=%tu\n", - p, p - addr); + pr_err("INFO: Object 0x%p @offset=%tu\n", p, p - addr); print_tracking(s, p); } } @@ -3119,7 +3207,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { - remove_partial(n, page); + __remove_partial(n, page); discard_slab(s, page); } else { list_slab_objects(s, page, @@ -3151,36 +3239,13 @@ static inline int kmem_cache_close(struct kmem_cache *s) int __kmem_cache_shutdown(struct kmem_cache *s) { - int rc = kmem_cache_close(s); - - if (!rc) { - /* - * We do the same lock strategy around sysfs_slab_add, see - * __kmem_cache_create. Because this is pretty much the last - * operation we do and the lock will be released shortly after - * that in slab_common.c, we could just move sysfs_slab_remove - * to a later point in common code. We should do that when we - * have a common sysfs framework for all allocators. - */ - mutex_unlock(&slab_mutex); - sysfs_slab_remove(s); - mutex_lock(&slab_mutex); - } - - return rc; + return kmem_cache_close(s); } /******************************************************************** * Kmalloc subsystem *******************************************************************/ -struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT]; -EXPORT_SYMBOL(kmalloc_caches); - -#ifdef CONFIG_ZONE_DMA -static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT]; -#endif - static int __init setup_slub_min_order(char *str) { get_option(&str, &slub_min_order); @@ -3217,73 +3282,15 @@ static int __init setup_slub_nomerge(char *str) __setup("slub_nomerge", setup_slub_nomerge); -/* - * Conversion table for small slabs sizes / 8 to the index in the - * kmalloc array. This is necessary for slabs < 192 since we have non power - * of two cache sizes there. The size of larger slabs can be determined using - * fls. - */ -static s8 size_index[24] = { - 3, /* 8 */ - 4, /* 16 */ - 5, /* 24 */ - 5, /* 32 */ - 6, /* 40 */ - 6, /* 48 */ - 6, /* 56 */ - 6, /* 64 */ - 1, /* 72 */ - 1, /* 80 */ - 1, /* 88 */ - 1, /* 96 */ - 7, /* 104 */ - 7, /* 112 */ - 7, /* 120 */ - 7, /* 128 */ - 2, /* 136 */ - 2, /* 144 */ - 2, /* 152 */ - 2, /* 160 */ - 2, /* 168 */ - 2, /* 176 */ - 2, /* 184 */ - 2 /* 192 */ -}; - -static inline int size_index_elem(size_t bytes) -{ - return (bytes - 1) / 8; -} - -static struct kmem_cache *get_slab(size_t size, gfp_t flags) -{ - int index; - - if (size <= 192) { - if (!size) - return ZERO_SIZE_PTR; - - index = size_index[size_index_elem(size)]; - } else - index = fls(size - 1); - -#ifdef CONFIG_ZONE_DMA - if (unlikely((flags & SLUB_DMA))) - return kmalloc_dma_caches[index]; - -#endif - return kmalloc_caches[index]; -} - void *__kmalloc(size_t size, gfp_t flags) { struct kmem_cache *s; void *ret; - if (unlikely(size > SLUB_MAX_SIZE)) + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) return kmalloc_large(size, flags); - s = get_slab(size, flags); + s = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(s))) return s; @@ -3302,12 +3309,12 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) struct page *page; void *ptr = NULL; - flags |= __GFP_COMP | __GFP_NOTRACK | __GFP_KMEMCG; - page = alloc_pages_node(node, flags, get_order(size)); + flags |= __GFP_COMP | __GFP_NOTRACK; + page = alloc_kmem_pages_node(node, flags, get_order(size)); if (page) ptr = page_address(page); - kmemleak_alloc(ptr, size, 1, flags); + kmalloc_large_node_hook(ptr, size, flags); return ptr; } @@ -3316,7 +3323,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) struct kmem_cache *s; void *ret; - if (unlikely(size > SLUB_MAX_SIZE)) { + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { ret = kmalloc_large_node(size, flags, node); trace_kmalloc_node(_RET_IP_, ret, @@ -3326,7 +3333,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) return ret; } - s = get_slab(size, flags); + s = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(s))) return s; @@ -3358,42 +3365,6 @@ size_t ksize(const void *object) } EXPORT_SYMBOL(ksize); -#ifdef CONFIG_SLUB_DEBUG -bool verify_mem_not_deleted(const void *x) -{ - struct page *page; - void *object = (void *)x; - unsigned long flags; - bool rv; - - if (unlikely(ZERO_OR_NULL_PTR(x))) - return false; - - local_irq_save(flags); - - page = virt_to_head_page(x); - if (unlikely(!PageSlab(page))) { - /* maybe it was from stack? */ - rv = true; - goto out_unlock; - } - - slab_lock(page); - if (on_freelist(page->slab_cache, page, object)) { - object_err(page->slab_cache, page, object, "Object is on free-list"); - rv = false; - } else { - rv = true; - } - slab_unlock(page); - -out_unlock: - local_irq_restore(flags); - return rv; -} -EXPORT_SYMBOL(verify_mem_not_deleted); -#endif - void kfree(const void *x) { struct page *page; @@ -3407,8 +3378,8 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { BUG_ON(!PageCompound(page)); - kmemleak_free(x); - __free_memcg_kmem_pages(page, compound_order(page)); + kfree_hook(x); + __free_kmem_pages(page, compound_order(page)); return; } slab_free(page->slab_cache, page, object, _RET_IP_); @@ -3425,7 +3396,7 @@ EXPORT_SYMBOL(kfree); * being allocated from last increasing the chance that the last objects * are freed in them. */ -int kmem_cache_shrink(struct kmem_cache *s) +int __kmem_cache_shrink(struct kmem_cache *s) { int node; int i; @@ -3481,16 +3452,14 @@ int kmem_cache_shrink(struct kmem_cache *s) kfree(slabs_by_inuse); return 0; } -EXPORT_SYMBOL(kmem_cache_shrink); -#if defined(CONFIG_MEMORY_HOTPLUG) static int slab_mem_going_offline_callback(void *arg) { struct kmem_cache *s; mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) - kmem_cache_shrink(s); + __kmem_cache_shrink(s); mutex_unlock(&slab_mutex); return 0; @@ -3598,7 +3567,10 @@ static int slab_memory_callback(struct notifier_block *self, return ret; } -#endif /* CONFIG_MEMORY_HOTPLUG */ +static struct notifier_block slab_memory_callback_nb = { + .notifier_call = slab_memory_callback, + .priority = SLAB_CALLBACK_PRI, +}; /******************************************************************** * Basic setup of slabs @@ -3617,6 +3589,12 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) memcpy(s, static_cache, kmem_cache->object_size); + /* + * This runs very early, and only the boot processor is supposed to be + * up. Even if it weren't true, IRQs are not up so we couldn't fire + * IPIs around. + */ + __flush_cpu_slab(s, smp_processor_id()); for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n = get_node(s, node); struct page *p; @@ -3639,8 +3617,6 @@ void __init kmem_cache_init(void) { static __initdata struct kmem_cache boot_kmem_cache, boot_kmem_cache_node; - int i; - int caches = 2; if (debug_guardpage_minorder()) slub_max_order = 0; @@ -3651,7 +3627,7 @@ void __init kmem_cache_init(void) create_boot_cache(kmem_cache_node, "kmem_cache_node", sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN); - hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI); + register_hotmemory_notifier(&slab_memory_callback_nb); /* Able to allocate the per node structures */ slab_state = PARTIAL; @@ -3671,103 +3647,14 @@ void __init kmem_cache_init(void) kmem_cache_node = bootstrap(&boot_kmem_cache_node); /* Now we can use the kmem_cache to allocate kmalloc slabs */ - - /* - * Patch up the size_index table if we have strange large alignment - * requirements for the kmalloc array. This is only the case for - * MIPS it seems. The standard arches will not generate any code here. - * - * Largest permitted alignment is 256 bytes due to the way we - * handle the index determination for the smaller caches. - * - * Make sure that nothing crazy happens if someone starts tinkering - * around with ARCH_KMALLOC_MINALIGN - */ - BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 || - (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1))); - - for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) { - int elem = size_index_elem(i); - if (elem >= ARRAY_SIZE(size_index)) - break; - size_index[elem] = KMALLOC_SHIFT_LOW; - } - - if (KMALLOC_MIN_SIZE == 64) { - /* - * The 96 byte size cache is not used if the alignment - * is 64 byte. - */ - for (i = 64 + 8; i <= 96; i += 8) - size_index[size_index_elem(i)] = 7; - } else if (KMALLOC_MIN_SIZE == 128) { - /* - * The 192 byte sized cache is not used if the alignment - * is 128 byte. Redirect kmalloc to use the 256 byte cache - * instead. - */ - for (i = 128 + 8; i <= 192; i += 8) - size_index[size_index_elem(i)] = 8; - } - - /* Caches that are not of the two-to-the-power-of size */ - if (KMALLOC_MIN_SIZE <= 32) { - kmalloc_caches[1] = create_kmalloc_cache("kmalloc-96", 96, 0); - caches++; - } - - if (KMALLOC_MIN_SIZE <= 64) { - kmalloc_caches[2] = create_kmalloc_cache("kmalloc-192", 192, 0); - caches++; - } - - for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) { - kmalloc_caches[i] = create_kmalloc_cache("kmalloc", 1 << i, 0); - caches++; - } - - slab_state = UP; - - /* Provide the correct kmalloc names now that the caches are up */ - if (KMALLOC_MIN_SIZE <= 32) { - kmalloc_caches[1]->name = kstrdup(kmalloc_caches[1]->name, GFP_NOWAIT); - BUG_ON(!kmalloc_caches[1]->name); - } - - if (KMALLOC_MIN_SIZE <= 64) { - kmalloc_caches[2]->name = kstrdup(kmalloc_caches[2]->name, GFP_NOWAIT); - BUG_ON(!kmalloc_caches[2]->name); - } - - for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) { - char *s = kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i); - - BUG_ON(!s); - kmalloc_caches[i]->name = s; - } + create_kmalloc_caches(0); #ifdef CONFIG_SMP register_cpu_notifier(&slab_notifier); #endif -#ifdef CONFIG_ZONE_DMA - for (i = 0; i < SLUB_PAGE_SHIFT; i++) { - struct kmem_cache *s = kmalloc_caches[i]; - - if (s && s->size) { - char *name = kasprintf(GFP_NOWAIT, - "dma-kmalloc-%d", s->object_size); - - BUG_ON(!name); - kmalloc_dma_caches[i] = create_kmalloc_cache(name, - s->object_size, SLAB_CACHE_DMA); - } - } -#endif - printk(KERN_INFO - "SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d," - " CPUs=%d, Nodes=%d\n", - caches, cache_line_size(), + pr_info("SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d, CPUs=%d, Nodes=%d\n", + cache_line_size(), slub_min_order, slub_max_order, slub_min_objects, nr_cpu_ids, nr_node_ids); } @@ -3784,6 +3671,9 @@ static int slab_unmergeable(struct kmem_cache *s) if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE)) return 1; + if (!is_root_cache(s)) + return 1; + if (s->ctor) return 1; @@ -3796,9 +3686,8 @@ static int slab_unmergeable(struct kmem_cache *s) return 0; } -static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, - size_t align, unsigned long flags, const char *name, - void (*ctor)(void *)) +static struct kmem_cache *find_mergeable(size_t size, size_t align, + unsigned long flags, const char *name, void (*ctor)(void *)) { struct kmem_cache *s; @@ -3821,7 +3710,7 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, continue; if ((flags & SLUB_MERGE_SAME) != (s->flags & SLUB_MERGE_SAME)) - continue; + continue; /* * Check if alignment is compatible. * Courtesy of Adrian Drzewiecki @@ -3832,23 +3721,24 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, if (s->size - size >= sizeof(void *)) continue; - if (!cache_match_memcg(s, memcg)) - continue; - return s; } return NULL; } struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)) +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *s; - s = find_mergeable(memcg, size, align, flags, name, ctor); + s = find_mergeable(size, align, flags, name, ctor); if (s) { + int i; + struct kmem_cache *c; + s->refcount++; + /* * Adjust the object sizes so that we clear * the complete object on kzalloc. @@ -3856,6 +3746,15 @@ __kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, s->object_size = max(s->object_size, (int)size); s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *))); + for_each_memcg_cache_index(i) { + c = cache_from_memcg_idx(s, i); + if (!c) + continue; + c->object_size = s->object_size; + c->inuse = max_t(int, c->inuse, + ALIGN(size, sizeof(void *))); + } + if (sysfs_slab_alias(s, name)) { s->refcount--; s = NULL; @@ -3878,10 +3777,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags) return 0; memcg_propagate_slab_attrs(s); - mutex_unlock(&slab_mutex); err = sysfs_slab_add(s); - mutex_lock(&slab_mutex); - if (err) kmem_cache_close(s); @@ -3893,7 +3789,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags) * Use the cpu notifier to insure that the cpu slabs are flushed when * necessary. */ -static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb, +static int slab_cpuup_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { long cpu = (long)hcpu; @@ -3919,7 +3815,7 @@ static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata slab_notifier = { +static struct notifier_block slab_notifier = { .notifier_call = slab_cpuup_callback }; @@ -3930,10 +3826,10 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) struct kmem_cache *s; void *ret; - if (unlikely(size > SLUB_MAX_SIZE)) + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) return kmalloc_large(size, gfpflags); - s = get_slab(size, gfpflags); + s = kmalloc_slab(size, gfpflags); if (unlikely(ZERO_OR_NULL_PTR(s))) return s; @@ -3953,7 +3849,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, struct kmem_cache *s; void *ret; - if (unlikely(size > SLUB_MAX_SIZE)) { + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { ret = kmalloc_large_node(size, gfpflags, node); trace_kmalloc_node(caller, ret, @@ -3963,7 +3859,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, return ret; } - s = get_slab(size, gfpflags); + s = kmalloc_slab(size, gfpflags); if (unlikely(ZERO_OR_NULL_PTR(s))) return s; @@ -4039,8 +3935,8 @@ static int validate_slab_node(struct kmem_cache *s, count++; } if (count != n->nr_partial) - printk(KERN_ERR "SLUB %s: %ld partial slabs counted but " - "counter=%ld\n", s->name, count, n->nr_partial); + pr_err("SLUB %s: %ld partial slabs counted but counter=%ld\n", + s->name, count, n->nr_partial); if (!(s->flags & SLAB_STORE_USER)) goto out; @@ -4050,9 +3946,8 @@ static int validate_slab_node(struct kmem_cache *s, count++; } if (count != atomic_long_read(&n->nr_slabs)) - printk(KERN_ERR "SLUB: %s %ld slabs counted but " - "counter=%ld\n", s->name, count, - atomic_long_read(&n->nr_slabs)); + pr_err("SLUB: %s %ld slabs counted but counter=%ld\n", + s->name, count, atomic_long_read(&n->nr_slabs)); out: spin_unlock_irqrestore(&n->list_lock, flags); @@ -4285,15 +4180,17 @@ static int list_locations(struct kmem_cache *s, char *buf, !cpumask_empty(to_cpumask(l->cpus)) && len < PAGE_SIZE - 60) { len += sprintf(buf + len, " cpus="); - len += cpulist_scnprintf(buf + len, PAGE_SIZE - len - 50, + len += cpulist_scnprintf(buf + len, + PAGE_SIZE - len - 50, to_cpumask(l->cpus)); } if (nr_online_nodes > 1 && !nodes_empty(l->nodes) && len < PAGE_SIZE - 60) { len += sprintf(buf + len, " nodes="); - len += nodelist_scnprintf(buf + len, PAGE_SIZE - len - 50, - l->nodes); + len += nodelist_scnprintf(buf + len, + PAGE_SIZE - len - 50, + l->nodes); } len += sprintf(buf + len, "\n"); @@ -4312,55 +4209,52 @@ static void resiliency_test(void) { u8 *p; - BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || SLUB_PAGE_SHIFT < 10); + BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10); - printk(KERN_ERR "SLUB resiliency testing\n"); - printk(KERN_ERR "-----------------------\n"); - printk(KERN_ERR "A. Corruption after allocation\n"); + pr_err("SLUB resiliency testing\n"); + pr_err("-----------------------\n"); + pr_err("A. Corruption after allocation\n"); p = kzalloc(16, GFP_KERNEL); p[16] = 0x12; - printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer" - " 0x12->0x%p\n\n", p + 16); + pr_err("\n1. kmalloc-16: Clobber Redzone/next pointer 0x12->0x%p\n\n", + p + 16); validate_slab_cache(kmalloc_caches[4]); /* Hmmm... The next two are dangerous */ p = kzalloc(32, GFP_KERNEL); p[32 + sizeof(void *)] = 0x34; - printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab" - " 0x34 -> -0x%p\n", p); - printk(KERN_ERR - "If allocated object is overwritten then not detectable\n\n"); + pr_err("\n2. kmalloc-32: Clobber next pointer/next slab 0x34 -> -0x%p\n", + p); + pr_err("If allocated object is overwritten then not detectable\n\n"); validate_slab_cache(kmalloc_caches[5]); p = kzalloc(64, GFP_KERNEL); p += 64 + (get_cycles() & 0xff) * sizeof(void *); *p = 0x56; - printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", - p); - printk(KERN_ERR - "If allocated object is overwritten then not detectable\n\n"); + pr_err("\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", + p); + pr_err("If allocated object is overwritten then not detectable\n\n"); validate_slab_cache(kmalloc_caches[6]); - printk(KERN_ERR "\nB. Corruption after free\n"); + pr_err("\nB. Corruption after free\n"); p = kzalloc(128, GFP_KERNEL); kfree(p); *p = 0x78; - printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); + pr_err("1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); validate_slab_cache(kmalloc_caches[7]); p = kzalloc(256, GFP_KERNEL); kfree(p); p[50] = 0x9a; - printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", - p); + pr_err("\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p); validate_slab_cache(kmalloc_caches[8]); p = kzalloc(512, GFP_KERNEL); kfree(p); p[512] = 0xab; - printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); + pr_err("\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); validate_slab_cache(kmalloc_caches[9]); } #else @@ -4391,18 +4285,17 @@ static ssize_t show_slab_objects(struct kmem_cache *s, int node; int x; unsigned long *nodes; - unsigned long *per_cpu; - nodes = kzalloc(2 * sizeof(unsigned long) * nr_node_ids, GFP_KERNEL); + nodes = kzalloc(sizeof(unsigned long) * nr_node_ids, GFP_KERNEL); if (!nodes) return -ENOMEM; - per_cpu = nodes + nr_node_ids; if (flags & SO_CPU) { int cpu; for_each_possible_cpu(cpu) { - struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); + struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, + cpu); int node; struct page *page; @@ -4423,27 +4316,30 @@ static ssize_t show_slab_objects(struct kmem_cache *s, page = ACCESS_ONCE(c->partial); if (page) { - x = page->pobjects; + node = page_to_nid(page); + if (flags & SO_TOTAL) + WARN_ON_ONCE(1); + else if (flags & SO_OBJECTS) + WARN_ON_ONCE(1); + else + x = page->pages; total += x; nodes[node] += x; } - - per_cpu[node]++; } } - lock_memory_hotplug(); + get_online_mems(); #ifdef CONFIG_SLUB_DEBUG if (flags & SO_ALL) { for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n = get_node(s, node); - if (flags & SO_TOTAL) - x = atomic_long_read(&n->total_objects); - else if (flags & SO_OBJECTS) - x = atomic_long_read(&n->total_objects) - - count_partial(n, count_free); - + if (flags & SO_TOTAL) + x = atomic_long_read(&n->total_objects); + else if (flags & SO_OBJECTS) + x = atomic_long_read(&n->total_objects) - + count_partial(n, count_free); else x = atomic_long_read(&n->nr_slabs); total += x; @@ -4473,7 +4369,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, x += sprintf(buf + x, " N%d=%lu", node, nodes[node]); #endif - unlock_memory_hotplug(); + put_online_mems(); kfree(nodes); return x + sprintf(buf + x, "\n"); } @@ -4543,7 +4439,7 @@ static ssize_t order_store(struct kmem_cache *s, unsigned long order; int err; - err = strict_strtoul(buf, 10, &order); + err = kstrtoul(buf, 10, &order); if (err) return err; @@ -4571,7 +4467,7 @@ static ssize_t min_partial_store(struct kmem_cache *s, const char *buf, unsigned long min; int err; - err = strict_strtoul(buf, 10, &min); + err = kstrtoul(buf, 10, &min); if (err) return err; @@ -4591,10 +4487,10 @@ static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf, unsigned long objects; int err; - err = strict_strtoul(buf, 10, &objects); + err = kstrtoul(buf, 10, &objects); if (err) return err; - if (objects && kmem_cache_debug(s)) + if (objects && !kmem_cache_has_cpu_partial(s)) return -EINVAL; s->cpu_partial = objects; @@ -4907,7 +4803,7 @@ static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s, unsigned long ratio; int err; - err = strict_strtoul(buf, 10, &ratio); + err = kstrtoul(buf, 10, &ratio); if (err) return err; @@ -5137,7 +5033,7 @@ static ssize_t slab_attr_store(struct kobject *kobj, * through the descendants with best-effort propagation. */ for_each_memcg_cache_index(i) { - struct kmem_cache *c = cache_from_memcg(s, i); + struct kmem_cache *c = cache_from_memcg_idx(s, i); if (c) attribute->store(c, buf, len); } @@ -5152,15 +5048,18 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) #ifdef CONFIG_MEMCG_KMEM int i; char *buffer = NULL; + struct kmem_cache *root_cache; - if (!is_root_cache(s)) + if (is_root_cache(s)) return; + root_cache = s->memcg_params->root_cache; + /* * This mean this cache had no attribute written. Therefore, no point * in copying default values around */ - if (!s->max_attr_size) + if (!root_cache->max_attr_size) return; for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) { @@ -5182,7 +5081,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) */ if (buffer) buf = buffer; - else if (s->max_attr_size < ARRAY_SIZE(mbuf)) + else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf)) buf = mbuf; else { buffer = (char *) get_zeroed_page(GFP_KERNEL); @@ -5191,7 +5090,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) buf = buffer; } - attr->show(s->memcg_params->root_cache, buf); + attr->show(root_cache, buf); attr->store(s, buf, strlen(buf)); } @@ -5200,6 +5099,11 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) #endif } +static void kmem_cache_release(struct kobject *k) +{ + slab_kmem_cache_release(to_slab(k)); +} + static const struct sysfs_ops slab_sysfs_ops = { .show = slab_attr_show, .store = slab_attr_store, @@ -5207,6 +5111,7 @@ static const struct sysfs_ops slab_sysfs_ops = { static struct kobj_type slab_ktype = { .sysfs_ops = &slab_sysfs_ops, + .release = kmem_cache_release, }; static int uevent_filter(struct kset *kset, struct kobject *kobj) @@ -5224,6 +5129,15 @@ static const struct kset_uevent_ops slab_uevent_ops = { static struct kset *slab_kset; +static inline struct kset *cache_kset(struct kmem_cache *s) +{ +#ifdef CONFIG_MEMCG_KMEM + if (!is_root_cache(s)) + return s->memcg_params->root_cache->memcg_kset; +#endif + return slab_kset; +} + #define ID_STR_LENGTH 64 /* Create a unique string id for a slab cache: @@ -5259,7 +5173,8 @@ static char *create_unique_id(struct kmem_cache *s) #ifdef CONFIG_MEMCG_KMEM if (!is_root_cache(s)) - p += sprintf(p, "-%08d", memcg_cache_id(s->memcg_params->memcg)); + p += sprintf(p, "-%08d", + memcg_cache_id(s->memcg_params->memcg)); #endif BUG_ON(p > name + ID_STR_LENGTH - 1); @@ -5288,29 +5203,42 @@ static int sysfs_slab_add(struct kmem_cache *s) name = create_unique_id(s); } - s->kobj.kset = slab_kset; - err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, name); - if (err) { - kobject_put(&s->kobj); - return err; - } + s->kobj.kset = cache_kset(s); + err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); + if (err) + goto out_put_kobj; err = sysfs_create_group(&s->kobj, &slab_attr_group); - if (err) { - kobject_del(&s->kobj); - kobject_put(&s->kobj); - return err; + if (err) + goto out_del_kobj; + +#ifdef CONFIG_MEMCG_KMEM + if (is_root_cache(s)) { + s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj); + if (!s->memcg_kset) { + err = -ENOMEM; + goto out_del_kobj; + } } +#endif + kobject_uevent(&s->kobj, KOBJ_ADD); if (!unmergeable) { /* Setup first alias */ sysfs_slab_alias(s, s->name); - kfree(name); } - return 0; +out: + if (!unmergeable) + kfree(name); + return err; +out_del_kobj: + kobject_del(&s->kobj); +out_put_kobj: + kobject_put(&s->kobj); + goto out; } -static void sysfs_slab_remove(struct kmem_cache *s) +void sysfs_slab_remove(struct kmem_cache *s) { if (slab_state < FULL) /* @@ -5319,6 +5247,9 @@ static void sysfs_slab_remove(struct kmem_cache *s) */ return; +#ifdef CONFIG_MEMCG_KMEM + kset_unregister(s->memcg_kset); +#endif kobject_uevent(&s->kobj, KOBJ_REMOVE); kobject_del(&s->kobj); kobject_put(&s->kobj); @@ -5369,7 +5300,7 @@ static int __init slab_sysfs_init(void) slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj); if (!slab_kset) { mutex_unlock(&slab_mutex); - printk(KERN_ERR "Cannot register slab subsystem.\n"); + pr_err("Cannot register slab subsystem.\n"); return -ENOSYS; } @@ -5378,8 +5309,8 @@ static int __init slab_sysfs_init(void) list_for_each_entry(s, &slab_caches, list) { err = sysfs_slab_add(s); if (err) - printk(KERN_ERR "SLUB: Unable to add boot slab %s" - " to sysfs\n", s->name); + pr_err("SLUB: Unable to add boot slab %s to sysfs\n", + s->name); } while (alias_list) { @@ -5388,8 +5319,8 @@ static int __init slab_sysfs_init(void) alias_list = alias_list->next; err = sysfs_slab_alias(al->s, al->name); if (err) - printk(KERN_ERR "SLUB: Unable to add boot slab alias" - " %s to sysfs\n", al->name); + pr_err("SLUB: Unable to add boot slab alias %s to sysfs\n", + al->name); kfree(al); } @@ -5407,7 +5338,6 @@ __initcall(slab_sysfs_init); #ifdef CONFIG_SLABINFO void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo) { - unsigned long nr_partials = 0; unsigned long nr_slabs = 0; unsigned long nr_objs = 0; unsigned long nr_free = 0; @@ -5419,9 +5349,8 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo) if (!n) continue; - nr_partials += n->nr_partial; - nr_slabs += atomic_long_read(&n->nr_slabs); - nr_objs += atomic_long_read(&n->total_objects); + nr_slabs += node_nr_slabs(n); + nr_objs += node_nr_objs(n); nr_free += count_partial(n, count_free); } diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 1b7e22ab9b0..4cba9c2783a 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -40,7 +40,8 @@ static void * __init_refok __earlyonly_bootmem_alloc(int node, unsigned long align, unsigned long goal) { - return __alloc_bootmem_node_high(NODE_DATA(node), size, align, goal); + return memblock_virt_alloc_try_nid(size, align, goal, + BOOTMEM_ALLOC_ACCESSIBLE, node); } static void *vmemmap_buf; @@ -53,10 +54,12 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) struct page *page; if (node_state(node, N_HIGH_MEMORY)) - page = alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO, get_order(size)); + page = alloc_pages_node( + node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT, + get_order(size)); else - page = alloc_pages(GFP_KERNEL | __GFP_ZERO, + page = alloc_pages( + GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT, get_order(size)); if (page) return page_address(page); @@ -145,11 +148,10 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) return pgd; } -int __meminit vmemmap_populate_basepages(struct page *start_page, - unsigned long size, int node) +int __meminit vmemmap_populate_basepages(unsigned long start, + unsigned long end, int node) { - unsigned long addr = (unsigned long)start_page; - unsigned long end = (unsigned long)(start_page + size); + unsigned long addr = start; pgd_t *pgd; pud_t *pud; pmd_t *pmd; @@ -176,9 +178,15 @@ int __meminit vmemmap_populate_basepages(struct page *start_page, struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid) { - struct page *map = pfn_to_page(pnum * PAGES_PER_SECTION); - int error = vmemmap_populate(map, PAGES_PER_SECTION, nid); - if (error) + unsigned long start; + unsigned long end; + struct page *map; + + map = pfn_to_page(pnum * PAGES_PER_SECTION); + start = (unsigned long)map; + end = (unsigned long)(map + PAGES_PER_SECTION); + + if (vmemmap_populate(start, end, nid)) return NULL; return map; @@ -219,7 +227,8 @@ void __init sparse_mem_maps_populate_node(struct page **map_map, if (vmemmap_buf_start) { /* need to free left buf */ - free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf); + memblock_free_early(__pa(vmemmap_buf), + vmemmap_buf_end - vmemmap_buf); vmemmap_buf = NULL; vmemmap_buf_end = NULL; } diff --git a/mm/sparse.c b/mm/sparse.c index 6b5fb762e2c..d1b48b691ac 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -5,10 +5,12 @@ #include <linux/slab.h> #include <linux/mmzone.h> #include <linux/bootmem.h> +#include <linux/compiler.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> + #include "internal.h" #include <asm/dma.h> #include <asm/pgalloc.h> @@ -69,7 +71,7 @@ static struct mem_section noinline __init_refok *sparse_index_alloc(int nid) else section = kzalloc(array_size, GFP_KERNEL); } else { - section = alloc_bootmem_node(NODE_DATA(nid), array_size); + section = memblock_virt_alloc_node(array_size, nid); } return section; @@ -79,7 +81,6 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid) { unsigned long root = SECTION_NR_TO_ROOT(section_nr); struct mem_section *section; - int ret = 0; if (mem_section[root]) return -EEXIST; @@ -90,7 +91,7 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid) mem_section[root] = section; - return ret; + return 0; } #else /* !SPARSEMEM_EXTREME */ static inline int sparse_index_init(unsigned long section_nr, int nid) @@ -269,7 +270,7 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, /* * A page may contain usemaps for other sections preventing the * page being freed and making a section unremovable while - * other sections referencing the usemap retmain active. Similarly, + * other sections referencing the usemap remain active. Similarly, * a pgdat can prevent a section being removed. If section A * contains a pgdat and section B contains the usemap, both * sections become inter-dependent. This allocates usemaps @@ -280,8 +281,9 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, limit = goal + (1UL << PA_SECTION_SHIFT); nid = early_pfn_to_nid(goal >> PAGE_SHIFT); again: - p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, - SMP_CACHE_BYTES, goal, limit); + p = memblock_virt_alloc_try_nid_nopanic(size, + SMP_CACHE_BYTES, goal, limit, + nid); if (!p && limit) { limit = 0; goto again; @@ -332,7 +334,7 @@ static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, unsigned long size) { - return alloc_bootmem_node_nopanic(pgdat, size); + return memblock_virt_alloc_node_nopanic(size, pgdat->node_id); } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) @@ -340,13 +342,14 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap) } #endif /* CONFIG_MEMORY_HOTREMOVE */ -static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map, +static void __init sparse_early_usemaps_alloc_node(void *data, unsigned long pnum_begin, unsigned long pnum_end, unsigned long usemap_count, int nodeid) { void *usemap; unsigned long pnum; + unsigned long **usemap_map = (unsigned long **)data; int size = usemap_size(); usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid), @@ -376,8 +379,9 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid) return map; size = PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION); - map = __alloc_bootmem_node_high(NODE_DATA(nid), size, - PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + map = memblock_virt_alloc_try_nid(size, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + BOOTMEM_ALLOC_ACCESSIBLE, nid); return map; } void __init sparse_mem_maps_populate_node(struct page **map_map, @@ -401,8 +405,9 @@ void __init sparse_mem_maps_populate_node(struct page **map_map, } size = PAGE_ALIGN(size); - map = __alloc_bootmem_node_high(NODE_DATA(nodeid), size * map_count, - PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + map = memblock_virt_alloc_try_nid(size * map_count, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + BOOTMEM_ALLOC_ACCESSIBLE, nodeid); if (map) { for (pnum = pnum_begin; pnum < pnum_end; pnum++) { if (!present_section_nr(pnum)) @@ -431,11 +436,12 @@ void __init sparse_mem_maps_populate_node(struct page **map_map, #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER -static void __init sparse_early_mem_maps_alloc_node(struct page **map_map, +static void __init sparse_early_mem_maps_alloc_node(void *data, unsigned long pnum_begin, unsigned long pnum_end, unsigned long map_count, int nodeid) { + struct page **map_map = (struct page **)data; sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end, map_count, nodeid); } @@ -457,48 +463,22 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum) } #endif -void __attribute__((weak)) __meminit vmemmap_populate_print_last(void) +void __weak __meminit vmemmap_populate_print_last(void) { } -/* - * Allocate the accumulated non-linear sections, allocate a mem_map - * for each and record the physical to section mapping. +/** + * alloc_usemap_and_memmap - memory alloction for pageblock flags and vmemmap + * @map: usemap_map for pageblock flags or mmap_map for vmemmap */ -void __init sparse_init(void) +static void __init alloc_usemap_and_memmap(void (*alloc_func) + (void *, unsigned long, unsigned long, + unsigned long, int), void *data) { unsigned long pnum; - struct page *map; - unsigned long *usemap; - unsigned long **usemap_map; - int size; + unsigned long map_count; int nodeid_begin = 0; unsigned long pnum_begin = 0; - unsigned long usemap_count; -#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER - unsigned long map_count; - int size2; - struct page **map_map; -#endif - - /* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */ - set_pageblock_order(); - - /* - * map is using big page (aka 2M in x86 64 bit) - * usemap is less one page (aka 24 bytes) - * so alloc 2M (with 2M align) and 24 bytes in turn will - * make next 2M slip to one more 2M later. - * then in big system, the memory will have a lot of holes... - * here try to allocate 2M pages continuously. - * - * powerpc need to call sparse_init_one_section right after each - * sparse_early_mem_map_alloc, so allocate usemap_map at first. - */ - size = sizeof(unsigned long *) * NR_MEM_SECTIONS; - usemap_map = alloc_bootmem(size); - if (!usemap_map) - panic("can not allocate usemap_map\n"); for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { struct mem_section *ms; @@ -510,7 +490,7 @@ void __init sparse_init(void) pnum_begin = pnum; break; } - usemap_count = 1; + map_count = 1; for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) { struct mem_section *ms; int nodeid; @@ -520,61 +500,69 @@ void __init sparse_init(void) ms = __nr_to_section(pnum); nodeid = sparse_early_nid(ms); if (nodeid == nodeid_begin) { - usemap_count++; + map_count++; continue; } /* ok, we need to take cake of from pnum_begin to pnum - 1*/ - sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, pnum, - usemap_count, nodeid_begin); + alloc_func(data, pnum_begin, pnum, + map_count, nodeid_begin); /* new start, update count etc*/ nodeid_begin = nodeid; pnum_begin = pnum; - usemap_count = 1; + map_count = 1; } /* ok, last chunk */ - sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS, - usemap_count, nodeid_begin); + alloc_func(data, pnum_begin, NR_MEM_SECTIONS, + map_count, nodeid_begin); +} +/* + * Allocate the accumulated non-linear sections, allocate a mem_map + * for each and record the physical to section mapping. + */ +void __init sparse_init(void) +{ + unsigned long pnum; + struct page *map; + unsigned long *usemap; + unsigned long **usemap_map; + int size; #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER - size2 = sizeof(struct page *) * NR_MEM_SECTIONS; - map_map = alloc_bootmem(size2); - if (!map_map) - panic("can not allocate map_map\n"); + int size2; + struct page **map_map; +#endif - for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { - struct mem_section *ms; + /* see include/linux/mmzone.h 'struct mem_section' definition */ + BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section))); - if (!present_section_nr(pnum)) - continue; - ms = __nr_to_section(pnum); - nodeid_begin = sparse_early_nid(ms); - pnum_begin = pnum; - break; - } - map_count = 1; - for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) { - struct mem_section *ms; - int nodeid; + /* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */ + set_pageblock_order(); - if (!present_section_nr(pnum)) - continue; - ms = __nr_to_section(pnum); - nodeid = sparse_early_nid(ms); - if (nodeid == nodeid_begin) { - map_count++; - continue; - } - /* ok, we need to take cake of from pnum_begin to pnum - 1*/ - sparse_early_mem_maps_alloc_node(map_map, pnum_begin, pnum, - map_count, nodeid_begin); - /* new start, update count etc*/ - nodeid_begin = nodeid; - pnum_begin = pnum; - map_count = 1; - } - /* ok, last chunk */ - sparse_early_mem_maps_alloc_node(map_map, pnum_begin, NR_MEM_SECTIONS, - map_count, nodeid_begin); + /* + * map is using big page (aka 2M in x86 64 bit) + * usemap is less one page (aka 24 bytes) + * so alloc 2M (with 2M align) and 24 bytes in turn will + * make next 2M slip to one more 2M later. + * then in big system, the memory will have a lot of holes... + * here try to allocate 2M pages continuously. + * + * powerpc need to call sparse_init_one_section right after each + * sparse_early_mem_map_alloc, so allocate usemap_map at first. + */ + size = sizeof(unsigned long *) * NR_MEM_SECTIONS; + usemap_map = memblock_virt_alloc(size, 0); + if (!usemap_map) + panic("can not allocate usemap_map\n"); + alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node, + (void *)usemap_map); + +#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER + size2 = sizeof(struct page *) * NR_MEM_SECTIONS; + map_map = memblock_virt_alloc(size2, 0); + if (!map_map) + panic("can not allocate map_map\n"); + alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node, + (void *)map_map); #endif for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { @@ -600,31 +588,39 @@ void __init sparse_init(void) vmemmap_populate_print_last(); #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER - free_bootmem(__pa(map_map), size2); + memblock_free_early(__pa(map_map), size2); #endif - free_bootmem(__pa(usemap_map), size); + memblock_free_early(__pa(usemap_map), size); } #ifdef CONFIG_MEMORY_HOTPLUG #ifdef CONFIG_SPARSEMEM_VMEMMAP -static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, - unsigned long nr_pages) +static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid) { /* This will make the necessary allocations eventually. */ return sparse_mem_map_populate(pnum, nid); } -static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) +static void __kfree_section_memmap(struct page *memmap) { - return; /* XXX: Not implemented yet */ + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION); + + vmemmap_free(start, end); } -static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) +#ifdef CONFIG_MEMORY_HOTREMOVE +static void free_map_bootmem(struct page *memmap) { + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION); + + vmemmap_free(start, end); } +#endif /* CONFIG_MEMORY_HOTREMOVE */ #else -static struct page *__kmalloc_section_memmap(unsigned long nr_pages) +static struct page *__kmalloc_section_memmap(void) { struct page *page, *ret; - unsigned long memmap_size = sizeof(struct page) * nr_pages; + unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION; page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size)); if (page) @@ -642,27 +638,30 @@ got_map_ptr: return ret; } -static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, - unsigned long nr_pages) +static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid) { - return __kmalloc_section_memmap(nr_pages); + return __kmalloc_section_memmap(); } -static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) +static void __kfree_section_memmap(struct page *memmap) { if (is_vmalloc_addr(memmap)) vfree(memmap); else free_pages((unsigned long)memmap, - get_order(sizeof(struct page) * nr_pages)); + get_order(sizeof(struct page) * PAGES_PER_SECTION)); } -static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) +#ifdef CONFIG_MEMORY_HOTREMOVE +static void free_map_bootmem(struct page *memmap) { unsigned long maps_section_nr, removing_section_nr, i; - unsigned long magic; + unsigned long magic, nr_pages; struct page *page = virt_to_page(memmap); + nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) + >> PAGE_SHIFT; + for (i = 0; i < nr_pages; i++, page++) { magic = (unsigned long) page->lru.next; @@ -683,47 +682,15 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) put_page_bootmem(page); } } +#endif /* CONFIG_MEMORY_HOTREMOVE */ #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -static void free_section_usemap(struct page *memmap, unsigned long *usemap) -{ - struct page *usemap_page; - unsigned long nr_pages; - - if (!usemap) - return; - - usemap_page = virt_to_page(usemap); - /* - * Check to see if allocation came from hot-plug-add - */ - if (PageSlab(usemap_page)) { - kfree(usemap); - if (memmap) - __kfree_section_memmap(memmap, PAGES_PER_SECTION); - return; - } - - /* - * The usemap came from bootmem. This is packed with other usemaps - * on the section which has pgdat at boot time. Just keep it as is now. - */ - - if (memmap) { - nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) - >> PAGE_SHIFT; - - free_map_bootmem(memmap, nr_pages); - } -} - /* * returns the number of sections whose mem_maps were properly * set. If this is <=0, then that means that the passed-in * map was not consumed and must be freed. */ -int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn, - int nr_pages) +int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn) { unsigned long section_nr = pfn_to_section_nr(start_pfn); struct pglist_data *pgdat = zone->zone_pgdat; @@ -740,12 +707,12 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn, ret = sparse_index_init(section_nr, pgdat->node_id); if (ret < 0 && ret != -EEXIST) return ret; - memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages); + memmap = kmalloc_section_memmap(section_nr, pgdat->node_id); if (!memmap) return -ENOMEM; usemap = __kmalloc_section_usemap(); if (!usemap) { - __kfree_section_memmap(memmap, nr_pages); + __kfree_section_memmap(memmap); return -ENOMEM; } @@ -757,7 +724,7 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn, goto out; } - memset(memmap, 0, sizeof(struct page) * nr_pages); + memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION); ms->section_mem_map |= SECTION_MARKED_PRESENT; @@ -767,11 +734,12 @@ out: pgdat_resize_unlock(pgdat, &flags); if (ret <= 0) { kfree(usemap); - __kfree_section_memmap(memmap, nr_pages); + __kfree_section_memmap(memmap); } return ret; } +#ifdef CONFIG_MEMORY_HOTREMOVE #ifdef CONFIG_MEMORY_FAILURE static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) { @@ -782,7 +750,7 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) for (i = 0; i < PAGES_PER_SECTION; i++) { if (PageHWPoison(&memmap[i])) { - atomic_long_sub(1, &mce_bad_pages); + atomic_long_sub(1, &num_poisoned_pages); ClearPageHWPoison(&memmap[i]); } } @@ -793,11 +761,40 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) } #endif +static void free_section_usemap(struct page *memmap, unsigned long *usemap) +{ + struct page *usemap_page; + + if (!usemap) + return; + + usemap_page = virt_to_page(usemap); + /* + * Check to see if allocation came from hot-plug-add + */ + if (PageSlab(usemap_page) || PageCompound(usemap_page)) { + kfree(usemap); + if (memmap) + __kfree_section_memmap(memmap); + return; + } + + /* + * The usemap came from bootmem. This is packed with other usemaps + * on the section which has pgdat at boot time. Just keep it as is now. + */ + + if (memmap) + free_map_bootmem(memmap); +} + void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) { struct page *memmap = NULL; - unsigned long *usemap = NULL; + unsigned long *usemap = NULL, flags; + struct pglist_data *pgdat = zone->zone_pgdat; + pgdat_resize_lock(pgdat, &flags); if (ms->section_mem_map) { usemap = ms->pageblock_flags; memmap = sparse_decode_mem_map(ms->section_mem_map, @@ -805,8 +802,10 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) ms->section_mem_map = 0; ms->pageblock_flags = NULL; } + pgdat_resize_unlock(pgdat, &flags); clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION); free_section_usemap(memmap, usemap); } -#endif +#endif /* CONFIG_MEMORY_HOTREMOVE */ +#endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/mm/swap.c b/mm/swap.c index 6310dc2008f..9e8e3472248 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -30,13 +30,17 @@ #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> +#include <linux/uio.h> #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/pagemap.h> + /* How many pages do we try to swap or page in/out together? */ int page_cluster; -static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs); +static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); @@ -53,7 +57,7 @@ static void __page_cache_release(struct page *page) spin_lock_irqsave(&zone->lru_lock, flags); lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(!PageLRU(page)); + VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); spin_unlock_irqrestore(&zone->lru_lock, flags); @@ -63,7 +67,7 @@ static void __page_cache_release(struct page *page) static void __put_single_page(struct page *page) { __page_cache_release(page); - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } static void __put_compound_page(struct page *page) @@ -75,86 +79,185 @@ static void __put_compound_page(struct page *page) (*dtor)(page); } -static void put_compound_page(struct page *page) +/** + * Two special cases here: we could avoid taking compound_lock_irqsave + * and could skip the tail refcounting(in _mapcount). + * + * 1. Hugetlbfs page: + * + * PageHeadHuge will remain true until the compound page + * is released and enters the buddy allocator, and it could + * not be split by __split_huge_page_refcount(). + * + * So if we see PageHeadHuge set, and we have the tail page pin, + * then we could safely put head page. + * + * 2. Slab THP page: + * + * PG_slab is cleared before the slab frees the head page, and + * tail pin cannot be the last reference left on the head page, + * because the slab code is free to reuse the compound page + * after a kfree/kmem_cache_free without having to check if + * there's any tail pin left. In turn all tail pinsmust be always + * released while the head is still pinned by the slab code + * and so we know PG_slab will be still set too. + * + * So if we see PageSlab set, and we have the tail page pin, + * then we could safely put head page. + */ +static __always_inline +void put_unrefcounted_compound_page(struct page *page_head, struct page *page) { - if (unlikely(PageTail(page))) { - /* __split_huge_page_refcount can run under us */ - struct page *page_head = compound_trans_head(page); - - if (likely(page != page_head && - get_page_unless_zero(page_head))) { - unsigned long flags; - - /* - * THP can not break up slab pages so avoid taking - * compound_lock(). Slab performs non-atomic bit ops - * on page->flags for better performance. In particular - * slab_unlock() in slub used to be a hot path. It is - * still hot on arches that do not support - * this_cpu_cmpxchg_double(). - */ - if (PageSlab(page_head)) { - if (PageTail(page)) { - if (put_page_testzero(page_head)) - VM_BUG_ON(1); - - atomic_dec(&page->_mapcount); - goto skip_lock_tail; - } else - goto skip_lock; - } - /* - * page_head wasn't a dangling pointer but it - * may not be a head page anymore by the time - * we obtain the lock. That is ok as long as it - * can't be freed from under us. - */ - flags = compound_lock_irqsave(page_head); - if (unlikely(!PageTail(page))) { - /* __split_huge_page_refcount run before us */ - compound_unlock_irqrestore(page_head, flags); -skip_lock: - if (put_page_testzero(page_head)) - __put_single_page(page_head); -out_put_single: - if (put_page_testzero(page)) - __put_single_page(page); - return; - } - VM_BUG_ON(page_head != page->first_page); + /* + * If @page is a THP tail, we must read the tail page + * flags after the head page flags. The + * __split_huge_page_refcount side enforces write memory barriers + * between clearing PageTail and before the head page + * can be freed and reallocated. + */ + smp_rmb(); + if (likely(PageTail(page))) { + /* + * __split_huge_page_refcount cannot race + * here, see the comment above this function. + */ + VM_BUG_ON_PAGE(!PageHead(page_head), page_head); + VM_BUG_ON_PAGE(page_mapcount(page) != 0, page); + if (put_page_testzero(page_head)) { /* - * We can release the refcount taken by - * get_page_unless_zero() now that - * __split_huge_page_refcount() is blocked on - * the compound_lock. + * If this is the tail of a slab THP page, + * the tail pin must not be the last reference + * held on the page, because the PG_slab cannot + * be cleared before all tail pins (which skips + * the _mapcount tail refcounting) have been + * released. + * + * If this is the tail of a hugetlbfs page, + * the tail pin may be the last reference on + * the page instead, because PageHeadHuge will + * not go away until the compound page enters + * the buddy allocator. */ - if (put_page_testzero(page_head)) - VM_BUG_ON(1); - /* __split_huge_page_refcount will wait now */ - VM_BUG_ON(page_mapcount(page) <= 0); - atomic_dec(&page->_mapcount); - VM_BUG_ON(atomic_read(&page_head->_count) <= 0); - VM_BUG_ON(atomic_read(&page->_count) != 0); - compound_unlock_irqrestore(page_head, flags); + VM_BUG_ON_PAGE(PageSlab(page_head), page_head); + __put_compound_page(page_head); + } + } else + /* + * __split_huge_page_refcount run before us, + * @page was a THP tail. The split @page_head + * has been freed and reallocated as slab or + * hugetlbfs page of smaller order (only + * possible if reallocated as slab on x86). + */ + if (put_page_testzero(page)) + __put_single_page(page); +} -skip_lock_tail: +static __always_inline +void put_refcounted_compound_page(struct page *page_head, struct page *page) +{ + if (likely(page != page_head && get_page_unless_zero(page_head))) { + unsigned long flags; + + /* + * @page_head wasn't a dangling pointer but it may not + * be a head page anymore by the time we obtain the + * lock. That is ok as long as it can't be freed from + * under us. + */ + flags = compound_lock_irqsave(page_head); + if (unlikely(!PageTail(page))) { + /* __split_huge_page_refcount run before us */ + compound_unlock_irqrestore(page_head, flags); if (put_page_testzero(page_head)) { + /* + * The @page_head may have been freed + * and reallocated as a compound page + * of smaller order and then freed + * again. All we know is that it + * cannot have become: a THP page, a + * compound page of higher order, a + * tail page. That is because we + * still hold the refcount of the + * split THP tail and page_head was + * the THP head before the split. + */ if (PageHead(page_head)) __put_compound_page(page_head); else __put_single_page(page_head); } - } else { - /* page_head is a dangling pointer */ - VM_BUG_ON(PageTail(page)); - goto out_put_single; +out_put_single: + if (put_page_testzero(page)) + __put_single_page(page); + return; } - } else if (put_page_testzero(page)) { - if (PageHead(page)) - __put_compound_page(page); - else - __put_single_page(page); + VM_BUG_ON_PAGE(page_head != page->first_page, page); + /* + * We can release the refcount taken by + * get_page_unless_zero() now that + * __split_huge_page_refcount() is blocked on the + * compound_lock. + */ + if (put_page_testzero(page_head)) + VM_BUG_ON_PAGE(1, page_head); + /* __split_huge_page_refcount will wait now */ + VM_BUG_ON_PAGE(page_mapcount(page) <= 0, page); + atomic_dec(&page->_mapcount); + VM_BUG_ON_PAGE(atomic_read(&page_head->_count) <= 0, page_head); + VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page); + compound_unlock_irqrestore(page_head, flags); + + if (put_page_testzero(page_head)) { + if (PageHead(page_head)) + __put_compound_page(page_head); + else + __put_single_page(page_head); + } + } else { + /* @page_head is a dangling pointer */ + VM_BUG_ON_PAGE(PageTail(page), page); + goto out_put_single; + } +} + +static void put_compound_page(struct page *page) +{ + struct page *page_head; + + /* + * We see the PageCompound set and PageTail not set, so @page maybe: + * 1. hugetlbfs head page, or + * 2. THP head page. + */ + if (likely(!PageTail(page))) { + if (put_page_testzero(page)) { + /* + * By the time all refcounts have been released + * split_huge_page cannot run anymore from under us. + */ + if (PageHead(page)) + __put_compound_page(page); + else + __put_single_page(page); + } + return; } + + /* + * We see the PageCompound set and PageTail set, so @page maybe: + * 1. a tail hugetlbfs page, or + * 2. a tail THP page, or + * 3. a split THP page. + * + * Case 3 is possible, as we may race with + * __split_huge_page_refcount tearing down a THP page. + */ + page_head = compound_head_by_tail(page); + if (!__compound_tail_refcounted(page_head)) + put_unrefcounted_compound_page(page_head, page); + else + put_refcounted_compound_page(page_head, page); } void put_page(struct page *page) @@ -181,22 +284,37 @@ bool __get_page_tail(struct page *page) * split_huge_page(). */ unsigned long flags; - bool got = false; - struct page *page_head = compound_trans_head(page); - - if (likely(page != page_head && get_page_unless_zero(page_head))) { + bool got; + struct page *page_head = compound_head(page); - /* Ref to put_compound_page() comment. */ - if (PageSlab(page_head)) { - if (likely(PageTail(page))) { - __get_page_tail_foll(page, false); - return true; - } else { - put_page(page_head); - return false; - } + /* Ref to put_compound_page() comment. */ + if (!__compound_tail_refcounted(page_head)) { + smp_rmb(); + if (likely(PageTail(page))) { + /* + * This is a hugetlbfs page or a slab + * page. __split_huge_page_refcount + * cannot race here. + */ + VM_BUG_ON_PAGE(!PageHead(page_head), page_head); + __get_page_tail_foll(page, true); + return true; + } else { + /* + * __split_huge_page_refcount run + * before us, "page" was a THP + * tail. The split page_head has been + * freed and reallocated as slab or + * hugetlbfs page of smaller order + * (only possible if reallocated as + * slab on x86). + */ + return false; } + } + got = false; + if (likely(page != page_head && get_page_unless_zero(page_head))) { /* * page_head wasn't a dangling pointer but it * may not be a head page anymore by the time @@ -355,7 +473,7 @@ void rotate_reclaimable_page(struct page *page) page_cache_get(page); local_irq_save(flags); - pvec = &__get_cpu_var(lru_rotate_pvecs); + pvec = this_cpu_ptr(&lru_rotate_pvecs); if (!pagevec_add(pvec, page)) pagevec_move_tail(pvec); local_irq_restore(flags); @@ -383,6 +501,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec, SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); + trace_mm_lru_activate(page, page_to_pfn(page)); __count_vm_event(PGACTIVATE); update_page_reclaim_stat(lruvec, file, 1); @@ -400,6 +519,11 @@ static void activate_page_drain(int cpu) pagevec_lru_move_fn(pvec, __activate_page, NULL); } +static bool need_activate_page_drain(int cpu) +{ + return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0; +} + void activate_page(struct page *page) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { @@ -417,6 +541,11 @@ static inline void activate_page_drain(int cpu) { } +static bool need_activate_page_drain(int cpu) +{ + return false; +} + void activate_page(struct page *page) { struct zone *zone = page_zone(page); @@ -427,6 +556,33 @@ void activate_page(struct page *page) } #endif +static void __lru_cache_activate_page(struct page *page) +{ + struct pagevec *pvec = &get_cpu_var(lru_add_pvec); + int i; + + /* + * Search backwards on the optimistic assumption that the page being + * activated has just been added to this pagevec. Note that only + * the local pagevec is examined as a !PageLRU page could be in the + * process of being released, reclaimed, migrated or on a remote + * pagevec that is currently being drained. Furthermore, marking + * a remote pagevec's page PageActive potentially hits a race where + * a page is marked PageActive just after it is added to the inactive + * list causing accounting errors and BUG_ON checks to trigger. + */ + for (i = pagevec_count(pvec) - 1; i >= 0; i--) { + struct page *pagevec_page = pvec->pages[i]; + + if (pagevec_page == page) { + SetPageActive(page); + break; + } + } + + put_cpu_var(lru_add_pvec); +} + /* * Mark a page as having seen activity. * @@ -437,9 +593,21 @@ void activate_page(struct page *page) void mark_page_accessed(struct page *page) { if (!PageActive(page) && !PageUnevictable(page) && - PageReferenced(page) && PageLRU(page)) { - activate_page(page); + PageReferenced(page)) { + + /* + * If the page is on the LRU, queue it for activation via + * activate_page_pvecs. Otherwise, assume the page is on a + * pagevec, mark it active and it'll be moved to the active + * LRU on the next drain. + */ + if (PageLRU(page)) + activate_page(page); + else + __lru_cache_activate_page(page); ClearPageReferenced(page); + if (page_is_file_cache(page)) + workingset_activation(page); } else if (!PageReferenced(page)) { SetPageReferenced(page); } @@ -447,42 +615,60 @@ void mark_page_accessed(struct page *page) EXPORT_SYMBOL(mark_page_accessed); /* - * Order of operations is important: flush the pagevec when it's already - * full, not when adding the last page, to make sure that last page is - * not added to the LRU directly when passed to this function. Because - * mark_page_accessed() (called after this when writing) only activates - * pages that are on the LRU, linear writes in subpage chunks would see - * every PAGEVEC_SIZE page activated, which is unexpected. + * Used to mark_page_accessed(page) that is not visible yet and when it is + * still safe to use non-atomic ops */ -void __lru_cache_add(struct page *page, enum lru_list lru) +void init_page_accessed(struct page *page) { - struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru]; + if (!PageReferenced(page)) + __SetPageReferenced(page); +} +EXPORT_SYMBOL(init_page_accessed); + +static void __lru_cache_add(struct page *page) +{ + struct pagevec *pvec = &get_cpu_var(lru_add_pvec); page_cache_get(page); if (!pagevec_space(pvec)) - __pagevec_lru_add(pvec, lru); + __pagevec_lru_add(pvec); pagevec_add(pvec, page); - put_cpu_var(lru_add_pvecs); + put_cpu_var(lru_add_pvec); } -EXPORT_SYMBOL(__lru_cache_add); /** - * lru_cache_add_lru - add a page to a page list - * @page: the page to be added to the LRU. - * @lru: the LRU list to which the page is added. + * lru_cache_add: add a page to the page lists + * @page: the page to add */ -void lru_cache_add_lru(struct page *page, enum lru_list lru) +void lru_cache_add_anon(struct page *page) { - if (PageActive(page)) { - VM_BUG_ON(PageUnevictable(page)); + if (PageActive(page)) ClearPageActive(page); - } else if (PageUnevictable(page)) { - VM_BUG_ON(PageActive(page)); - ClearPageUnevictable(page); - } + __lru_cache_add(page); +} - VM_BUG_ON(PageLRU(page) || PageActive(page) || PageUnevictable(page)); - __lru_cache_add(page, lru); +void lru_cache_add_file(struct page *page) +{ + if (PageActive(page)) + ClearPageActive(page); + __lru_cache_add(page); +} +EXPORT_SYMBOL(lru_cache_add_file); + +/** + * lru_cache_add - add a page to a page list + * @page: the page to be added to the LRU. + * + * Queue the page for addition to the LRU via pagevec. The decision on whether + * to add the page to the [in]active [file|anon] list is deferred until the + * pagevec is drained. This gives a chance for the caller of lru_cache_add() + * have the page added to the active list using mark_page_accessed(). + */ +void lru_cache_add(struct page *page) +{ + VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); + VM_BUG_ON_PAGE(PageLRU(page), page); + __lru_cache_add(page); } /** @@ -502,6 +688,7 @@ void add_page_to_unevictable_list(struct page *page) spin_lock_irq(&zone->lru_lock); lruvec = mem_cgroup_page_lruvec(page, zone); + ClearPageActive(page); SetPageUnevictable(page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE); @@ -582,15 +769,10 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, */ void lru_add_drain_cpu(int cpu) { - struct pagevec *pvecs = per_cpu(lru_add_pvecs, cpu); - struct pagevec *pvec; - int lru; + struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu); - for_each_lru(lru) { - pvec = &pvecs[lru - LRU_BASE]; - if (pagevec_count(pvec)) - __pagevec_lru_add(pvec, lru); - } + if (pagevec_count(pvec)) + __pagevec_lru_add(pvec); pvec = &per_cpu(lru_rotate_pvecs, cpu); if (pagevec_count(pvec)) { @@ -646,12 +828,36 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) lru_add_drain(); } -/* - * Returns 0 for success - */ -int lru_add_drain_all(void) +static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + +void lru_add_drain_all(void) { - return schedule_on_each_cpu(lru_add_drain_per_cpu); + static DEFINE_MUTEX(lock); + static struct cpumask has_work; + int cpu; + + mutex_lock(&lock); + get_online_cpus(); + cpumask_clear(&has_work); + + for_each_online_cpu(cpu) { + struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); + + if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || + pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || + need_activate_page_drain(cpu)) { + INIT_WORK(work, lru_add_drain_per_cpu); + schedule_work_on(cpu, work); + cpumask_set_cpu(cpu, &has_work); + } + } + + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); + + put_online_cpus(); + mutex_unlock(&lock); } /* @@ -667,7 +873,7 @@ int lru_add_drain_all(void) * grabbed the page via the LRU. If it did, give up: shrink_inactive_list() * will free it. */ -void release_pages(struct page **pages, int nr, int cold) +void release_pages(struct page **pages, int nr, bool cold) { int i; LIST_HEAD(pages_to_free); @@ -702,11 +908,14 @@ void release_pages(struct page **pages, int nr, int cold) } lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(!PageLRU(page)); + VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); } + /* Clear Active bit in case of parallel mark_page_accessed */ + __ClearPageActive(page); + list_add(&page->lru, &pages_to_free); } if (zone) @@ -737,37 +946,26 @@ EXPORT_SYMBOL(__pagevec_release); #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* used by __split_huge_page_refcount() */ void lru_add_page_tail(struct page *page, struct page *page_tail, - struct lruvec *lruvec) + struct lruvec *lruvec, struct list_head *list) { - int uninitialized_var(active); - enum lru_list lru; const int file = 0; - VM_BUG_ON(!PageHead(page)); - VM_BUG_ON(PageCompound(page_tail)); - VM_BUG_ON(PageLRU(page_tail)); + VM_BUG_ON_PAGE(!PageHead(page), page); + VM_BUG_ON_PAGE(PageCompound(page_tail), page); + VM_BUG_ON_PAGE(PageLRU(page_tail), page); VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&lruvec_zone(lruvec)->lru_lock)); - SetPageLRU(page_tail); - - if (page_evictable(page_tail)) { - if (PageActive(page)) { - SetPageActive(page_tail); - active = 1; - lru = LRU_ACTIVE_ANON; - } else { - active = 0; - lru = LRU_INACTIVE_ANON; - } - } else { - SetPageUnevictable(page_tail); - lru = LRU_UNEVICTABLE; - } + if (!list) + SetPageLRU(page_tail); if (likely(PageLRU(page))) list_add_tail(&page_tail->lru, &page->lru); - else { + else if (list) { + /* page reclaim is reclaiming a huge page */ + get_page(page_tail); + list_add_tail(&page_tail->lru, list); + } else { struct list_head *list_head; /* * Head page has not yet been counted, as an hpage, @@ -776,47 +974,93 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, * Use the standard add function to put page_tail on the list, * but then correct its position so they all end up in order. */ - add_page_to_lru_list(page_tail, lruvec, lru); + add_page_to_lru_list(page_tail, lruvec, page_lru(page_tail)); list_head = page_tail->lru.prev; list_move_tail(&page_tail->lru, list_head); } if (!PageUnevictable(page)) - update_page_reclaim_stat(lruvec, file, active); + update_page_reclaim_stat(lruvec, file, PageActive(page_tail)); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, void *arg) { - enum lru_list lru = (enum lru_list)arg; - int file = is_file_lru(lru); - int active = is_active_lru(lru); + int file = page_is_file_cache(page); + int active = PageActive(page); + enum lru_list lru = page_lru(page); - VM_BUG_ON(PageActive(page)); - VM_BUG_ON(PageUnevictable(page)); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); - if (active) - SetPageActive(page); add_page_to_lru_list(page, lruvec, lru); update_page_reclaim_stat(lruvec, file, active); + trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page)); } /* * Add the passed pages to the LRU, then drop the caller's refcount * on them. Reinitialises the caller's pagevec. */ -void __pagevec_lru_add(struct pagevec *pvec, enum lru_list lru) +void __pagevec_lru_add(struct pagevec *pvec) { - VM_BUG_ON(is_unevictable_lru(lru)); - - pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, (void *)lru); + pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL); } EXPORT_SYMBOL(__pagevec_lru_add); /** + * pagevec_lookup_entries - gang pagecache lookup + * @pvec: Where the resulting entries are placed + * @mapping: The address_space to search + * @start: The starting entry index + * @nr_entries: The maximum number of entries + * @indices: The cache indices corresponding to the entries in @pvec + * + * pagevec_lookup_entries() will search for and return a group of up + * to @nr_entries pages and shadow entries in the mapping. All + * entries are placed in @pvec. pagevec_lookup_entries() takes a + * reference against actual pages in @pvec. + * + * The search returns a group of mapping-contiguous entries with + * ascending indexes. There may be holes in the indices due to + * not-present entries. + * + * pagevec_lookup_entries() returns the number of entries which were + * found. + */ +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_pages, + pgoff_t *indices) +{ + pvec->nr = find_get_entries(mapping, start, nr_pages, + pvec->pages, indices); + return pagevec_count(pvec); +} + +/** + * pagevec_remove_exceptionals - pagevec exceptionals pruning + * @pvec: The pagevec to prune + * + * pagevec_lookup_entries() fills both pages and exceptional radix + * tree entries into the pagevec. This function prunes all + * exceptionals from @pvec without leaving holes, so that it can be + * passed on to page-only pagevec operations. + */ +void pagevec_remove_exceptionals(struct pagevec *pvec) +{ + int i, j; + + for (i = 0, j = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + if (!radix_tree_exceptional_entry(page)) + pvec->pages[j++] = page; + } + pvec->nr = j; +} + +/** * pagevec_lookup - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search @@ -855,9 +1099,15 @@ EXPORT_SYMBOL(pagevec_lookup_tag); void __init swap_setup(void) { unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT); - #ifdef CONFIG_SWAP - bdi_init(swapper_space.backing_dev_info); + int i; + + if (bdi_init(swapper_spaces[0].backing_dev_info)) + panic("Failed to init swap bdi"); + for (i = 0; i < MAX_SWAPFILES; i++) { + spin_lock_init(&swapper_spaces[i].tree_lock); + INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); + } #endif /* Use a smaller cluster for small-memory machines */ diff --git a/mm/swap_state.c b/mm/swap_state.c index 0cb36fb1f61..2972eee184a 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -36,12 +36,12 @@ static struct backing_dev_info swap_backing_dev_info = { .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, }; -struct address_space swapper_space = { - .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), - .tree_lock = __SPIN_LOCK_UNLOCKED(swapper_space.tree_lock), - .a_ops = &swap_aops, - .i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear), - .backing_dev_info = &swap_backing_dev_info, +struct address_space swapper_spaces[MAX_SWAPFILES] = { + [0 ... MAX_SWAPFILES - 1] = { + .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), + .a_ops = &swap_aops, + .backing_dev_info = &swap_backing_dev_info, + } }; #define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0) @@ -53,13 +53,26 @@ static struct { unsigned long find_total; } swap_cache_info; +unsigned long total_swapcache_pages(void) +{ + int i; + unsigned long ret = 0; + + for (i = 0; i < MAX_SWAPFILES; i++) + ret += swapper_spaces[i].nrpages; + return ret; +} + +static atomic_t swapin_readahead_hits = ATOMIC_INIT(4); + void show_swap_cache_info(void) { - printk("%lu pages in swap cache\n", total_swapcache_pages); + printk("%lu pages in swap cache\n", total_swapcache_pages()); printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n", swap_cache_info.add_total, swap_cache_info.del_total, swap_cache_info.find_success, swap_cache_info.find_total); - printk("Free swap = %ldkB\n", nr_swap_pages << (PAGE_SHIFT - 10)); + printk("Free swap = %ldkB\n", + get_nr_swap_pages() << (PAGE_SHIFT - 10)); printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10)); } @@ -67,26 +80,29 @@ void show_swap_cache_info(void) * __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space, * but sets SwapCache flag and private instead of mapping and index. */ -static int __add_to_swap_cache(struct page *page, swp_entry_t entry) +int __add_to_swap_cache(struct page *page, swp_entry_t entry) { int error; + struct address_space *address_space; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageSwapCache(page)); - VM_BUG_ON(!PageSwapBacked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageSwapCache(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); page_cache_get(page); SetPageSwapCache(page); set_page_private(page, entry.val); - spin_lock_irq(&swapper_space.tree_lock); - error = radix_tree_insert(&swapper_space.page_tree, entry.val, page); + address_space = swap_address_space(entry); + spin_lock_irq(&address_space->tree_lock); + error = radix_tree_insert(&address_space->page_tree, + entry.val, page); if (likely(!error)) { - total_swapcache_pages++; + address_space->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(add_total); } - spin_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&address_space->tree_lock); if (unlikely(error)) { /* @@ -108,7 +124,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) { int error; - error = radix_tree_preload(gfp_mask); + error = radix_tree_maybe_preload(gfp_mask); if (!error) { error = __add_to_swap_cache(page, entry); radix_tree_preload_end(); @@ -122,14 +138,19 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) */ void __delete_from_swap_cache(struct page *page) { - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageSwapCache(page)); - VM_BUG_ON(PageWriteback(page)); + swp_entry_t entry; + struct address_space *address_space; - radix_tree_delete(&swapper_space.page_tree, page_private(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + VM_BUG_ON_PAGE(PageWriteback(page), page); + + entry.val = page_private(page); + address_space = swap_address_space(entry); + radix_tree_delete(&address_space->page_tree, page_private(page)); set_page_private(page, 0); ClearPageSwapCache(page); - total_swapcache_pages--; + address_space->nrpages--; __dec_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(del_total); } @@ -141,20 +162,20 @@ void __delete_from_swap_cache(struct page *page) * Allocate swap space for the page and add the page to the * swap cache. Caller needs to hold the page lock. */ -int add_to_swap(struct page *page) +int add_to_swap(struct page *page, struct list_head *list) { swp_entry_t entry; int err; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageUptodate(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageUptodate(page), page); entry = get_swap_page(); if (!entry.val) return 0; if (unlikely(PageTransHuge(page))) - if (unlikely(split_huge_page(page))) { + if (unlikely(split_huge_page_to_list(page, list))) { swapcache_free(entry, NULL); return 0; } @@ -195,12 +216,14 @@ int add_to_swap(struct page *page) void delete_from_swap_cache(struct page *page) { swp_entry_t entry; + struct address_space *address_space; entry.val = page_private(page); - spin_lock_irq(&swapper_space.tree_lock); + address_space = swap_address_space(entry); + spin_lock_irq(&address_space->tree_lock); __delete_from_swap_cache(page); - spin_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&address_space->tree_lock); swapcache_free(entry, page); page_cache_release(page); @@ -247,7 +270,7 @@ void free_pages_and_swap_cache(struct page **pages, int nr) for (i = 0; i < todo; i++) free_swap_cache(pagep[i]); - release_pages(pagep, todo, 0); + release_pages(pagep, todo, false); pagep += todo; nr -= todo; } @@ -263,10 +286,13 @@ struct page * lookup_swap_cache(swp_entry_t entry) { struct page *page; - page = find_get_page(&swapper_space, entry.val); + page = find_get_page(swap_address_space(entry), entry.val); - if (page) + if (page) { INC_CACHE_INFO(find_success); + if (TestClearPageReadahead(page)) + atomic_inc(&swapin_readahead_hits); + } INC_CACHE_INFO(find_total); return page; @@ -290,7 +316,8 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * called after lookup_swap_cache() failed, re-calling * that would confuse statistics. */ - found_page = find_get_page(&swapper_space, entry.val); + found_page = find_get_page(swap_address_space(entry), + entry.val); if (found_page) break; @@ -306,7 +333,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * call radix_tree_preload() while we can wait. */ - err = radix_tree_preload(gfp_mask & GFP_KERNEL); + err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL); if (err) break; @@ -314,8 +341,24 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * Swap entry may have been freed since our caller observed it. */ err = swapcache_prepare(entry); - if (err == -EEXIST) { /* seems racy */ + if (err == -EEXIST) { radix_tree_preload_end(); + /* + * We might race against get_swap_page() and stumble + * across a SWAP_HAS_CACHE swap_map entry whose page + * has not been brought into the swapcache yet, while + * the other end is scheduled away waiting on discard + * I/O completion at scan_swap_map(). + * + * In order to avoid turning this transitory state + * into a permanent loop around this -EEXIST case + * if !CONFIG_PREEMPT and the I/O completion happens + * to be waiting on the CPU waitqueue where we are now + * busy looping, we just conditionally invoke the + * scheduler here, if there are some more important + * tasks to run. + */ + cond_resched(); continue; } if (err) { /* swp entry is obsolete ? */ @@ -351,6 +394,50 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, return found_page; } +static unsigned long swapin_nr_pages(unsigned long offset) +{ + static unsigned long prev_offset; + unsigned int pages, max_pages, last_ra; + static atomic_t last_readahead_pages; + + max_pages = 1 << ACCESS_ONCE(page_cluster); + if (max_pages <= 1) + return 1; + + /* + * This heuristic has been found to work well on both sequential and + * random loads, swapping to hard disk or to SSD: please don't ask + * what the "+ 2" means, it just happens to work well, that's all. + */ + pages = atomic_xchg(&swapin_readahead_hits, 0) + 2; + if (pages == 2) { + /* + * We can have no readahead hits to judge by: but must not get + * stuck here forever, so check for an adjacent offset instead + * (and don't even bother to check whether swap type is same). + */ + if (offset != prev_offset + 1 && offset != prev_offset - 1) + pages = 1; + prev_offset = offset; + } else { + unsigned int roundup = 4; + while (roundup < pages) + roundup <<= 1; + pages = roundup; + } + + if (pages > max_pages) + pages = max_pages; + + /* Don't shrink readahead too fast */ + last_ra = atomic_read(&last_readahead_pages) / 2; + if (pages < last_ra) + pages = last_ra; + atomic_set(&last_readahead_pages, pages); + + return pages; +} + /** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory @@ -374,11 +461,16 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { struct page *page; - unsigned long offset = swp_offset(entry); + unsigned long entry_offset = swp_offset(entry); + unsigned long offset = entry_offset; unsigned long start_offset, end_offset; - unsigned long mask = (1UL << page_cluster) - 1; + unsigned long mask; struct blk_plug plug; + mask = swapin_nr_pages(offset) - 1; + if (!mask) + goto skip; + /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; end_offset = offset | mask; @@ -392,10 +484,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, gfp_mask, vma, addr); if (!page) continue; + if (offset != entry_offset) + SetPageReadahead(page); page_cache_release(page); } blk_finish_plug(&plug); lru_add_drain(); /* Push any new pages onto the LRU now */ +skip: return read_swap_cache_async(entry, gfp_mask, vma, addr); } diff --git a/mm/swapfile.c b/mm/swapfile.c index e97a0e5aea9..4c524f7bd0b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -47,7 +47,8 @@ static sector_t map_swap_entry(swp_entry_t, struct block_device**); DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; -long nr_swap_pages; +atomic_long_t nr_swap_pages; +/* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority; @@ -56,7 +57,26 @@ static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; -struct swap_list_t swap_list = {-1, -1}; +/* + * all active swap_info_structs + * protected with swap_lock, and ordered by priority. + */ +PLIST_HEAD(swap_active_head); + +/* + * all available (active, not full) swap_info_structs + * protected with swap_avail_lock, ordered by priority. + * This is used by get_swap_page() instead of swap_active_head + * because swap_active_head includes all swap_info_structs, + * but get_swap_page() doesn't need to look at full ones. + * This uses its own lock instead of swap_lock because when a + * swap_info_struct changes between not-full/full, it needs to + * add/remove itself to/from this list, but the swap_info_struct->lock + * is held and the locking order requires swap_lock to be taken + * before any swap_info_struct->lock. + */ +static PLIST_HEAD(swap_avail_head); +static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -79,7 +99,7 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) struct page *page; int ret = 0; - page = find_get_page(&swapper_space, entry.val); + page = find_get_page(swap_address_space(entry), entry.val); if (!page) return 0; /* @@ -173,14 +193,296 @@ static void discard_swap_cluster(struct swap_info_struct *si, } } -static int wait_for_discard(void *word) +#define SWAPFILE_CLUSTER 256 +#define LATENCY_LIMIT 256 + +static inline void cluster_set_flag(struct swap_cluster_info *info, + unsigned int flag) { - schedule(); - return 0; + info->flags = flag; } -#define SWAPFILE_CLUSTER 256 -#define LATENCY_LIMIT 256 +static inline unsigned int cluster_count(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_count(struct swap_cluster_info *info, + unsigned int c) +{ + info->data = c; +} + +static inline void cluster_set_count_flag(struct swap_cluster_info *info, + unsigned int c, unsigned int f) +{ + info->flags = f; + info->data = c; +} + +static inline unsigned int cluster_next(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_next(struct swap_cluster_info *info, + unsigned int n) +{ + info->data = n; +} + +static inline void cluster_set_next_flag(struct swap_cluster_info *info, + unsigned int n, unsigned int f) +{ + info->flags = f; + info->data = n; +} + +static inline bool cluster_is_free(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_FREE; +} + +static inline bool cluster_is_null(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_NEXT_NULL; +} + +static inline void cluster_set_null(struct swap_cluster_info *info) +{ + info->flags = CLUSTER_FLAG_NEXT_NULL; + info->data = 0; +} + +/* Add a cluster to discard list and schedule it to do discard */ +static void swap_cluster_schedule_discard(struct swap_info_struct *si, + unsigned int idx) +{ + /* + * If scan_swap_map() can't find a free cluster, it will check + * si->swap_map directly. To make sure the discarding cluster isn't + * taken by scan_swap_map(), mark the swap entries bad (occupied). It + * will be cleared after discard + */ + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + SWAP_MAP_BAD, SWAPFILE_CLUSTER); + + if (cluster_is_null(&si->discard_cluster_head)) { + cluster_set_next_flag(&si->discard_cluster_head, + idx, 0); + cluster_set_next_flag(&si->discard_cluster_tail, + idx, 0); + } else { + unsigned int tail = cluster_next(&si->discard_cluster_tail); + cluster_set_next(&si->cluster_info[tail], idx); + cluster_set_next_flag(&si->discard_cluster_tail, + idx, 0); + } + + schedule_work(&si->discard_work); +} + +/* + * Doing discard actually. After a cluster discard is finished, the cluster + * will be added to free cluster list. caller should hold si->lock. +*/ +static void swap_do_scheduled_discard(struct swap_info_struct *si) +{ + struct swap_cluster_info *info; + unsigned int idx; + + info = si->cluster_info; + + while (!cluster_is_null(&si->discard_cluster_head)) { + idx = cluster_next(&si->discard_cluster_head); + + cluster_set_next_flag(&si->discard_cluster_head, + cluster_next(&info[idx]), 0); + if (cluster_next(&si->discard_cluster_tail) == idx) { + cluster_set_null(&si->discard_cluster_head); + cluster_set_null(&si->discard_cluster_tail); + } + spin_unlock(&si->lock); + + discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, + SWAPFILE_CLUSTER); + + spin_lock(&si->lock); + cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&si->free_cluster_head)) { + cluster_set_next_flag(&si->free_cluster_head, + idx, 0); + cluster_set_next_flag(&si->free_cluster_tail, + idx, 0); + } else { + unsigned int tail; + + tail = cluster_next(&si->free_cluster_tail); + cluster_set_next(&info[tail], idx); + cluster_set_next_flag(&si->free_cluster_tail, + idx, 0); + } + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + 0, SWAPFILE_CLUSTER); + } +} + +static void swap_discard_work(struct work_struct *work) +{ + struct swap_info_struct *si; + + si = container_of(work, struct swap_info_struct, discard_work); + + spin_lock(&si->lock); + swap_do_scheduled_discard(si); + spin_unlock(&si->lock); +} + +/* + * The cluster corresponding to page_nr will be used. The cluster will be + * removed from free cluster list and its usage counter will be increased. + */ +static void inc_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + if (cluster_is_free(&cluster_info[idx])) { + VM_BUG_ON(cluster_next(&p->free_cluster_head) != idx); + cluster_set_next_flag(&p->free_cluster_head, + cluster_next(&cluster_info[idx]), 0); + if (cluster_next(&p->free_cluster_tail) == idx) { + cluster_set_null(&p->free_cluster_tail); + cluster_set_null(&p->free_cluster_head); + } + cluster_set_count_flag(&cluster_info[idx], 0, 0); + } + + VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) + 1); +} + +/* + * The cluster corresponding to page_nr decreases one usage. If the usage + * counter becomes 0, which means no page in the cluster is in using, we can + * optionally discard the cluster and add it to free cluster list. + */ +static void dec_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + + VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) - 1); + + if (cluster_count(&cluster_info[idx]) == 0) { + /* + * If the swap is discardable, prepare discard the cluster + * instead of free it immediately. The cluster will be freed + * after discard. + */ + if ((p->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == + (SWP_WRITEOK | SWP_PAGE_DISCARD)) { + swap_cluster_schedule_discard(p, idx); + return; + } + + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&p->free_cluster_head)) { + cluster_set_next_flag(&p->free_cluster_head, idx, 0); + cluster_set_next_flag(&p->free_cluster_tail, idx, 0); + } else { + unsigned int tail = cluster_next(&p->free_cluster_tail); + cluster_set_next(&cluster_info[tail], idx); + cluster_set_next_flag(&p->free_cluster_tail, idx, 0); + } + } +} + +/* + * It's possible scan_swap_map() uses a free cluster in the middle of free + * cluster list. Avoiding such abuse to avoid list corruption. + */ +static bool +scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, + unsigned long offset) +{ + struct percpu_cluster *percpu_cluster; + bool conflict; + + offset /= SWAPFILE_CLUSTER; + conflict = !cluster_is_null(&si->free_cluster_head) && + offset != cluster_next(&si->free_cluster_head) && + cluster_is_free(&si->cluster_info[offset]); + + if (!conflict) + return false; + + percpu_cluster = this_cpu_ptr(si->percpu_cluster); + cluster_set_null(&percpu_cluster->index); + return true; +} + +/* + * Try to get a swap entry from current cpu's swap entry pool (a cluster). This + * might involve allocating a new cluster for current CPU too. + */ +static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, + unsigned long *offset, unsigned long *scan_base) +{ + struct percpu_cluster *cluster; + bool found_free; + unsigned long tmp; + +new_cluster: + cluster = this_cpu_ptr(si->percpu_cluster); + if (cluster_is_null(&cluster->index)) { + if (!cluster_is_null(&si->free_cluster_head)) { + cluster->index = si->free_cluster_head; + cluster->next = cluster_next(&cluster->index) * + SWAPFILE_CLUSTER; + } else if (!cluster_is_null(&si->discard_cluster_head)) { + /* + * we don't have free cluster but have some clusters in + * discarding, do discard now and reclaim them + */ + swap_do_scheduled_discard(si); + *scan_base = *offset = si->cluster_next; + goto new_cluster; + } else + return; + } + + found_free = false; + + /* + * Other CPUs can use our cluster if they can't find a free cluster, + * check if there is still free entry in the cluster + */ + tmp = cluster->next; + while (tmp < si->max && tmp < (cluster_next(&cluster->index) + 1) * + SWAPFILE_CLUSTER) { + if (!si->swap_map[tmp]) { + found_free = true; + break; + } + tmp++; + } + if (!found_free) { + cluster_set_null(&cluster->index); + goto new_cluster; + } + cluster->next = tmp + 1; + *offset = tmp; + *scan_base = tmp; +} static unsigned long scan_swap_map(struct swap_info_struct *si, unsigned char usage) @@ -189,7 +491,6 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; - int found_free_cluster = 0; /* * We try to cluster swap pages by allocating them sequentially @@ -205,36 +506,27 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, si->flags += SWP_SCANNING; scan_base = offset = si->cluster_next; + /* SSD algorithm */ + if (si->cluster_info) { + scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + goto checks; + } + if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } - if (si->flags & SWP_DISCARDABLE) { - /* - * Start range check on racing allocations, in case - * they overlap the cluster we eventually decide on - * (we scan without swap_lock to allow preemption). - * It's hardly conceivable that cluster_nr could be - * wrapped during our scan, but don't depend on it. - */ - if (si->lowest_alloc) - goto checks; - si->lowest_alloc = si->max; - si->highest_alloc = 0; - } - spin_unlock(&swap_lock); + + spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. - * But if seek is cheap, search from our current position, so - * that swap is allocated from all over the partition: if the - * Flash Translation Layer only remaps within limited zones, - * we don't want to wear out the first zone too quickly. + * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info + * case, just handled by scan_swap_map_try_ssd_cluster() above. */ - if (!(si->flags & SWP_SOLIDSTATE)) - scan_base = offset = si->lowest_bit; + scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ @@ -242,32 +534,10 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { - spin_lock(&swap_lock); + spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; - goto checks; - } - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; - } - } - - offset = si->lowest_bit; - last_in_cluster = offset + SWAPFILE_CLUSTER - 1; - - /* Locate the first empty (unaligned) cluster */ - for (; last_in_cluster < scan_base; offset++) { - if (si->swap_map[offset]) - last_in_cluster = offset + SWAPFILE_CLUSTER; - else if (offset == last_in_cluster) { - spin_lock(&swap_lock); - offset -= SWAPFILE_CLUSTER - 1; - si->cluster_next = offset; - si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; goto checks; } if (unlikely(--latency_ration < 0)) { @@ -277,12 +547,15 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, } offset = scan_base; - spin_lock(&swap_lock); + spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; - si->lowest_alloc = 0; } checks: + if (si->cluster_info) { + while (scan_swap_map_ssd_cluster_conflict(si, offset)) + scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) @@ -293,9 +566,9 @@ checks: /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; - spin_unlock(&swap_lock); + spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset); - spin_lock(&swap_lock); + spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; @@ -313,75 +586,26 @@ checks: if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; + spin_lock(&swap_avail_lock); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } si->swap_map[offset] = usage; + inc_cluster_info_page(si, si->cluster_info, offset); si->cluster_next = offset + 1; si->flags -= SWP_SCANNING; - if (si->lowest_alloc) { - /* - * Only set when SWP_DISCARDABLE, and there's a scan - * for a free cluster in progress or just completed. - */ - if (found_free_cluster) { - /* - * To optimize wear-levelling, discard the - * old data of the cluster, taking care not to - * discard any of its pages that have already - * been allocated by racing tasks (offset has - * already stepped over any at the beginning). - */ - if (offset < si->highest_alloc && - si->lowest_alloc <= last_in_cluster) - last_in_cluster = si->lowest_alloc - 1; - si->flags |= SWP_DISCARDING; - spin_unlock(&swap_lock); - - if (offset < last_in_cluster) - discard_swap_cluster(si, offset, - last_in_cluster - offset + 1); - - spin_lock(&swap_lock); - si->lowest_alloc = 0; - si->flags &= ~SWP_DISCARDING; - - smp_mb(); /* wake_up_bit advises this */ - wake_up_bit(&si->flags, ilog2(SWP_DISCARDING)); - - } else if (si->flags & SWP_DISCARDING) { - /* - * Delay using pages allocated by racing tasks - * until the whole discard has been issued. We - * could defer that delay until swap_writepage, - * but it's easier to keep this self-contained. - */ - spin_unlock(&swap_lock); - wait_on_bit(&si->flags, ilog2(SWP_DISCARDING), - wait_for_discard, TASK_UNINTERRUPTIBLE); - spin_lock(&swap_lock); - } else { - /* - * Note pages allocated by racing tasks while - * scan for a free cluster is in progress, so - * that its final discard can exclude them. - */ - if (offset < si->lowest_alloc) - si->lowest_alloc = offset; - if (offset > si->highest_alloc) - si->highest_alloc = offset; - } - } return offset; scan: - spin_unlock(&swap_lock); + spin_unlock(&si->lock); while (++offset <= si->highest_bit) { if (!si->swap_map[offset]) { - spin_lock(&swap_lock); + spin_lock(&si->lock); goto checks; } if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { - spin_lock(&swap_lock); + spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { @@ -390,21 +614,22 @@ scan: } } offset = si->lowest_bit; - while (++offset < scan_base) { + while (offset < scan_base) { if (!si->swap_map[offset]) { - spin_lock(&swap_lock); + spin_lock(&si->lock); goto checks; } if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { - spin_lock(&swap_lock); + spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } + offset++; } - spin_lock(&swap_lock); + spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; @@ -413,65 +638,87 @@ no_page: swp_entry_t get_swap_page(void) { - struct swap_info_struct *si; + struct swap_info_struct *si, *next; pgoff_t offset; - int type, next; - int wrapped = 0; - spin_lock(&swap_lock); - if (nr_swap_pages <= 0) + if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; - nr_swap_pages--; - - for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - si = swap_info[type]; - next = si->next; - if (next < 0 || - (!wrapped && si->prio != swap_info[next]->prio)) { - next = swap_list.head; - wrapped++; + atomic_long_dec(&nr_swap_pages); + + spin_lock(&swap_avail_lock); + +start_over: + plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + /* requeue si to after same-priority siblings */ + plist_requeue(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); + spin_lock(&si->lock); + if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + if (plist_node_empty(&si->avail_list)) { + spin_unlock(&si->lock); + goto nextsi; + } + WARN(!si->highest_bit, + "swap_info %d in list but !highest_bit\n", + si->type); + WARN(!(si->flags & SWP_WRITEOK), + "swap_info %d in list but !SWP_WRITEOK\n", + si->type); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&si->lock); + goto nextsi; } - if (!si->highest_bit) - continue; - if (!(si->flags & SWP_WRITEOK)) - continue; - - swap_list.next = next; /* This is called for allocating swap entry for cache */ offset = scan_swap_map(si, SWAP_HAS_CACHE); - if (offset) { - spin_unlock(&swap_lock); - return swp_entry(type, offset); - } - next = swap_list.next; + spin_unlock(&si->lock); + if (offset) + return swp_entry(si->type, offset); + pr_debug("scan_swap_map of si %d failed to find offset\n", + si->type); + spin_lock(&swap_avail_lock); +nextsi: + /* + * if we got here, it's likely that si was almost full before, + * and since scan_swap_map() can drop the si->lock, multiple + * callers probably all tried to get a page from the same si + * and it filled up before we could get one; or, the si filled + * up between us dropping swap_avail_lock and taking si->lock. + * Since we dropped the swap_avail_lock, the swap_avail_head + * list may have been modified; so if next is still in the + * swap_avail_head list then try it, otherwise start over. + */ + if (plist_node_empty(&next->avail_list)) + goto start_over; } - nr_swap_pages++; + spin_unlock(&swap_avail_lock); + + atomic_long_inc(&nr_swap_pages); noswap: - spin_unlock(&swap_lock); return (swp_entry_t) {0}; } -/* The only caller of this function is now susupend routine */ +/* The only caller of this function is now suspend routine */ swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si; pgoff_t offset; - spin_lock(&swap_lock); si = swap_info[type]; + spin_lock(&si->lock); if (si && (si->flags & SWP_WRITEOK)) { - nr_swap_pages--; + atomic_long_dec(&nr_swap_pages); /* This is called for allocating swap entry, not cache */ offset = scan_swap_map(si, 1); if (offset) { - spin_unlock(&swap_lock); + spin_unlock(&si->lock); return swp_entry(type, offset); } - nr_swap_pages++; + atomic_long_inc(&nr_swap_pages); } - spin_unlock(&swap_lock); + spin_unlock(&si->lock); return (swp_entry_t) {0}; } @@ -493,20 +740,20 @@ static struct swap_info_struct *swap_info_get(swp_entry_t entry) goto bad_offset; if (!p->swap_map[offset]) goto bad_free; - spin_lock(&swap_lock); + spin_lock(&p->lock); return p; bad_free: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val); + pr_err("swap_free: %s%08lx\n", Unused_offset, entry.val); goto out; bad_offset: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val); + pr_err("swap_free: %s%08lx\n", Bad_offset, entry.val); goto out; bad_device: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val); + pr_err("swap_free: %s%08lx\n", Unused_file, entry.val); goto out; bad_nofile: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_free: %s%08lx\n", Bad_file, entry.val); out: return NULL; } @@ -549,14 +796,22 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, /* free if no reference */ if (!usage) { + dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; - if (offset > p->highest_bit) + if (offset > p->highest_bit) { + bool was_full = !p->highest_bit; p->highest_bit = offset; - if (swap_list.next >= 0 && - p->prio > swap_info[swap_list.next]->prio) - swap_list.next = p->type; - nr_swap_pages++; + if (was_full && (p->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + WARN_ON(!plist_node_empty(&p->avail_list)); + if (plist_node_empty(&p->avail_list)) + plist_add(&p->avail_list, + &swap_avail_head); + spin_unlock(&swap_avail_lock); + } + } + atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); if (p->flags & SWP_BLKDEV) { @@ -571,7 +826,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, } /* - * Caller has made sure that the swapdevice corresponding to entry + * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free(swp_entry_t entry) @@ -581,7 +836,7 @@ void swap_free(swp_entry_t entry) p = swap_info_get(entry); if (p) { swap_entry_free(p, entry, 1); - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } } @@ -598,7 +853,7 @@ void swapcache_free(swp_entry_t entry, struct page *page) count = swap_entry_free(p, entry, SWAP_HAS_CACHE); if (page) mem_cgroup_uncharge_swapcache(page, entry, count != 0); - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } } @@ -617,7 +872,7 @@ int page_swapcount(struct page *page) p = swap_info_get(entry); if (p) { count = swap_count(p->swap_map[swp_offset(entry)]); - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } return count; } @@ -632,7 +887,7 @@ int reuse_swap_page(struct page *page) { int count; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) return 0; count = page_mapcount(page); @@ -652,7 +907,7 @@ int reuse_swap_page(struct page *page) */ int try_to_free_swap(struct page *page) { - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); if (!PageSwapCache(page)) return 0; @@ -673,7 +928,7 @@ int try_to_free_swap(struct page *page) * original page might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * - * Hibration suspends storage while it is writing the image + * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) @@ -699,13 +954,14 @@ int free_swap_and_cache(swp_entry_t entry) p = swap_info_get(entry); if (p) { if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) { - page = find_get_page(&swapper_space, entry.val); + page = find_get_page(swap_address_space(entry), + entry.val); if (page && !trylock_page(page)) { page_cache_release(page); page = NULL; } } - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } if (page) { /* @@ -803,17 +1059,34 @@ unsigned int count_swap_pages(int type, int free) if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; + spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } + spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ +static inline int maybe_same_pte(pte_t pte, pte_t swp_pte) +{ +#ifdef CONFIG_MEM_SOFT_DIRTY + /* + * When pte keeps soft dirty bit the pte generated + * from swap entry does not has it, still it's same + * pte from logical point of view. + */ + pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte); + return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty); +#else + return pte_same(pte, swp_pte); +#endif +} + /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to @@ -822,11 +1095,17 @@ unsigned int count_swap_pages(int type, int free) static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { + struct page *swapcache; struct mem_cgroup *memcg; spinlock_t *ptl; pte_t *pte; int ret = 1; + swapcache = page; + page = ksm_might_need_to_copy(page, vma, addr); + if (unlikely(!page)) + return -ENOMEM; + if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &memcg)) { ret = -ENOMEM; @@ -834,7 +1113,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) { + if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) { mem_cgroup_cancel_charge_swapin(memcg); ret = 0; goto out; @@ -845,7 +1124,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, get_page(page); set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); - page_add_anon_rmap(page, vma, addr); + if (page == swapcache) + page_add_anon_rmap(page, vma, addr); + else /* ksm created a completely new copy */ + page_add_new_anon_rmap(page, vma, addr); mem_cgroup_commit_charge_swapin(page, memcg); swap_free(entry); /* @@ -856,6 +1138,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, out: pte_unmap_unlock(pte, ptl); out_nolock: + if (page != swapcache) { + unlock_page(page); + put_page(page); + } return ret; } @@ -874,7 +1160,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * some architectures (e.g. x86_32 with PAE) we might catch a glimpse * of unmatched parts which look like swp_pte, so unuse_pte must * recheck under pte lock. Scanning without pte lock lets it be - * preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. + * preemptable whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. */ pte = pte_offset_map(pmd, addr); do { @@ -882,7 +1168,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * swapoff spends a _lot_ of time in this loop! * Test inline before going to call unuse_pte. */ - if (unlikely(pte_same(*pte, swp_pte))) { + if (unlikely(maybe_same_pte(*pte, swp_pte))) { pte_unmap(pte); ret = unuse_pte(vma, pmd, addr, entry, page); if (ret) @@ -1027,7 +1313,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, else continue; } - count = si->swap_map[i]; + count = ACCESS_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; } @@ -1047,7 +1333,11 @@ int try_to_unuse(unsigned int type, bool frontswap, { struct swap_info_struct *si = swap_info[type]; struct mm_struct *start_mm; - unsigned char *swap_map; + volatile unsigned char *swap_map; /* swap_map is accessed without + * locking. Mark it as volatile + * to prevent compiler doing + * something odd. + */ unsigned char swcount; struct page *page; swp_entry_t entry; @@ -1098,7 +1388,15 @@ int try_to_unuse(unsigned int type, bool frontswap, * reused since sys_swapoff() already disabled * allocation from here, or alloc_page() failed. */ - if (!*swap_map) + swcount = *swap_map; + /* + * We don't hold lock here, so the swap entry could be + * SWAP_MAP_BAD (when the cluster is discarding). + * Instead of fail out, We can just skip the swap + * entry because swapoff will wait for discarding + * finish anyway. + */ + if (!swcount || swcount == SWAP_MAP_BAD) continue; retval = -ENOMEM; break; @@ -1445,48 +1743,60 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, - unsigned long *frontswap_map) + struct swap_cluster_info *cluster_info) { - int i, prev; - if (prio >= 0) p->prio = prio; else p->prio = --least_priority; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + p->list.prio = -p->prio; + p->avail_list.prio = -p->prio; p->swap_map = swap_map; - frontswap_map_set(p, frontswap_map); + p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; - nr_swap_pages += p->pages; + atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; - /* insert swap space into swap_list: */ - prev = -1; - for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { - if (p->prio >= swap_info[i]->prio) - break; - prev = i; - } - p->next = i; - if (prev < 0) - swap_list.head = swap_list.next = p->type; - else - swap_info[prev]->next = p->type; + assert_spin_locked(&swap_lock); + /* + * both lists are plists, and thus priority ordered. + * swap_active_head needs to be priority ordered for swapoff(), + * which on removal of any swap_info_struct with an auto-assigned + * (i.e. negative) priority increments the auto-assigned priority + * of any lower-priority swap_info_structs. + * swap_avail_head needs to be priority ordered for get_swap_page(), + * which allocates swap pages from the highest available priority + * swap_info_struct. + */ + plist_add(&p->list, &swap_active_head); + spin_lock(&swap_avail_lock); + plist_add(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, + struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { + frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); - _enable_swap_info(p, prio, swap_map, frontswap_map); - frontswap_init(p->type); + spin_lock(&p->lock); + _enable_swap_info(p, prio, swap_map, cluster_info); + spin_unlock(&p->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); - _enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p)); + spin_lock(&p->lock); + _enable_swap_info(p, p->prio, p->swap_map, p->cluster_info); + spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -1494,12 +1804,14 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; + struct swap_cluster_info *cluster_info; + unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; - int i, type, prev; - int err; + int err, found = 0; + unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1516,17 +1828,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out; mapping = victim->f_mapping; - prev = -1; spin_lock(&swap_lock); - for (type = swap_list.head; type >= 0; type = swap_info[type]->next) { - p = swap_info[type]; + plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { - if (p->swap_file->f_mapping == mapping) + if (p->swap_file->f_mapping == mapping) { + found = 1; break; + } } - prev = type; } - if (type < 0) { + if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; @@ -1538,26 +1849,29 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (prev < 0) - swap_list.head = p->next; - else - swap_info[prev]->next = p->next; - if (type == swap_list.next) { - /* just pick something that's safe... */ - swap_list.next = swap_list.head; - } + spin_lock(&swap_avail_lock); + plist_del(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); + spin_lock(&p->lock); if (p->prio < 0) { - for (i = p->next; i >= 0; i = swap_info[i]->next) - swap_info[i]->prio = p->prio--; + struct swap_info_struct *si = p; + + plist_for_each_entry_continue(si, &swap_active_head, list) { + si->prio++; + si->list.prio--; + si->avail_list.prio--; + } least_priority++; } - nr_swap_pages -= p->pages; + plist_del(&p->list, &swap_active_head); + atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; + spin_unlock(&p->lock); spin_unlock(&swap_lock); set_current_oom_origin(); - err = try_to_unuse(type, false, 0); /* force all pages to be unused */ + err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { @@ -1566,40 +1880,53 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out_dput; } + flush_work(&p->discard_work); + destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); + spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { + spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); + spin_lock(&p->lock); } swap_file = p->swap_file; + old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; - p->flags = 0; - frontswap_invalidate_area(type); + cluster_info = p->cluster_info; + p->cluster_info = NULL; + frontswap_map = frontswap_map_get(p); + spin_unlock(&p->lock); spin_unlock(&swap_lock); + frontswap_invalidate_area(p->type); + frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; vfree(swap_map); - vfree(frontswap_map_get(p)); - /* Destroy swap account informatin */ - swap_cgroup_swapoff(type); + vfree(cluster_info); + vfree(frontswap_map); + /* Destroy swap account information */ + swap_cgroup_swapoff(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); - set_blocksize(bdev, p->old_block_size); + set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } else { mutex_lock(&inode->i_mutex); @@ -1607,6 +1934,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) mutex_unlock(&inode->i_mutex); } filp_close(swap_file, NULL); + + /* + * Clear the SWP_USED flag after all resources are freed so that swapon + * can reuse this swap_info in alloc_swap_info() safely. It is ok to + * not hold p->lock after we cleared its SWP_WRITEOK. + */ + spin_lock(&swap_lock); + p->flags = 0; + spin_unlock(&swap_lock); + err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); @@ -1699,7 +2036,7 @@ static int swap_show(struct seq_file *swap, void *v) len = seq_path(swap, &file->f_path, " \t\n\\"); seq_printf(swap, "%*s%s\t%u\t%u\t%d\n", len < 40 ? 40 - len : 1, " ", - S_ISBLK(file->f_path.dentry->d_inode->i_mode) ? + S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", si->pages << (PAGE_SHIFT - 10), si->inuse_pages << (PAGE_SHIFT - 10), @@ -1791,9 +2128,11 @@ static struct swap_info_struct *alloc_swap_info(void) */ } INIT_LIST_HEAD(&p->first_swap_extent.list); + plist_node_init(&p->list, 0); + plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; - p->next = -1; spin_unlock(&swap_lock); + spin_lock_init(&p->lock); return p; } @@ -1834,9 +2173,10 @@ static unsigned long read_swap_header(struct swap_info_struct *p, int i; unsigned long maxpages; unsigned long swapfilepages; + unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { - printk(KERN_ERR "Unable to find swap-space signature\n"); + pr_err("Unable to find swap-space signature\n"); return 0; } @@ -1850,9 +2190,8 @@ static unsigned long read_swap_header(struct swap_info_struct *p, } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { - printk(KERN_WARNING - "Unable to handle swap header version %d\n", - swap_header->info.version); + pr_warn("Unable to handle swap header version %d\n", + swap_header->info.version); return 0; } @@ -1876,8 +2215,14 @@ static unsigned long read_swap_header(struct swap_info_struct *p, */ maxpages = swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; - if (maxpages > swap_header->info.last_page) { - maxpages = swap_header->info.last_page + 1; + last_page = swap_header->info.last_page; + if (last_page > maxpages) { + pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", + maxpages << (PAGE_SHIFT - 10), + last_page << (PAGE_SHIFT - 10)); + } + if (maxpages > last_page) { + maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; @@ -1888,8 +2233,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { - printk(KERN_WARNING - "Swap area shorter than signature indicates\n"); + pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) @@ -1903,15 +2247,23 @@ static unsigned long read_swap_header(struct swap_info_struct *p, static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, + struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { int i; unsigned int nr_good_pages; int nr_extents; + unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); + unsigned long idx = p->cluster_next / SWAPFILE_CLUSTER; nr_good_pages = maxpages - 1; /* omit header page */ + cluster_set_null(&p->free_cluster_head); + cluster_set_null(&p->free_cluster_tail); + cluster_set_null(&p->discard_cluster_head); + cluster_set_null(&p->discard_cluster_tail); + for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) @@ -1919,11 +2271,25 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; + /* + * Haven't marked the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, page_nr); } } + /* Haven't marked the cluster free yet, no list operation involved */ + for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) + inc_cluster_info_page(p, cluster_info, i); + if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; + /* + * Not mark the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); @@ -1932,13 +2298,51 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, nr_good_pages = p->pages; } if (!nr_good_pages) { - printk(KERN_WARNING "Empty swap-file\n"); + pr_warn("Empty swap-file\n"); return -EINVAL; } + if (!cluster_info) + return nr_extents; + + for (i = 0; i < nr_clusters; i++) { + if (!cluster_count(&cluster_info[idx])) { + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&p->free_cluster_head)) { + cluster_set_next_flag(&p->free_cluster_head, + idx, 0); + cluster_set_next_flag(&p->free_cluster_tail, + idx, 0); + } else { + unsigned int tail; + + tail = cluster_next(&p->free_cluster_tail); + cluster_set_next(&cluster_info[tail], idx); + cluster_set_next_flag(&p->free_cluster_tail, + idx, 0); + } + } + idx++; + if (idx == nr_clusters) + idx = 0; + } return nr_extents; } +/* + * Helper to sys_swapon determining if a given swap + * backing device queue supports DISCARD operations. + */ +static bool swap_discardable(struct swap_info_struct *si) +{ + struct request_queue *q = bdev_get_queue(si->bdev); + + if (!q || !blk_queue_discard(q)) + return false; + + return true; +} + SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; @@ -1953,6 +2357,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; + struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; @@ -1967,6 +2372,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (IS_ERR(p)) return PTR_ERR(p); + INIT_WORK(&p->discard_work, swap_discard_work); + name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); @@ -2026,28 +2433,74 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -ENOMEM; goto bad_swap; } + if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { + p->flags |= SWP_SOLIDSTATE; + /* + * select a random position to start with to help wear leveling + * SSD + */ + p->cluster_next = 1 + (prandom_u32() % p->highest_bit); + + cluster_info = vzalloc(DIV_ROUND_UP(maxpages, + SWAPFILE_CLUSTER) * sizeof(*cluster_info)); + if (!cluster_info) { + error = -ENOMEM; + goto bad_swap; + } + p->percpu_cluster = alloc_percpu(struct percpu_cluster); + if (!p->percpu_cluster) { + error = -ENOMEM; + goto bad_swap; + } + for_each_possible_cpu(i) { + struct percpu_cluster *cluster; + cluster = per_cpu_ptr(p->percpu_cluster, i); + cluster_set_null(&cluster->index); + } + } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, - maxpages, &span); + cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap; } /* frontswap enabled? set up bit-per-page map for frontswap */ if (frontswap_enabled) - frontswap_map = vzalloc(maxpages / sizeof(long)); + frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); + + if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { + /* + * When discard is enabled for swap with no particular + * policy flagged, we set all swap discard flags here in + * order to sustain backward compatibility with older + * swapon(8) releases. + */ + p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | + SWP_PAGE_DISCARD); - if (p->bdev) { - if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { - p->flags |= SWP_SOLIDSTATE; - p->cluster_next = 1 + (random32() % p->highest_bit); + /* + * By flagging sys_swapon, a sysadmin can tell us to + * either do single-time area discards only, or to just + * perform discards for released swap page-clusters. + * Now it's time to adjust the p->flags accordingly. + */ + if (swap_flags & SWAP_FLAG_DISCARD_ONCE) + p->flags &= ~SWP_PAGE_DISCARD; + else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) + p->flags &= ~SWP_AREA_DISCARD; + + /* issue a swapon-time discard if it's still required */ + if (p->flags & SWP_AREA_DISCARD) { + int err = discard_swap(p); + if (unlikely(err)) + pr_err("swapon: discard_swap(%p): %d\n", + p, err); } - if ((swap_flags & SWAP_FLAG_DISCARD) && discard_swap(p) == 0) - p->flags |= SWP_DISCARDABLE; } mutex_lock(&swapon_mutex); @@ -2055,14 +2508,16 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; - enable_swap_info(p, prio, swap_map, frontswap_map); + enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); - printk(KERN_INFO "Adding %uk swap on %s. " - "Priority:%d extents:%d across:%lluk %s%s%s\n", + pr_info("Adding %uk swap on %s. " + "Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", + (p->flags & SWP_AREA_DISCARD) ? "s" : "", + (p->flags & SWP_PAGE_DISCARD) ? "c" : "", (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); @@ -2074,6 +2529,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = 0; goto out; bad_swap: + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); @@ -2085,6 +2542,7 @@ bad_swap: p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); + vfree(cluster_info); if (swap_file) { if (inode && S_ISREG(inode->i_mode)) { mutex_unlock(&inode->i_mutex); @@ -2116,7 +2574,7 @@ void si_swapinfo(struct sysinfo *val) if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += si->inuse_pages; } - val->freeswap = nr_swap_pages + nr_to_be_unused; + val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } @@ -2149,11 +2607,21 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) p = swap_info[type]; offset = swp_offset(entry); - spin_lock(&swap_lock); + spin_lock(&p->lock); if (unlikely(offset >= p->max)) goto unlock_out; count = p->swap_map[offset]; + + /* + * swapin_readahead() doesn't check if a swap entry is valid, so the + * swap entry could be SWAP_MAP_BAD. Check here with lock held. + */ + if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { + err = -ENOENT; + goto unlock_out; + } + has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; @@ -2184,12 +2652,12 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) p->swap_map[offset] = count | has_cache; unlock_out: - spin_unlock(&swap_lock); + spin_unlock(&p->lock); out: return err; bad_file: - printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val); goto out; } @@ -2243,7 +2711,7 @@ struct swap_info_struct *page_swap_info(struct page *page) */ struct address_space *__page_file_mapping(struct page *page) { - VM_BUG_ON(!PageSwapCache(page)); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); return page_swap_info(page)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(__page_file_mapping); @@ -2251,7 +2719,7 @@ EXPORT_SYMBOL_GPL(__page_file_mapping); pgoff_t __page_file_index(struct page *page) { swp_entry_t swap = { .val = page_private(page) }; - VM_BUG_ON(!PageSwapCache(page)); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); return swp_offset(swap); } EXPORT_SYMBOL_GPL(__page_file_index); @@ -2309,14 +2777,14 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) } if (!page) { - spin_unlock(&swap_lock); + spin_unlock(&si->lock); return -ENOMEM; } /* * We are fortunate that although vmalloc_to_page uses pte_offset_map, - * no architecture is using highmem pages for kernel pagetables: so it - * will not corrupt the GFP_ATOMIC caller's atomic pagetable kmaps. + * no architecture is using highmem pages for kernel page tables: so it + * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. */ head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; @@ -2357,7 +2825,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out: - spin_unlock(&swap_lock); + spin_unlock(&si->lock); outer: if (page) __free_page(page); diff --git a/mm/truncate.c b/mm/truncate.c index c75b736e54b..eda24730716 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -22,11 +22,51 @@ #include <linux/cleancache.h> #include "internal.h" +static void clear_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + struct radix_tree_node *node; + void **slot; + + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return; + + spin_lock_irq(&mapping->tree_lock); + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot)) + goto unlock; + if (*slot != entry) + goto unlock; + radix_tree_replace_slot(slot, NULL); + mapping->nrshadows--; + if (!node) + goto unlock; + workingset_node_shadows_dec(node); + /* + * Don't track node without shadow entries. + * + * Avoid acquiring the list_lru lock if already untracked. + * The list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && + !list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, &node->private_list); + __radix_tree_delete_node(&mapping->page_tree, node); +unlock: + spin_unlock_irq(&mapping->tree_lock); +} /** * do_invalidatepage - invalidate part or all of a page * @page: the page which is affected - * @offset: the index of the truncation point + * @offset: start of the range to invalidate + * @length: length of the range to invalidate * * do_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. @@ -37,24 +77,18 @@ * 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 do_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) { - void (*invalidatepage)(struct page *, unsigned long); + void (*invalidatepage)(struct page *, unsigned int, unsigned int); + 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) -{ - zero_user_segment(page, partial, PAGE_CACHE_SIZE); - cleancache_invalidate_page(page->mapping, page); - if (page_has_private(page)) - do_invalidatepage(page, partial); + (*invalidatepage)(page, offset, length); } /* @@ -103,7 +137,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) return -EIO; if (page_has_private(page)) - do_invalidatepage(page, 0); + do_invalidatepage(page, 0, PAGE_CACHE_SIZE); cancel_dirty_page(page, PAGE_CACHE_SIZE); @@ -185,11 +219,11 @@ int invalidate_inode_page(struct page *page) * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate - * @lend: offset to which to truncate + * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between - * specified offsets (and zeroing out partial page - * (if lstart is not page aligned)). + * specified offsets (and zeroing out partial pages + * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass @@ -200,37 +234,67 @@ int invalidate_inode_page(struct page *page) * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. + * + * Note that since ->invalidatepage() accepts range to invalidate + * truncate_inode_pages_range is able to handle cases where lend + 1 is not + * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { - const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; - const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1); - struct pagevec pvec; - pgoff_t index; - pgoff_t end; - int i; + pgoff_t start; /* inclusive */ + pgoff_t end; /* exclusive */ + unsigned int partial_start; /* inclusive */ + unsigned int partial_end; /* exclusive */ + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + pgoff_t index; + int i; cleancache_invalidate_inode(mapping); - if (mapping->nrpages == 0) + if (mapping->nrpages == 0 && mapping->nrshadows == 0) return; - BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1)); - end = (lend >> PAGE_CACHE_SHIFT); + /* Offsets within partial pages */ + partial_start = lstart & (PAGE_CACHE_SIZE - 1); + partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1); + + /* + * 'start' and 'end' always covers the range of pages to be fully + * truncated. Partial pages are covered with 'partial_start' at the + * start of the range and 'partial_end' at the end of the range. + * Note that 'end' is exclusive while 'lend' is inclusive. + */ + start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + if (lend == -1) + /* + * lend == -1 indicates end-of-file so we have to set 'end' + * to the highest possible pgoff_t and since the type is + * unsigned we're using -1. + */ + end = -1; + else + end = (lend + 1) >> PAGE_CACHE_SHIFT; pagevec_init(&pvec, 0); index = start; - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index < end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; - if (index > end) + index = indices[i]; + if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -241,33 +305,67 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); index++; } - if (partial) { + if (partial_start) { struct page *page = find_lock_page(mapping, start - 1); if (page) { + unsigned int top = PAGE_CACHE_SIZE; + if (start > end) { + /* Truncation within a single page */ + top = partial_end; + partial_end = 0; + } + wait_on_page_writeback(page); + zero_user_segment(page, partial_start, top); + cleancache_invalidate_page(mapping, page); + if (page_has_private(page)) + do_invalidatepage(page, partial_start, + top - partial_start); + unlock_page(page); + page_cache_release(page); + } + } + if (partial_end) { + struct page *page = find_lock_page(mapping, end); + if (page) { wait_on_page_writeback(page); - truncate_partial_page(page, partial); + zero_user_segment(page, 0, partial_end); + cleancache_invalidate_page(mapping, page); + if (page_has_private(page)) + do_invalidatepage(page, 0, + partial_end); unlock_page(page); page_cache_release(page); } } + /* + * If the truncation happened within a single page no pages + * will be released, just zeroed, so we can bail out now. + */ + if (start >= end) + return; index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + if (!pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { + /* If all gone from start onwards, we're done */ if (index == start) break; + /* Otherwise restart to make sure all gone */ index = start; continue; } - if (index == start && pvec.pages[0]->index > end) { + if (index == start && indices[0] >= end) { + /* All gone out of hole to be punched, we're done */ + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } @@ -276,9 +374,17 @@ void truncate_inode_pages_range(struct address_space *mapping, struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; - if (index > end) + index = indices[i]; + if (index >= end) { + /* Restart punch to make sure all gone */ + index = start - 1; break; + } + + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } lock_page(page); WARN_ON(page->index != index); @@ -286,6 +392,7 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -313,6 +420,53 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) EXPORT_SYMBOL(truncate_inode_pages); /** + * truncate_inode_pages_final - truncate *all* pages before inode dies + * @mapping: mapping to truncate + * + * Called under (and serialized by) inode->i_mutex. + * + * Filesystems have to use this in the .evict_inode path to inform the + * VM that this is the final truncate and the inode is going away. + */ +void truncate_inode_pages_final(struct address_space *mapping) +{ + unsigned long nrshadows; + unsigned long nrpages; + + /* + * Page reclaim can not participate in regular inode lifetime + * management (can't call iput()) and thus can race with the + * inode teardown. Tell it when the address space is exiting, + * so that it does not install eviction information after the + * final truncate has begun. + */ + mapping_set_exiting(mapping); + + /* + * When reclaim installs eviction entries, it increases + * nrshadows first, then decreases nrpages. Make sure we see + * this in the right order or we might miss an entry. + */ + nrpages = mapping->nrpages; + smp_rmb(); + nrshadows = mapping->nrshadows; + + if (nrpages || nrshadows) { + /* + * As truncation uses a lockless tree lookup, cycle + * the tree lock to make sure any ongoing tree + * modification that does not see AS_EXITING is + * completed before starting the final truncate. + */ + spin_lock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); + + truncate_inode_pages(mapping, 0); + } +} +EXPORT_SYMBOL(truncate_inode_pages_final); + +/** * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode * @mapping: the address_space which holds the pages to invalidate * @start: the offset 'from' which to invalidate @@ -328,32 +482,31 @@ EXPORT_SYMBOL(truncate_inode_pages); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; - /* - * Note: this function may get called on a shmem/tmpfs mapping: - * pagevec_lookup() might then return 0 prematurely (because it - * got a gangful of swap entries); but it's hardly worth worrying - * about - it can rarely have anything to free from such a mapping - * (most pages are dirty), and already skips over any difficulties. - */ - pagevec_init(&pvec, 0); - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -367,6 +520,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, deactivate_page(page); count += ret; } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -397,7 +551,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) goto failed; BUG_ON(page_has_private(page)); - __delete_from_page_cache(page); + __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -434,6 +588,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page) int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; @@ -444,17 +599,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cleancache_invalidate_inode(mapping); pagevec_init(&pvec, 0); index = start; - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); if (page->mapping != mapping) { @@ -492,6 +653,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, ret = ret2; unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -520,7 +682,6 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode - * @oldsize: old file size * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache @@ -533,7 +694,7 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ -void truncate_pagecache(struct inode *inode, loff_t oldsize, loff_t newsize) +void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); @@ -567,12 +728,8 @@ EXPORT_SYMBOL(truncate_pagecache); */ void truncate_setsize(struct inode *inode, loff_t newsize) { - loff_t oldsize; - - oldsize = inode->i_size; i_size_write(inode, newsize); - - truncate_pagecache(inode, oldsize, newsize); + truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); @@ -598,10 +755,8 @@ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are - * doing their own page rounding first; and truncate_inode_pages_range - * currently BUGs if lend is not pagealigned-1 (it handles partial - * page at start of hole, but not partial page at end of hole). Note - * unmap_mapping_range allows holelen 0 for all, and we allow lend -1. + * doing their own page rounding first. Note that unmap_mapping_range + * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* diff --git a/mm/util.c b/mm/util.c index c55e26b17d9..d5ea733c508 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1,10 +1,17 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/compiler.h> #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/security.h> +#include <linux/swap.h> +#include <linux/swapops.h> +#include <linux/mman.h> +#include <linux/hugetlb.h> +#include <linux/vmalloc.h> + #include <asm/uaccess.h> #include "internal.h" @@ -293,7 +300,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } #endif @@ -303,7 +309,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) * If the architecture not support this function, simply return with no * page pinned */ -int __attribute__((weak)) __get_user_pages_fast(unsigned long start, +int __weak __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { return 0; @@ -334,7 +340,7 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast); * callers need to carefully consider what to use. On many architectures, * get_user_pages_fast simply falls back to get_user_pages. */ -int __attribute__((weak)) get_user_pages_fast(unsigned long start, +int __weak get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { struct mm_struct *mm = current->mm; @@ -355,12 +361,16 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, { unsigned long ret; struct mm_struct *mm = current->mm; + unsigned long populate; ret = security_mmap_file(file, prot, flag); if (!ret) { down_write(&mm->mmap_sem); - ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff); + ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff, + &populate); up_write(&mm->mmap_sem); + if (populate) + mm_populate(ret, populate); } return ret; } @@ -378,6 +388,123 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, } EXPORT_SYMBOL(vm_mmap); +void kvfree(const void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} +EXPORT_SYMBOL(kvfree); + +struct address_space *page_mapping(struct page *page) +{ + struct address_space *mapping = page->mapping; + + /* This happens if someone calls flush_dcache_page on slab page */ + if (unlikely(PageSlab(page))) + return NULL; + + if (unlikely(PageSwapCache(page))) { + swp_entry_t entry; + + entry.val = page_private(page); + mapping = swap_address_space(entry); + } else if ((unsigned long)mapping & PAGE_MAPPING_ANON) + mapping = NULL; + return mapping; +} + +int overcommit_ratio_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + sysctl_overcommit_kbytes = 0; + return ret; +} + +int overcommit_kbytes_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + sysctl_overcommit_ratio = 0; + return ret; +} + +/* + * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used + */ +unsigned long vm_commit_limit(void) +{ + unsigned long allowed; + + if (sysctl_overcommit_kbytes) + allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); + else + allowed = ((totalram_pages - hugetlb_total_pages()) + * sysctl_overcommit_ratio / 100); + allowed += total_swap_pages; + + return allowed; +} + +/** + * get_cmdline() - copy the cmdline value to a buffer. + * @task: the task whose cmdline value to copy. + * @buffer: the buffer to copy to. + * @buflen: the length of the buffer. Larger cmdline values are truncated + * to this length. + * Returns the size of the cmdline field copied. Note that the copy does + * not guarantee an ending NULL byte. + */ +int get_cmdline(struct task_struct *task, char *buffer, int buflen) +{ + int res = 0; + unsigned int len; + struct mm_struct *mm = get_task_mm(task); + if (!mm) + goto out; + if (!mm->arg_end) + goto out_mm; /* Shh! No looking before we're done */ + + len = mm->arg_end - mm->arg_start; + + if (len > buflen) + len = buflen; + + res = access_process_vm(task, mm->arg_start, buffer, len, 0); + + /* + * If the nul at the end of args has been overwritten, then + * assume application is using setproctitle(3). + */ + if (res > 0 && buffer[res-1] != '\0' && len < buflen) { + len = strnlen(buffer, res); + if (len < res) { + res = len; + } else { + len = mm->env_end - mm->env_start; + if (len > buflen - res) + len = buflen - res; + res += access_process_vm(task, mm->env_start, + buffer+res, len, 0); + res = strnlen(buffer, res); + } + } +out_mm: + mmput(mm); +out: + return res; +} + /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); diff --git a/mm/vmacache.c b/mm/vmacache.c new file mode 100644 index 00000000000..9f25af825de --- /dev/null +++ b/mm/vmacache.c @@ -0,0 +1,132 @@ +/* + * Copyright (C) 2014 Davidlohr Bueso. + */ +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmacache.h> + +/* + * Flush vma caches for threads that share a given mm. + * + * The operation is safe because the caller holds the mmap_sem + * exclusively and other threads accessing the vma cache will + * have mmap_sem held at least for read, so no extra locking + * is required to maintain the vma cache. + */ +void vmacache_flush_all(struct mm_struct *mm) +{ + struct task_struct *g, *p; + + /* + * Single threaded tasks need not iterate the entire + * list of process. We can avoid the flushing as well + * since the mm's seqnum was increased and don't have + * to worry about other threads' seqnum. Current's + * flush will occur upon the next lookup. + */ + if (atomic_read(&mm->mm_users) == 1) + return; + + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * Only flush the vmacache pointers as the + * mm seqnum is already set and curr's will + * be set upon invalidation when the next + * lookup is done. + */ + if (mm == p->mm) + vmacache_flush(p); + } + rcu_read_unlock(); +} + +/* + * This task may be accessing a foreign mm via (for example) + * get_user_pages()->find_vma(). The vmacache is task-local and this + * task's vmacache pertains to a different mm (ie, its own). There is + * nothing we can do here. + * + * Also handle the case where a kernel thread has adopted this mm via use_mm(). + * That kernel thread's vmacache is not applicable to this mm. + */ +static bool vmacache_valid_mm(struct mm_struct *mm) +{ + return current->mm == mm && !(current->flags & PF_KTHREAD); +} + +void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) +{ + if (vmacache_valid_mm(newvma->vm_mm)) + current->vmacache[VMACACHE_HASH(addr)] = newvma; +} + +static bool vmacache_valid(struct mm_struct *mm) +{ + struct task_struct *curr; + + if (!vmacache_valid_mm(mm)) + return false; + + curr = current; + if (mm->vmacache_seqnum != curr->vmacache_seqnum) { + /* + * First attempt will always be invalid, initialize + * the new cache for this task here. + */ + curr->vmacache_seqnum = mm->vmacache_seqnum; + vmacache_flush(curr); + return false; + } + return true; +} + +struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (!vma) + continue; + if (WARN_ON_ONCE(vma->vm_mm != mm)) + break; + if (vma->vm_start <= addr && vma->vm_end > addr) { + count_vm_vmacache_event(VMACACHE_FIND_HITS); + return vma; + } + } + + return NULL; +} + +#ifndef CONFIG_MMU +struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (vma && vma->vm_start == start && vma->vm_end == end) { + count_vm_vmacache_event(VMACACHE_FIND_HITS); + return vma; + } + } + + return NULL; +} +#endif diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5123a169ab7..f64632b6719 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -27,10 +27,32 @@ #include <linux/pfn.h> #include <linux/kmemleak.h> #include <linux/atomic.h> +#include <linux/compiler.h> +#include <linux/llist.h> + #include <asm/uaccess.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> +struct vfree_deferred { + struct llist_head list; + struct work_struct wq; +}; +static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred); + +static void __vunmap(const void *, int); + +static void free_work(struct work_struct *w) +{ + struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); + struct llist_node *llnode = llist_del_all(&p->list); + while (llnode) { + void *p = llnode; + llnode = llist_next(llnode); + __vunmap(p, 1); + } +} + /*** Page table manipulation functions ***/ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end) @@ -249,19 +271,9 @@ EXPORT_SYMBOL(vmalloc_to_pfn); #define VM_LAZY_FREEING 0x02 #define VM_VM_AREA 0x04 -struct vmap_area { - unsigned long va_start; - unsigned long va_end; - unsigned long flags; - struct rb_node rb_node; /* address sorted rbtree */ - struct list_head list; /* address sorted list */ - struct list_head purge_list; /* "lazy purge" list */ - struct vm_struct *vm; - struct rcu_head rcu_head; -}; - static DEFINE_SPINLOCK(vmap_area_lock); -static LIST_HEAD(vmap_area_list); +/* Export for kexec only */ +LIST_HEAD(vmap_area_list); static struct rb_root vmap_area_root = RB_ROOT; /* The vmap cache globals are protected by vmap_area_lock */ @@ -282,7 +294,7 @@ static struct vmap_area *__find_vmap_area(unsigned long addr) va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; - else if (addr > va->va_start) + else if (addr >= va->va_end) n = n->rb_right; else return va; @@ -313,7 +325,7 @@ static void __insert_vmap_area(struct vmap_area *va) rb_link_node(&va->rb_node, parent, p); rb_insert_color(&va->rb_node, &vmap_area_root); - /* address-sort this list so it is usable like the vmlist */ + /* address-sort this list */ tmp = rb_prev(&va->rb_node); if (tmp) { struct vmap_area *prev; @@ -349,6 +361,12 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, if (unlikely(!va)) return ERR_PTR(-ENOMEM); + /* + * Only scan the relevant parts containing pointers to other objects + * to avoid false negatives. + */ + kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK); + retry: spin_lock(&vmap_area_lock); /* @@ -378,12 +396,12 @@ nocache: addr = ALIGN(first->va_end, align); if (addr < vstart) goto nocache; - if (addr + size - 1 < addr) + if (addr + size < addr) goto overflow; } else { addr = ALIGN(vstart, align); - if (addr + size - 1 < addr) + if (addr + size < addr) goto overflow; n = vmap_area_root.rb_node; @@ -410,7 +428,7 @@ nocache: if (addr + cached_hole_size < first->va_start) cached_hole_size = first->va_start - addr; addr = ALIGN(first->va_end, align); - if (addr + size - 1 < addr) + if (addr + size < addr) goto overflow; if (list_is_last(&first->list, &vmap_area_list)) @@ -742,9 +760,7 @@ struct vmap_block_queue { struct vmap_block { spinlock_t lock; struct vmap_area *va; - struct vmap_block_queue *vbq; unsigned long free, dirty; - DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS); DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); struct list_head free_list; struct rcu_head rcu_head; @@ -810,7 +826,6 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) vb->va = va; vb->free = VMAP_BBMAP_BITS; vb->dirty = 0; - bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS); bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS); INIT_LIST_HEAD(&vb->free_list); @@ -822,7 +837,6 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) radix_tree_preload_end(); vbq = &get_cpu_var(vmap_block_queue); - vb->vbq = vbq; spin_lock(&vbq->lock); list_add_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); @@ -863,7 +877,6 @@ static void purge_fragmented_blocks(int cpu) if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) { vb->free = 0; /* prevent further allocs after releasing lock */ vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */ - bitmap_fill(vb->alloc_map, VMAP_BBMAP_BITS); bitmap_fill(vb->dirty_map, VMAP_BBMAP_BITS); spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); @@ -881,11 +894,6 @@ static void purge_fragmented_blocks(int cpu) } } -static void purge_fragmented_blocks_thiscpu(void) -{ - purge_fragmented_blocks(smp_processor_id()); -} - static void purge_fragmented_blocks_allcpus(void) { int cpu; @@ -900,7 +908,6 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) struct vmap_block *vb; unsigned long addr = 0; unsigned int order; - int purge = 0; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -924,17 +931,7 @@ again: if (vb->free < 1UL << order) goto next; - i = bitmap_find_free_region(vb->alloc_map, - VMAP_BBMAP_BITS, order); - - if (i < 0) { - if (vb->free + vb->dirty == VMAP_BBMAP_BITS) { - /* fragmented and no outstanding allocations */ - BUG_ON(vb->dirty != VMAP_BBMAP_BITS); - purge = 1; - } - goto next; - } + i = VMAP_BBMAP_BITS - vb->free; addr = vb->va->va_start + (i << PAGE_SHIFT); BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(vb->va->va_start)); @@ -950,9 +947,6 @@ next: spin_unlock(&vb->lock); } - if (purge) - purge_fragmented_blocks_thiscpu(); - put_cpu_var(vmap_block_queue); rcu_read_unlock(); @@ -1030,15 +1024,16 @@ void vm_unmap_aliases(void) rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { - int i; + int i, j; spin_lock(&vb->lock); i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS); - while (i < VMAP_BBMAP_BITS) { + if (i < VMAP_BBMAP_BITS) { unsigned long s, e; - int j; - j = find_next_zero_bit(vb->dirty_map, - VMAP_BBMAP_BITS, i); + + j = find_last_bit(vb->dirty_map, + VMAP_BBMAP_BITS); + j = j + 1; /* need exclusive index */ s = vb->va->va_start + (i << PAGE_SHIFT); e = vb->va->va_start + (j << PAGE_SHIFT); @@ -1048,10 +1043,6 @@ void vm_unmap_aliases(void) start = s; if (e > end) end = e; - - i = j; - i = find_next_bit(vb->dirty_map, - VMAP_BBMAP_BITS, i); } spin_unlock(&vb->lock); } @@ -1094,6 +1085,12 @@ EXPORT_SYMBOL(vm_unmap_ram); * @node: prefer to allocate data structures on this node * @prot: memory protection to use. PAGE_KERNEL for regular RAM * + * If you use this function for less than VMAP_MAX_ALLOC pages, it could be + * faster than vmap so it's good. But if you mix long-life and short-life + * objects with vm_map_ram(), it could consume lots of address space through + * fragmentation (especially on a 32bit machine). You could see failures in + * the end. Please use this function for short-lived objects. + * * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot) @@ -1125,6 +1122,7 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro } EXPORT_SYMBOL(vm_map_ram); +static struct vm_struct *vmlist __initdata; /** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add @@ -1184,10 +1182,14 @@ void __init vmalloc_init(void) for_each_possible_cpu(i) { struct vmap_block_queue *vbq; + struct vfree_deferred *p; vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); + p = &per_cpu(vfree_deferred, i); + init_llist_head(&p->list); + INIT_WORK(&p->wq, free_work); } /* Import existing vmlist entries. */ @@ -1266,11 +1268,12 @@ void unmap_kernel_range(unsigned long addr, unsigned long size) vunmap_page_range(addr, end); flush_tlb_kernel_range(addr, end); } +EXPORT_SYMBOL_GPL(unmap_kernel_range); int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) { unsigned long addr = (unsigned long)area->addr; - unsigned long end = addr + area->size - PAGE_SIZE; + unsigned long end = addr + get_vm_area_size(area); int err; err = vmap_page_range(addr, end, prot, *pages); @@ -1283,41 +1286,28 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) } EXPORT_SYMBOL_GPL(map_vm_area); -/*** Old vmalloc interfaces ***/ -DEFINE_RWLOCK(vmlist_lock); -struct vm_struct *vmlist; - static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { + spin_lock(&vmap_area_lock); vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->vm = vm; va->flags |= VM_VM_AREA; + spin_unlock(&vmap_area_lock); } -static void insert_vmalloc_vmlist(struct vm_struct *vm) -{ - struct vm_struct *tmp, **p; - - vm->flags &= ~VM_UNLIST; - write_lock(&vmlist_lock); - for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { - if (tmp->addr >= vm->addr) - break; - } - vm->next = *p; - *p = vm; - write_unlock(&vmlist_lock); -} - -static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, const void *caller) +static void clear_vm_uninitialized_flag(struct vm_struct *vm) { - setup_vmalloc_vm(vm, va, flags, caller); - insert_vmalloc_vmlist(vm); + /* + * Before removing VM_UNINITIALIZED, + * we should make sure that vm has proper values. + * Pair with smp_rmb() in show_numa_info(). + */ + smp_wmb(); + vm->flags &= ~VM_UNINITIALIZED; } static struct vm_struct *__get_vm_area_node(unsigned long size, @@ -1328,16 +1318,8 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, struct vm_struct *area; BUG_ON(in_interrupt()); - if (flags & VM_IOREMAP) { - int bit = fls(size); - - if (bit > IOREMAP_MAX_ORDER) - bit = IOREMAP_MAX_ORDER; - else if (bit < PAGE_SHIFT) - bit = PAGE_SHIFT; - - align = 1ul << bit; - } + if (flags & VM_IOREMAP) + align = 1ul << clamp(fls(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); size = PAGE_ALIGN(size); if (unlikely(!size)) @@ -1358,17 +1340,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, return NULL; } - /* - * When this function is called from __vmalloc_node_range, - * we do not add vm_struct to vmlist here to avoid - * accessing uninitialized members of vm_struct such as - * pages and nr_pages fields. They will be set later. - * To distinguish it from others, we use a VM_UNLIST flag. - */ - if (flags & VM_UNLIST) - setup_vmalloc_vm(area, va, flags, caller); - else - insert_vmalloc_vm(area, va, flags, caller); + setup_vmalloc_vm(area, va, flags, caller); return area; } @@ -1376,8 +1348,8 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end) { - return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL, - __builtin_return_address(0)); + return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE, + GFP_KERNEL, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(__get_vm_area); @@ -1385,8 +1357,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { - return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL, - caller); + return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE, + GFP_KERNEL, caller); } /** @@ -1401,14 +1373,15 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, - -1, GFP_KERNEL, __builtin_return_address(0)); + NUMA_NO_NODE, GFP_KERNEL, + __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, - -1, GFP_KERNEL, caller); + NUMA_NO_NODE, GFP_KERNEL, caller); } /** @@ -1446,19 +1419,10 @@ struct vm_struct *remove_vm_area(const void *addr) if (va && va->flags & VM_VM_AREA) { struct vm_struct *vm = va->vm; - if (!(vm->flags & VM_UNLIST)) { - struct vm_struct *tmp, **p; - /* - * remove from list and disallow access to - * this vm_struct before unmap. (address range - * confliction is maintained by vmap.) - */ - write_lock(&vmlist_lock); - for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) - ; - *p = tmp->next; - write_unlock(&vmlist_lock); - } + spin_lock(&vmap_area_lock); + va->vm = NULL; + va->flags &= ~VM_VM_AREA; + spin_unlock(&vmap_area_lock); vmap_debug_free_range(va->va_start, va->va_end); free_unmap_vmap_area(va); @@ -1476,10 +1440,9 @@ static void __vunmap(const void *addr, int deallocate_pages) if (!addr) return; - if ((PAGE_SIZE-1) & (unsigned long)addr) { - WARN(1, KERN_ERR "Trying to vfree() bad address (%p)\n", addr); + if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", + addr)) return; - } area = remove_vm_area(addr); if (unlikely(!area)) { @@ -1510,7 +1473,7 @@ static void __vunmap(const void *addr, int deallocate_pages) kfree(area); return; } - + /** * vfree - release memory allocated by vmalloc() * @addr: memory base address @@ -1519,15 +1482,26 @@ static void __vunmap(const void *addr, int deallocate_pages) * obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is * NULL, no operation is performed. * - * Must not be called in interrupt context. + * Must not be called in NMI context (strictly speaking, only if we don't + * have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling + * conventions for vfree() arch-depenedent would be a really bad idea) + * + * NOTE: assumes that the object at *addr has a size >= sizeof(llist_node) */ void vfree(const void *addr) { - BUG_ON(in_interrupt()); + BUG_ON(in_nmi()); kmemleak_free(addr); - __vunmap(addr, 1); + if (!addr) + return; + if (unlikely(in_interrupt())) { + struct vfree_deferred *p = this_cpu_ptr(&vfree_deferred); + if (llist_add((struct llist_node *)addr, &p->list)) + schedule_work(&p->wq); + } else + __vunmap(addr, 1); } EXPORT_SYMBOL(vfree); @@ -1544,7 +1518,8 @@ void vunmap(const void *addr) { BUG_ON(in_interrupt()); might_sleep(); - __vunmap(addr, 0); + if (addr) + __vunmap(addr, 0); } EXPORT_SYMBOL(vunmap); @@ -1586,27 +1561,26 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, pgprot_t prot, int node, const void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, - pgprot_t prot, int node, const void *caller) + pgprot_t prot, int node) { const int order = 0; struct page **pages; unsigned int nr_pages, array_size, i; gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; - nr_pages = (area->size - PAGE_SIZE) >> PAGE_SHIFT; + nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; array_size = (nr_pages * sizeof(struct page *)); area->nr_pages = nr_pages; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM, - PAGE_KERNEL, node, caller); + PAGE_KERNEL, node, area->caller); area->flags |= VM_VPAGES; } else { pages = kmalloc_node(array_size, nested_gfp, node); } area->pages = pages; - area->caller = caller; if (!area->pages) { remove_vm_area(area->addr); kfree(area); @@ -1617,7 +1591,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; gfp_t tmp_mask = gfp_mask | __GFP_NOWARN; - if (node < 0) + if (node == NUMA_NO_NODE) page = alloc_page(tmp_mask); else page = alloc_pages_node(node, tmp_mask, order); @@ -1650,7 +1624,7 @@ fail: * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages - * @node: node to use for allocation or -1 + * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level @@ -1669,27 +1643,28 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!size || (size >> PAGE_SHIFT) > totalram_pages) goto fail; - area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNLIST, + area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED, start, end, node, gfp_mask, caller); if (!area) goto fail; - addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller); + addr = __vmalloc_area_node(area, gfp_mask, prot, node); if (!addr) return NULL; /* - * In this function, newly allocated vm_struct is not added - * to vmlist at __get_vm_area_node(). so, it is added here. + * In this function, newly allocated vm_struct has VM_UNINITIALIZED + * flag. It means that vm_struct is not fully initialized. + * Now, it is fully initialized, so remove this flag here. */ - insert_vmalloc_vmlist(area); + clear_vm_uninitialized_flag(area); /* - * A ref_count = 3 is needed because the vm_struct and vmap_area - * structures allocated in the __get_vm_area_node() function contain - * references to the virtual address of the vmalloc'ed block. + * A ref_count = 2 is needed because vm_struct allocated in + * __get_vm_area_node() contains a reference to the virtual address of + * the vmalloc'ed block. */ - kmemleak_alloc(addr, real_size, 3, gfp_mask); + kmemleak_alloc(addr, real_size, 2, gfp_mask); return addr; @@ -1706,7 +1681,7 @@ fail: * @align: desired alignment * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages - * @node: node to use for allocation or -1 + * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level @@ -1723,7 +1698,7 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) { - return __vmalloc_node(size, 1, gfp_mask, prot, -1, + return __vmalloc_node(size, 1, gfp_mask, prot, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc); @@ -1746,7 +1721,8 @@ static inline void *__vmalloc_node_flags(unsigned long size, */ void *vmalloc(unsigned long size) { - return __vmalloc_node_flags(size, -1, GFP_KERNEL | __GFP_HIGHMEM); + return __vmalloc_node_flags(size, NUMA_NO_NODE, + GFP_KERNEL | __GFP_HIGHMEM); } EXPORT_SYMBOL(vmalloc); @@ -1762,7 +1738,7 @@ EXPORT_SYMBOL(vmalloc); */ void *vzalloc(unsigned long size) { - return __vmalloc_node_flags(size, -1, + return __vmalloc_node_flags(size, NUMA_NO_NODE, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc); @@ -1781,7 +1757,8 @@ void *vmalloc_user(unsigned long size) ret = __vmalloc_node(size, SHMLBA, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, - PAGE_KERNEL, -1, __builtin_return_address(0)); + PAGE_KERNEL, NUMA_NO_NODE, + __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); area->flags |= VM_USERMAP; @@ -1846,7 +1823,7 @@ EXPORT_SYMBOL(vzalloc_node); void *vmalloc_exec(unsigned long size) { return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); } #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) @@ -1867,7 +1844,7 @@ void *vmalloc_exec(unsigned long size) void *vmalloc_32(unsigned long size) { return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32); @@ -1884,7 +1861,7 @@ void *vmalloc_32_user(unsigned long size) void *ret; ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); area->flags |= VM_USERMAP; @@ -2002,7 +1979,8 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) long vread(char *buf, char *addr, unsigned long count) { - struct vm_struct *tmp; + struct vmap_area *va; + struct vm_struct *vm; char *vaddr, *buf_start = buf; unsigned long buflen = count; unsigned long n; @@ -2011,10 +1989,17 @@ long vread(char *buf, char *addr, unsigned long count) if ((unsigned long) addr + count < count) count = -(unsigned long) addr; - read_lock(&vmlist_lock); - for (tmp = vmlist; count && tmp; tmp = tmp->next) { - vaddr = (char *) tmp->addr; - if (addr >= vaddr + tmp->size - PAGE_SIZE) + spin_lock(&vmap_area_lock); + list_for_each_entry(va, &vmap_area_list, list) { + if (!count) + break; + + if (!(va->flags & VM_VM_AREA)) + continue; + + vm = va->vm; + vaddr = (char *) vm->addr; + if (addr >= vaddr + get_vm_area_size(vm)) continue; while (addr < vaddr) { if (count == 0) @@ -2024,10 +2009,10 @@ long vread(char *buf, char *addr, unsigned long count) addr++; count--; } - n = vaddr + tmp->size - PAGE_SIZE - addr; + n = vaddr + get_vm_area_size(vm) - addr; if (n > count) n = count; - if (!(tmp->flags & VM_IOREMAP)) + if (!(vm->flags & VM_IOREMAP)) aligned_vread(buf, addr, n); else /* IOREMAP area is treated as memory hole */ memset(buf, 0, n); @@ -2036,7 +2021,7 @@ long vread(char *buf, char *addr, unsigned long count) count -= n; } finished: - read_unlock(&vmlist_lock); + spin_unlock(&vmap_area_lock); if (buf == buf_start) return 0; @@ -2075,7 +2060,8 @@ finished: long vwrite(char *buf, char *addr, unsigned long count) { - struct vm_struct *tmp; + struct vmap_area *va; + struct vm_struct *vm; char *vaddr; unsigned long n, buflen; int copied = 0; @@ -2085,10 +2071,17 @@ long vwrite(char *buf, char *addr, unsigned long count) count = -(unsigned long) addr; buflen = count; - read_lock(&vmlist_lock); - for (tmp = vmlist; count && tmp; tmp = tmp->next) { - vaddr = (char *) tmp->addr; - if (addr >= vaddr + tmp->size - PAGE_SIZE) + spin_lock(&vmap_area_lock); + list_for_each_entry(va, &vmap_area_list, list) { + if (!count) + break; + + if (!(va->flags & VM_VM_AREA)) + continue; + + vm = va->vm; + vaddr = (char *) vm->addr; + if (addr >= vaddr + get_vm_area_size(vm)) continue; while (addr < vaddr) { if (count == 0) @@ -2097,10 +2090,10 @@ long vwrite(char *buf, char *addr, unsigned long count) addr++; count--; } - n = vaddr + tmp->size - PAGE_SIZE - addr; + n = vaddr + get_vm_area_size(vm) - addr; if (n > count) n = count; - if (!(tmp->flags & VM_IOREMAP)) { + if (!(vm->flags & VM_IOREMAP)) { aligned_vwrite(buf, addr, n); copied++; } @@ -2109,49 +2102,50 @@ long vwrite(char *buf, char *addr, unsigned long count) count -= n; } finished: - read_unlock(&vmlist_lock); + spin_unlock(&vmap_area_lock); if (!copied) return 0; return buflen; } /** - * 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 + * remap_vmalloc_range_partial - map vmalloc pages to userspace + * @vma: vma to cover + * @uaddr: target user address to start at + * @kaddr: virtual address of vmalloc kernel memory + * @size: size of map area * * Returns: 0 for success, -Exxx on failure * - * This function checks that addr is a valid vmalloc'ed area, and - * that it is big enough to cover the vma. Will return failure if - * that criteria isn't met. + * This function checks that @kaddr is a valid vmalloc'ed area, + * and that it is big enough to cover the range starting at + * @uaddr in @vma. Will return failure if that criteria isn't + * met. * * Similar to remap_pfn_range() (see mm/memory.c) */ -int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, - unsigned long pgoff) +int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, + void *kaddr, unsigned long size) { struct vm_struct *area; - unsigned long uaddr = vma->vm_start; - unsigned long usize = vma->vm_end - vma->vm_start; - if ((PAGE_SIZE-1) & (unsigned long)addr) + size = PAGE_ALIGN(size); + + if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr)) return -EINVAL; - area = find_vm_area(addr); + area = find_vm_area(kaddr); if (!area) return -EINVAL; if (!(area->flags & VM_USERMAP)) return -EINVAL; - if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE) + if (kaddr + size > area->addr + area->size) return -EINVAL; - addr += pgoff << PAGE_SHIFT; do { - struct page *page = vmalloc_to_page(addr); + struct page *page = vmalloc_to_page(kaddr); int ret; ret = vm_insert_page(vma, uaddr, page); @@ -2159,21 +2153,44 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, return ret; uaddr += PAGE_SIZE; - addr += PAGE_SIZE; - usize -= PAGE_SIZE; - } while (usize > 0); + kaddr += PAGE_SIZE; + size -= PAGE_SIZE; + } while (size > 0); vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; return 0; } +EXPORT_SYMBOL(remap_vmalloc_range_partial); + +/** + * remap_vmalloc_range - map vmalloc pages to userspace + * @vma: vma to cover (map full range of vma) + * @addr: vmalloc memory + * @pgoff: number of pages into addr before first page to map + * + * Returns: 0 for success, -Exxx on failure + * + * This function checks that addr is a valid vmalloc'ed area, and + * that it is big enough to cover the vma. Will return failure if + * that criteria isn't met. + * + * Similar to remap_pfn_range() (see mm/memory.c) + */ +int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, + unsigned long pgoff) +{ + return remap_vmalloc_range_partial(vma, vma->vm_start, + addr + (pgoff << PAGE_SHIFT), + vma->vm_end - vma->vm_start); +} EXPORT_SYMBOL(remap_vmalloc_range); /* * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. */ -void __attribute__((weak)) vmalloc_sync_all(void) +void __weak vmalloc_sync_all(void) { } @@ -2480,8 +2497,8 @@ found: /* insert all vm's */ for (area = 0; area < nr_vms; area++) - insert_vmalloc_vm(vms[area], vas[area], VM_ALLOC, - pcpu_get_vm_areas); + setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, + pcpu_get_vm_areas); kfree(vas); return vms; @@ -2516,19 +2533,19 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) #ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) - __acquires(&vmlist_lock) + __acquires(&vmap_area_lock) { loff_t n = *pos; - struct vm_struct *v; + struct vmap_area *va; - read_lock(&vmlist_lock); - v = vmlist; - while (n > 0 && v) { + spin_lock(&vmap_area_lock); + va = list_entry((&vmap_area_list)->next, typeof(*va), list); + while (n > 0 && &va->list != &vmap_area_list) { n--; - v = v->next; + va = list_entry(va->list.next, typeof(*va), list); } - if (!n) - return v; + if (!n && &va->list != &vmap_area_list) + return va; return NULL; @@ -2536,16 +2553,20 @@ static void *s_start(struct seq_file *m, loff_t *pos) static void *s_next(struct seq_file *m, void *p, loff_t *pos) { - struct vm_struct *v = p; + struct vmap_area *va = p, *next; ++*pos; - return v->next; + next = list_entry(va->list.next, typeof(*va), list); + if (&next->list != &vmap_area_list) + return next; + + return NULL; } static void s_stop(struct seq_file *m, void *p) - __releases(&vmlist_lock) + __releases(&vmap_area_lock) { - read_unlock(&vmlist_lock); + spin_unlock(&vmap_area_lock); } static void show_numa_info(struct seq_file *m, struct vm_struct *v) @@ -2556,6 +2577,11 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) if (!counters) return; + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); + if (v->flags & VM_UNINITIALIZED) + return; + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr++) @@ -2569,7 +2595,17 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) static int s_show(struct seq_file *m, void *p) { - struct vm_struct *v = p; + struct vmap_area *va = p; + struct vm_struct *v; + + /* + * s_show can encounter race with remove_vm_area, !VM_VM_AREA on + * behalf of vmap area is being tear down or vm_map_ram allocation. + */ + if (!(va->flags & VM_VM_AREA)) + return 0; + + v = va->vm; seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); @@ -2584,19 +2620,19 @@ static int s_show(struct seq_file *m, void *p) seq_printf(m, " phys=%llx", (unsigned long long)v->phys_addr); if (v->flags & VM_IOREMAP) - seq_printf(m, " ioremap"); + seq_puts(m, " ioremap"); if (v->flags & VM_ALLOC) - seq_printf(m, " vmalloc"); + seq_puts(m, " vmalloc"); if (v->flags & VM_MAP) - seq_printf(m, " vmap"); + seq_puts(m, " vmap"); if (v->flags & VM_USERMAP) - seq_printf(m, " user"); + seq_puts(m, " user"); if (v->flags & VM_VPAGES) - seq_printf(m, " vpages"); + seq_puts(m, " vpages"); show_numa_info(m, v); seq_putc(m, '\n'); @@ -2642,5 +2678,53 @@ static int __init proc_vmalloc_init(void) return 0; } module_init(proc_vmalloc_init); + +void get_vmalloc_info(struct vmalloc_info *vmi) +{ + struct vmap_area *va; + unsigned long free_area_size; + unsigned long prev_end; + + vmi->used = 0; + vmi->largest_chunk = 0; + + prev_end = VMALLOC_START; + + spin_lock(&vmap_area_lock); + + if (list_empty(&vmap_area_list)) { + vmi->largest_chunk = VMALLOC_TOTAL; + goto out; + } + + list_for_each_entry(va, &vmap_area_list, list) { + unsigned long addr = va->va_start; + + /* + * Some archs keep another range for modules in vmalloc space + */ + if (addr < VMALLOC_START) + continue; + if (addr >= VMALLOC_END) + break; + + if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING)) + continue; + + vmi->used += (va->va_end - va->va_start); + + free_area_size = addr - prev_end; + if (vmi->largest_chunk < free_area_size) + vmi->largest_chunk = free_area_size; + + prev_end = va->va_end; + } + + if (VMALLOC_END - prev_end > vmi->largest_chunk) + vmi->largest_chunk = VMALLOC_END - prev_end; + +out: + spin_unlock(&vmap_area_lock); +} #endif diff --git a/mm/vmpressure.c b/mm/vmpressure.c new file mode 100644 index 00000000000..d4042e75f7c --- /dev/null +++ b/mm/vmpressure.c @@ -0,0 +1,380 @@ +/* + * Linux VM pressure + * + * Copyright 2012 Linaro Ltd. + * Anton Vorontsov <anton.vorontsov@linaro.org> + * + * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro, + * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <linux/cgroup.h> +#include <linux/fs.h> +#include <linux/log2.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmstat.h> +#include <linux/eventfd.h> +#include <linux/slab.h> +#include <linux/swap.h> +#include <linux/printk.h> +#include <linux/vmpressure.h> + +/* + * The window size (vmpressure_win) is the number of scanned pages before + * we try to analyze scanned/reclaimed ratio. So the window is used as a + * rate-limit tunable for the "low" level notification, and also for + * averaging the ratio for medium/critical levels. Using small window + * sizes can cause lot of false positives, but too big window size will + * delay the notifications. + * + * As the vmscan reclaimer logic works with chunks which are multiple of + * SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well. + * + * TODO: Make the window size depend on machine size, as we do for vmstat + * thresholds. Currently we set it to 512 pages (2MB for 4KB pages). + */ +static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16; + +/* + * These thresholds are used when we account memory pressure through + * scanned/reclaimed ratio. The current values were chosen empirically. In + * essence, they are percents: the higher the value, the more number + * unsuccessful reclaims there were. + */ +static const unsigned int vmpressure_level_med = 60; +static const unsigned int vmpressure_level_critical = 95; + +/* + * When there are too little pages left to scan, vmpressure() may miss the + * critical pressure as number of pages will be less than "window size". + * However, in that case the vmscan priority will raise fast as the + * reclaimer will try to scan LRUs more deeply. + * + * The vmscan logic considers these special priorities: + * + * prio == DEF_PRIORITY (12): reclaimer starts with that value + * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed + * prio == 0 : close to OOM, kernel scans every page in an lru + * + * Any value in this range is acceptable for this tunable (i.e. from 12 to + * 0). Current value for the vmpressure_level_critical_prio is chosen + * empirically, but the number, in essence, means that we consider + * critical level when scanning depth is ~10% of the lru size (vmscan + * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one + * eights). + */ +static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10); + +static struct vmpressure *work_to_vmpressure(struct work_struct *work) +{ + return container_of(work, struct vmpressure, work); +} + +static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) +{ + struct cgroup_subsys_state *css = vmpressure_to_css(vmpr); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + memcg = parent_mem_cgroup(memcg); + if (!memcg) + return NULL; + return memcg_to_vmpressure(memcg); +} + +enum vmpressure_levels { + VMPRESSURE_LOW = 0, + VMPRESSURE_MEDIUM, + VMPRESSURE_CRITICAL, + VMPRESSURE_NUM_LEVELS, +}; + +static const char * const vmpressure_str_levels[] = { + [VMPRESSURE_LOW] = "low", + [VMPRESSURE_MEDIUM] = "medium", + [VMPRESSURE_CRITICAL] = "critical", +}; + +static enum vmpressure_levels vmpressure_level(unsigned long pressure) +{ + if (pressure >= vmpressure_level_critical) + return VMPRESSURE_CRITICAL; + else if (pressure >= vmpressure_level_med) + return VMPRESSURE_MEDIUM; + return VMPRESSURE_LOW; +} + +static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, + unsigned long reclaimed) +{ + unsigned long scale = scanned + reclaimed; + unsigned long pressure; + + /* + * We calculate the ratio (in percents) of how many pages were + * scanned vs. reclaimed in a given time frame (window). Note that + * time is in VM reclaimer's "ticks", i.e. number of pages + * scanned. This makes it possible to set desired reaction time + * and serves as a ratelimit. + */ + pressure = scale - (reclaimed * scale / scanned); + pressure = pressure * 100 / scale; + + pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, + scanned, reclaimed); + + return vmpressure_level(pressure); +} + +struct vmpressure_event { + struct eventfd_ctx *efd; + enum vmpressure_levels level; + struct list_head node; +}; + +static bool vmpressure_event(struct vmpressure *vmpr, + unsigned long scanned, unsigned long reclaimed) +{ + struct vmpressure_event *ev; + enum vmpressure_levels level; + bool signalled = false; + + level = vmpressure_calc_level(scanned, reclaimed); + + mutex_lock(&vmpr->events_lock); + + list_for_each_entry(ev, &vmpr->events, node) { + if (level >= ev->level) { + eventfd_signal(ev->efd, 1); + signalled = true; + } + } + + mutex_unlock(&vmpr->events_lock); + + return signalled; +} + +static void vmpressure_work_fn(struct work_struct *work) +{ + struct vmpressure *vmpr = work_to_vmpressure(work); + unsigned long scanned; + unsigned long reclaimed; + + /* + * Several contexts might be calling vmpressure(), so it is + * possible that the work was rescheduled again before the old + * work context cleared the counters. In that case we will run + * just after the old work returns, but then scanned might be zero + * here. No need for any locks here since we don't care if + * vmpr->reclaimed is in sync. + */ + if (!vmpr->scanned) + return; + + spin_lock(&vmpr->sr_lock); + scanned = vmpr->scanned; + reclaimed = vmpr->reclaimed; + vmpr->scanned = 0; + vmpr->reclaimed = 0; + spin_unlock(&vmpr->sr_lock); + + do { + if (vmpressure_event(vmpr, scanned, reclaimed)) + break; + /* + * If not handled, propagate the event upward into the + * hierarchy. + */ + } while ((vmpr = vmpressure_parent(vmpr))); +} + +/** + * vmpressure() - Account memory pressure through scanned/reclaimed ratio + * @gfp: reclaimer's gfp mask + * @memcg: cgroup memory controller handle + * @scanned: number of pages scanned + * @reclaimed: number of pages reclaimed + * + * This function should be called from the vmscan reclaim path to account + * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw + * pressure index is then further refined and averaged over time. + * + * This function does not return any value. + */ +void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, + unsigned long scanned, unsigned long reclaimed) +{ + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); + + /* + * Here we only want to account pressure that userland is able to + * help us with. For example, suppose that DMA zone is under + * pressure; if we notify userland about that kind of pressure, + * then it will be mostly a waste as it will trigger unnecessary + * freeing of memory by userland (since userland is more likely to + * have HIGHMEM/MOVABLE pages instead of the DMA fallback). That + * is why we include only movable, highmem and FS/IO pages. + * Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so + * we account it too. + */ + if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS))) + return; + + /* + * If we got here with no pages scanned, then that is an indicator + * that reclaimer was unable to find any shrinkable LRUs at the + * current scanning depth. But it does not mean that we should + * report the critical pressure, yet. If the scanning priority + * (scanning depth) goes too high (deep), we will be notified + * through vmpressure_prio(). But so far, keep calm. + */ + if (!scanned) + return; + + spin_lock(&vmpr->sr_lock); + vmpr->scanned += scanned; + vmpr->reclaimed += reclaimed; + scanned = vmpr->scanned; + spin_unlock(&vmpr->sr_lock); + + if (scanned < vmpressure_win) + return; + schedule_work(&vmpr->work); +} + +/** + * vmpressure_prio() - Account memory pressure through reclaimer priority level + * @gfp: reclaimer's gfp mask + * @memcg: cgroup memory controller handle + * @prio: reclaimer's priority + * + * This function should be called from the reclaim path every time when + * the vmscan's reclaiming priority (scanning depth) changes. + * + * This function does not return any value. + */ +void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) +{ + /* + * We only use prio for accounting critical level. For more info + * see comment for vmpressure_level_critical_prio variable above. + */ + if (prio > vmpressure_level_critical_prio) + return; + + /* + * OK, the prio is below the threshold, updating vmpressure + * information before shrinker dives into long shrinking of long + * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0 + * to the vmpressure() basically means that we signal 'critical' + * level. + */ + vmpressure(gfp, memcg, vmpressure_win, 0); +} + +/** + * vmpressure_register_event() - Bind vmpressure notifications to an eventfd + * @memcg: memcg that is interested in vmpressure notifications + * @eventfd: eventfd context to link notifications with + * @args: event arguments (used to set up a pressure level threshold) + * + * This function associates eventfd context with the vmpressure + * infrastructure, so that the notifications will be delivered to the + * @eventfd. The @args parameter is a string that denotes pressure level + * threshold (one of vmpressure_str_levels, i.e. "low", "medium", or + * "critical"). + * + * To be used as memcg event method. + */ +int vmpressure_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); + struct vmpressure_event *ev; + int level; + + for (level = 0; level < VMPRESSURE_NUM_LEVELS; level++) { + if (!strcmp(vmpressure_str_levels[level], args)) + break; + } + + if (level >= VMPRESSURE_NUM_LEVELS) + return -EINVAL; + + ev = kzalloc(sizeof(*ev), GFP_KERNEL); + if (!ev) + return -ENOMEM; + + ev->efd = eventfd; + ev->level = level; + + mutex_lock(&vmpr->events_lock); + list_add(&ev->node, &vmpr->events); + mutex_unlock(&vmpr->events_lock); + + return 0; +} + +/** + * vmpressure_unregister_event() - Unbind eventfd from vmpressure + * @memcg: memcg handle + * @eventfd: eventfd context that was used to link vmpressure with the @cg + * + * This function does internal manipulations to detach the @eventfd from + * the vmpressure notifications, and then frees internal resources + * associated with the @eventfd (but the @eventfd itself is not freed). + * + * To be used as memcg event method. + */ +void vmpressure_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); + struct vmpressure_event *ev; + + mutex_lock(&vmpr->events_lock); + list_for_each_entry(ev, &vmpr->events, node) { + if (ev->efd != eventfd) + continue; + list_del(&ev->node); + kfree(ev); + break; + } + mutex_unlock(&vmpr->events_lock); +} + +/** + * vmpressure_init() - Initialize vmpressure control structure + * @vmpr: Structure to be initialized + * + * This function should be called on every allocated vmpressure structure + * before any usage. + */ +void vmpressure_init(struct vmpressure *vmpr) +{ + spin_lock_init(&vmpr->sr_lock); + mutex_init(&vmpr->events_lock); + INIT_LIST_HEAD(&vmpr->events); + INIT_WORK(&vmpr->work, vmpressure_work_fn); +} + +/** + * vmpressure_cleanup() - shuts down vmpressure control structure + * @vmpr: Structure to be cleaned up + * + * This function should be called before the structure in which it is + * embedded is cleaned up. + */ +void vmpressure_cleanup(struct vmpressure *vmpr) +{ + /* + * Make sure there is no pending work before eventfd infrastructure + * goes away. + */ + flush_work(&vmpr->work); +} diff --git a/mm/vmscan.c b/mm/vmscan.c index 196709f5ee5..0f16ffe8eb6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -11,6 +11,8 @@ * Multiqueue VM started 5.8.00, Rik van Riel. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/module.h> #include <linux/gfp.h> @@ -19,6 +21,7 @@ #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> +#include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> @@ -42,11 +45,13 @@ #include <linux/sysctl.h> #include <linux/oom.h> #include <linux/prefetch.h> +#include <linux/printk.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> +#include <linux/balloon_compaction.h> #include "internal.h" @@ -81,6 +86,9 @@ struct scan_control { /* Scan (total_size >> priority) pages at once */ int priority; + /* anon vs. file LRUs scanning "ratio" */ + int swappiness; + /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. @@ -128,7 +136,7 @@ struct scan_control { * From 0 .. 100. Higher means more swappy. */ int vm_swappiness = 60; -long vm_total_pages; /* The total number of pages which the VM controls */ +unsigned long vm_total_pages; /* The total number of pages which the VM controls */ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); @@ -145,6 +153,25 @@ static bool global_reclaim(struct scan_control *sc) } #endif +static unsigned long zone_reclaimable_pages(struct zone *zone) +{ + int nr; + + nr = zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_FILE); + + if (get_nr_swap_pages() > 0) + nr += zone_page_state(zone, NR_ACTIVE_ANON) + + zone_page_state(zone, NR_INACTIVE_ANON); + + return nr; +} + +bool zone_reclaimable(struct zone *zone) +{ + return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; +} + static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) { if (!mem_cgroup_disabled()) @@ -154,14 +181,31 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) } /* - * Add a shrinker callback to be called from the vm + * Add a shrinker callback to be called from the vm. */ -void register_shrinker(struct shrinker *shrinker) +int register_shrinker(struct shrinker *shrinker) { - atomic_long_set(&shrinker->nr_in_batch, 0); + size_t size = sizeof(*shrinker->nr_deferred); + + /* + * If we only have one possible node in the system anyway, save + * ourselves the trouble and disable NUMA aware behavior. This way we + * will save memory and some small loop time later. + */ + if (nr_node_ids == 1) + shrinker->flags &= ~SHRINKER_NUMA_AWARE; + + if (shrinker->flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + return -ENOMEM; + down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); up_write(&shrinker_rwsem); + return 0; } EXPORT_SYMBOL(register_shrinker); @@ -173,18 +217,123 @@ void unregister_shrinker(struct shrinker *shrinker) down_write(&shrinker_rwsem); list_del(&shrinker->list); up_write(&shrinker_rwsem); + kfree(shrinker->nr_deferred); } EXPORT_SYMBOL(unregister_shrinker); -static inline int do_shrinker_shrink(struct shrinker *shrinker, - struct shrink_control *sc, - unsigned long nr_to_scan) -{ - sc->nr_to_scan = nr_to_scan; - return (*shrinker->shrink)(shrinker, sc); +#define SHRINK_BATCH 128 + +static unsigned long +shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, + unsigned long nr_pages_scanned, unsigned long lru_pages) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long freeable; + long nr; + long new_nr; + int nid = shrinkctl->nid; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0) + return 0; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); + + total_scan = nr; + delta = (4 * nr_pages_scanned) / shrinker->seeks; + delta *= freeable; + do_div(delta, lru_pages + 1); + total_scan += delta; + if (total_scan < 0) { + printk(KERN_ERR + "shrink_slab: %pF negative objects to delete nr=%ld\n", + shrinker->scan_objects, total_scan); + total_scan = freeable; + } + + /* + * We need to avoid excessive windup on filesystem shrinkers + * due to large numbers of GFP_NOFS allocations causing the + * shrinkers to return -1 all the time. This results in a large + * nr being built up so when a shrink that can do some work + * comes along it empties the entire cache due to nr >>> + * freeable. This is bad for sustaining a working set in + * memory. + * + * Hence only allow the shrinker to scan the entire cache when + * a large delta change is calculated directly. + */ + if (delta < freeable / 4) + total_scan = min(total_scan, freeable / 2); + + /* + * Avoid risking looping forever due to too large nr value: + * never try to free more than twice the estimate number of + * freeable entries. + */ + if (total_scan > freeable * 2) + total_scan = freeable * 2; + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + nr_pages_scanned, lru_pages, + freeable, delta, total_scan); + + /* + * Normally, we should not scan less than batch_size objects in one + * pass to avoid too frequent shrinker calls, but if the slab has less + * than batch_size objects in total and we are really tight on memory, + * we will try to reclaim all available objects, otherwise we can end + * up failing allocations although there are plenty of reclaimable + * objects spread over several slabs with usage less than the + * batch_size. + * + * We detect the "tight on memory" situations by looking at the total + * number of objects we want to scan (total_scan). If it is greater + * than the total number of objects on slab (freeable), we must be + * scanning at high prio and therefore should try to reclaim as much as + * possible. + */ + while (total_scan >= batch_size || + total_scan >= freeable) { + unsigned long ret; + unsigned long nr_to_scan = min(batch_size, total_scan); + + shrinkctl->nr_to_scan = nr_to_scan; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; + + count_vm_events(SLABS_SCANNED, nr_to_scan); + total_scan -= nr_to_scan; + + cond_resched(); + } + + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. If we exhausted the + * scan, there is no need to do an update. + */ + if (total_scan > 0) + new_nr = atomic_long_add_return(total_scan, + &shrinker->nr_deferred[nid]); + else + new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); + + trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); + return freed; } -#define SHRINK_BATCH 128 /* * Call the shrink functions to age shrinkable caches * @@ -204,115 +353,46 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker, * * Returns the number of slab objects which we shrunk. */ -unsigned long shrink_slab(struct shrink_control *shrink, +unsigned long shrink_slab(struct shrink_control *shrinkctl, unsigned long nr_pages_scanned, unsigned long lru_pages) { struct shrinker *shrinker; - unsigned long ret = 0; + unsigned long freed = 0; if (nr_pages_scanned == 0) nr_pages_scanned = SWAP_CLUSTER_MAX; if (!down_read_trylock(&shrinker_rwsem)) { - /* Assume we'll be able to shrink next time */ - ret = 1; + /* + * If we would return 0, our callers would understand that we + * have nothing else to shrink and give up trying. By returning + * 1 we keep it going and assume we'll be able to shrink next + * time. + */ + freed = 1; goto out; } list_for_each_entry(shrinker, &shrinker_list, list) { - unsigned long long delta; - long total_scan; - long max_pass; - int shrink_ret = 0; - long nr; - long new_nr; - long batch_size = shrinker->batch ? shrinker->batch - : SHRINK_BATCH; - - max_pass = do_shrinker_shrink(shrinker, shrink, 0); - if (max_pass <= 0) + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) { + shrinkctl->nid = 0; + freed += shrink_slab_node(shrinkctl, shrinker, + nr_pages_scanned, lru_pages); continue; - - /* - * copy the current shrinker scan count into a local variable - * and zero it so that other concurrent shrinker invocations - * don't also do this scanning work. - */ - nr = atomic_long_xchg(&shrinker->nr_in_batch, 0); - - total_scan = nr; - delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; - do_div(delta, lru_pages + 1); - total_scan += delta; - if (total_scan < 0) { - printk(KERN_ERR "shrink_slab: %pF negative objects to " - "delete nr=%ld\n", - shrinker->shrink, total_scan); - total_scan = max_pass; } - /* - * We need to avoid excessive windup on filesystem shrinkers - * due to large numbers of GFP_NOFS allocations causing the - * shrinkers to return -1 all the time. This results in a large - * nr being built up so when a shrink that can do some work - * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in - * memory. - * - * Hence only allow the shrinker to scan the entire cache when - * a large delta change is calculated directly. - */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); + for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) { + if (node_online(shrinkctl->nid)) + freed += shrink_slab_node(shrinkctl, shrinker, + nr_pages_scanned, lru_pages); - /* - * Avoid risking looping forever due to too large nr value: - * never try to free more than twice the estimate number of - * freeable entries. - */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; - - trace_mm_shrink_slab_start(shrinker, shrink, nr, - nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); - - while (total_scan >= batch_size) { - int nr_before; - - nr_before = do_shrinker_shrink(shrinker, shrink, 0); - shrink_ret = do_shrinker_shrink(shrinker, shrink, - batch_size); - if (shrink_ret == -1) - break; - if (shrink_ret < nr_before) - ret += nr_before - shrink_ret; - count_vm_events(SLABS_SCANNED, batch_size); - total_scan -= batch_size; - - cond_resched(); } - - /* - * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. If we exhausted the - * scan, there is no need to do an update. - */ - if (total_scan > 0) - new_nr = atomic_long_add_return(total_scan, - &shrinker->nr_in_batch); - else - new_nr = atomic_long_read(&shrinker->nr_in_batch); - - trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr); } up_read(&shrinker_rwsem); out: cond_resched(); - return ret; + return freed; } static inline int is_page_cache_freeable(struct page *page) @@ -384,7 +464,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * stalls if we need to run get_block(). We could test * PagePrivate for that. * - * If this process is currently in __generic_file_aio_write() against + * If this process is currently in __generic_file_write_iter() against * this page's queue, we can perform writeback even if that * will block. * @@ -403,7 +483,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, if (page_has_private(page)) { if (try_to_free_buffers(page)) { ClearPageDirty(page); - printk("%s: orphaned page\n", __func__); + pr_info("%s: orphaned page\n", __func__); return PAGE_CLEAN; } } @@ -449,7 +529,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * Same as remove_mapping, but if the page is removed from the mapping, it * gets returned with a refcount of 0. */ -static int __remove_mapping(struct address_space *mapping, struct page *page) +static int __remove_mapping(struct address_space *mapping, struct page *page, + bool reclaimed) { BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); @@ -495,10 +576,23 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) swapcache_free(swap, page); } else { void (*freepage)(struct page *); + void *shadow = NULL; freepage = mapping->a_ops->freepage; - - __delete_from_page_cache(page); + /* + * Remember a shadow entry for reclaimed file cache in + * order to detect refaults, thus thrashing, later on. + * + * But don't store shadows in an address space that is + * already exiting. This is not just an optizimation, + * inode reclaim needs to empty out the radix tree or + * the nodes are lost. Don't plant shadows behind its + * back. + */ + if (reclaimed && page_is_file_cache(page) && + !mapping_exiting(mapping)) + shadow = workingset_eviction(mapping, page); + __delete_from_page_cache(page, shadow); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -521,7 +615,7 @@ cannot_free: */ int remove_mapping(struct address_space *mapping, struct page *page) { - if (__remove_mapping(mapping, page)) { + if (__remove_mapping(mapping, page, false)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another @@ -544,11 +638,10 @@ int remove_mapping(struct address_space *mapping, struct page *page) */ void putback_lru_page(struct page *page) { - int lru; - int active = !!TestClearPageActive(page); + bool is_unevictable; int was_unevictable = PageUnevictable(page); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); redo: ClearPageUnevictable(page); @@ -560,14 +653,14 @@ redo: * unevictable page on [in]active list. * We know how to handle that. */ - lru = active + page_lru_base_type(page); - lru_cache_add_lru(page, lru); + is_unevictable = false; + lru_cache_add(page); } else { /* * Put unevictable pages directly on zone's unevictable * list. */ - lru = LRU_UNEVICTABLE; + is_unevictable = true; add_page_to_unevictable_list(page); /* * When racing with an mlock or AS_UNEVICTABLE clearing @@ -587,7 +680,7 @@ redo: * page is on unevictable list, it never be freed. To avoid that, * check after we added it to the list, again. */ - if (lru == LRU_UNEVICTABLE && page_evictable(page)) { + if (is_unevictable && page_evictable(page)) { if (!isolate_lru_page(page)) { put_page(page); goto redo; @@ -598,9 +691,9 @@ redo: */ } - if (was_unevictable && lru != LRU_UNEVICTABLE) + if (was_unevictable && !is_unevictable) count_vm_event(UNEVICTABLE_PGRESCUED); - else if (!was_unevictable && lru == LRU_UNEVICTABLE) + else if (!was_unevictable && is_unevictable) count_vm_event(UNEVICTABLE_PGCULLED); put_page(page); /* drop ref from isolate */ @@ -668,6 +761,35 @@ static enum page_references page_check_references(struct page *page, return PAGEREF_RECLAIM; } +/* Check if a page is dirty or under writeback */ +static void page_check_dirty_writeback(struct page *page, + bool *dirty, bool *writeback) +{ + struct address_space *mapping; + + /* + * Anonymous pages are not handled by flushers and must be written + * from reclaim context. Do not stall reclaim based on them + */ + if (!page_is_file_cache(page)) { + *dirty = false; + *writeback = false; + return; + } + + /* By default assume that the page flags are accurate */ + *dirty = PageDirty(page); + *writeback = PageWriteback(page); + + /* Verify dirty/writeback state if the filesystem supports it */ + if (!page_has_private(page)) + return; + + mapping = page_mapping(page); + if (mapping && mapping->a_ops->is_dirty_writeback) + mapping->a_ops->is_dirty_writeback(page, dirty, writeback); +} + /* * shrink_page_list() returns the number of reclaimed pages */ @@ -676,16 +798,21 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct scan_control *sc, enum ttu_flags ttu_flags, unsigned long *ret_nr_dirty, + unsigned long *ret_nr_unqueued_dirty, + unsigned long *ret_nr_congested, unsigned long *ret_nr_writeback, + unsigned long *ret_nr_immediate, bool force_reclaim) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); int pgactivate = 0; + unsigned long nr_unqueued_dirty = 0; unsigned long nr_dirty = 0; unsigned long nr_congested = 0; unsigned long nr_reclaimed = 0; unsigned long nr_writeback = 0; + unsigned long nr_immediate = 0; cond_resched(); @@ -695,6 +822,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct page *page; int may_enter_fs; enum page_references references = PAGEREF_RECLAIM_CLEAN; + bool dirty, writeback; cond_resched(); @@ -704,8 +832,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (!trylock_page(page)) goto keep; - VM_BUG_ON(PageActive(page)); - VM_BUG_ON(page_zone(page) != zone); + VM_BUG_ON_PAGE(PageActive(page), page); + VM_BUG_ON_PAGE(page_zone(page) != zone, page); sc->nr_scanned++; @@ -722,25 +850,77 @@ static unsigned long shrink_page_list(struct list_head *page_list, may_enter_fs = (sc->gfp_mask & __GFP_FS) || (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); + /* + * The number of dirty pages determines if a zone is marked + * reclaim_congested which affects wait_iff_congested. kswapd + * will stall and start writing pages if the tail of the LRU + * is all dirty unqueued pages. + */ + page_check_dirty_writeback(page, &dirty, &writeback); + if (dirty || writeback) + nr_dirty++; + + if (dirty && !writeback) + nr_unqueued_dirty++; + + /* + * Treat this page as congested if the underlying BDI is or if + * pages are cycling through the LRU so quickly that the + * pages marked for immediate reclaim are making it to the + * end of the LRU a second time. + */ + mapping = page_mapping(page); + if ((mapping && bdi_write_congested(mapping->backing_dev_info)) || + (writeback && PageReclaim(page))) + nr_congested++; + + /* + * If a page at the tail of the LRU is under writeback, there + * are three cases to consider. + * + * 1) If reclaim is encountering an excessive number of pages + * under writeback and this page is both under writeback and + * PageReclaim then it indicates that pages are being queued + * for IO but are being recycled through the LRU before the + * IO can complete. Waiting on the page itself risks an + * indefinite stall if it is impossible to writeback the + * page due to IO error or disconnected storage so instead + * note that the LRU is being scanned too quickly and the + * caller can stall after page list has been processed. + * + * 2) Global reclaim encounters a page, memcg encounters a + * page that is not marked for immediate reclaim or + * the caller does not have __GFP_IO. In this case mark + * the page for immediate reclaim and continue scanning. + * + * __GFP_IO is checked because a loop driver thread might + * enter reclaim, and deadlock if it waits on a page for + * which it is needed to do the write (loop masks off + * __GFP_IO|__GFP_FS for this reason); but more thought + * would probably show more reasons. + * + * Don't require __GFP_FS, since we're not going into the + * FS, just waiting on its writeback completion. Worryingly, + * ext4 gfs2 and xfs allocate pages with + * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing + * may_enter_fs here is liable to OOM on them. + * + * 3) memcg encounters a page that is not already marked + * PageReclaim. memcg does not have any dirty pages + * throttling so we could easily OOM just because too many + * pages are in writeback and there is nothing else to + * reclaim. Wait for the writeback to complete. + */ if (PageWriteback(page)) { - /* - * memcg doesn't have any dirty pages throttling so we - * could easily OOM just because too many pages are in - * writeback and there is nothing else to reclaim. - * - * Check __GFP_IO, certainly because a loop driver - * thread might enter reclaim, and deadlock if it waits - * on a page for which it is needed to do the write - * (loop masks off __GFP_IO|__GFP_FS for this reason); - * but more thought would probably show more reasons. - * - * Don't require __GFP_FS, since we're not going into - * the FS, just waiting on its writeback completion. - * Worryingly, ext4 gfs2 and xfs allocate pages with - * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so - * testing may_enter_fs here is liable to OOM on them. - */ - if (global_reclaim(sc) || + /* Case 1 above */ + if (current_is_kswapd() && + PageReclaim(page) && + zone_is_reclaim_writeback(zone)) { + nr_immediate++; + goto keep_locked; + + /* Case 2 above */ + } else if (global_reclaim(sc) || !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) { /* * This is slightly racy - end_page_writeback() @@ -755,9 +935,13 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ SetPageReclaim(page); nr_writeback++; + goto keep_locked; + + /* Case 3 above */ + } else { + wait_on_page_writeback(page); } - wait_on_page_writeback(page); } if (!force_reclaim) @@ -780,12 +964,13 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (PageAnon(page) && !PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; - if (!add_to_swap(page)) + if (!add_to_swap(page, page_list)) goto activate_locked; may_enter_fs = 1; - } - mapping = page_mapping(page); + /* Adding to swap updated mapping */ + mapping = page_mapping(page); + } /* * The page is mapped into the page tables of one or more @@ -805,16 +990,14 @@ static unsigned long shrink_page_list(struct list_head *page_list, } if (PageDirty(page)) { - nr_dirty++; - /* * Only kswapd can writeback filesystem pages to - * avoid risk of stack overflow but do not writeback - * unless under significant pressure. + * avoid risk of stack overflow but only writeback + * if many dirty pages have been encountered. */ if (page_is_file_cache(page) && (!current_is_kswapd() || - sc->priority >= DEF_PRIORITY - 2)) { + !zone_is_reclaim_dirty(zone))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() @@ -837,7 +1020,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* Page is dirty, try to write it out here */ switch (pageout(page, mapping, sc)) { case PAGE_KEEP: - nr_congested++; goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; @@ -903,7 +1085,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } - if (!mapping || !__remove_mapping(mapping, page)) + if (!mapping || !__remove_mapping(mapping, page, true)) goto keep_locked; /* @@ -935,32 +1117,26 @@ activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (PageSwapCache(page) && vm_swap_full()) try_to_free_swap(page); - VM_BUG_ON(PageActive(page)); + VM_BUG_ON_PAGE(PageActive(page), page); SetPageActive(page); pgactivate++; keep_locked: unlock_page(page); keep: list_add(&page->lru, &ret_pages); - VM_BUG_ON(PageLRU(page) || PageUnevictable(page)); + VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } - /* - * Tag a zone as congested if all the dirty pages encountered were - * backed by a congested BDI. In this case, reclaimers should just - * back off and wait for congestion to clear because further reclaim - * will encounter the same problem - */ - if (nr_dirty && nr_dirty == nr_congested && global_reclaim(sc)) - zone_set_flag(zone, ZONE_CONGESTED); - - free_hot_cold_page_list(&free_pages, 1); + free_hot_cold_page_list(&free_pages, true); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); mem_cgroup_uncharge_end(); *ret_nr_dirty += nr_dirty; + *ret_nr_congested += nr_congested; + *ret_nr_unqueued_dirty += nr_unqueued_dirty; *ret_nr_writeback += nr_writeback; + *ret_nr_immediate += nr_immediate; return nr_reclaimed; } @@ -972,22 +1148,23 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, .priority = DEF_PRIORITY, .may_unmap = 1, }; - unsigned long ret, dummy1, dummy2; + unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5; struct page *page, *next; LIST_HEAD(clean_pages); list_for_each_entry_safe(page, next, page_list, lru) { - if (page_is_file_cache(page) && !PageDirty(page)) { + if (page_is_file_cache(page) && !PageDirty(page) && + !isolated_balloon_page(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } } ret = shrink_page_list(&clean_pages, zone, &sc, - TTU_UNMAP|TTU_IGNORE_ACCESS, - &dummy1, &dummy2, true); + TTU_UNMAP|TTU_IGNORE_ACCESS, + &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true); list_splice(&clean_pages, page_list); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); + mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); return ret; } @@ -1101,7 +1278,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); - VM_BUG_ON(!PageLRU(page)); + VM_BUG_ON_PAGE(!PageLRU(page), page); switch (__isolate_lru_page(page, mode)) { case 0: @@ -1156,7 +1333,7 @@ int isolate_lru_page(struct page *page) { int ret = -EBUSY; - VM_BUG_ON(!page_count(page)); + VM_BUG_ON_PAGE(!page_count(page), page); if (PageLRU(page)) { struct zone *zone = page_zone(page); @@ -1227,7 +1404,7 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) struct page *page = lru_to_page(page_list); int lru; - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); list_del(&page->lru); if (unlikely(!page_evictable(page))) { spin_unlock_irq(&zone->lru_lock); @@ -1268,6 +1445,19 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) } /* + * If a kernel thread (such as nfsd for loop-back mounts) services + * a backing device by writing to the page cache it sets PF_LESS_THROTTLE. + * In that case we should only throttle if the backing device it is + * writing to is congested. In other cases it is safe to throttle. + */ +static int current_may_throttle(void) +{ + return !(current->flags & PF_LESS_THROTTLE) || + current->backing_dev_info == NULL || + bdi_write_congested(current->backing_dev_info); +} + +/* * shrink_inactive_list() is a helper for shrink_zone(). It returns the number * of reclaimed pages */ @@ -1280,7 +1470,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, unsigned long nr_reclaimed = 0; unsigned long nr_taken; unsigned long nr_dirty = 0; + unsigned long nr_congested = 0; + unsigned long nr_unqueued_dirty = 0; unsigned long nr_writeback = 0; + unsigned long nr_immediate = 0; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); struct zone *zone = lruvec_zone(lruvec); @@ -1322,7 +1515,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, return 0; nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP, - &nr_dirty, &nr_writeback, false); + &nr_dirty, &nr_unqueued_dirty, &nr_congested, + &nr_writeback, &nr_immediate, + false); spin_lock_irq(&zone->lru_lock); @@ -1343,7 +1538,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&page_list, 1); + free_hot_cold_page_list(&page_list, true); /* * If reclaim is isolating dirty pages under writeback, it implies @@ -1355,21 +1550,51 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * as there is no guarantee the dirtying process is throttled in the * same way balance_dirty_pages() manages. * - * This scales the number of dirty pages that must be under writeback - * before throttling depending on priority. It is a simple backoff - * function that has the most effect in the range DEF_PRIORITY to - * DEF_PRIORITY-2 which is the priority reclaim is considered to be - * in trouble and reclaim is considered to be in trouble. - * - * DEF_PRIORITY 100% isolated pages must be PageWriteback to throttle - * DEF_PRIORITY-1 50% must be PageWriteback - * DEF_PRIORITY-2 25% must be PageWriteback, kswapd in trouble - * ... - * DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any - * isolated page is PageWriteback + * Once a zone is flagged ZONE_WRITEBACK, kswapd will count the number + * of pages under pages flagged for immediate reclaim and stall if any + * are encountered in the nr_immediate check below. */ - if (nr_writeback && nr_writeback >= - (nr_taken >> (DEF_PRIORITY - sc->priority))) + if (nr_writeback && nr_writeback == nr_taken) + zone_set_flag(zone, ZONE_WRITEBACK); + + /* + * memcg will stall in page writeback so only consider forcibly + * stalling for global reclaim + */ + if (global_reclaim(sc)) { + /* + * Tag a zone as congested if all the dirty pages scanned were + * backed by a congested BDI and wait_iff_congested will stall. + */ + if (nr_dirty && nr_dirty == nr_congested) + zone_set_flag(zone, ZONE_CONGESTED); + + /* + * If dirty pages are scanned that are not queued for IO, it + * implies that flushers are not keeping up. In this case, flag + * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing + * pages from reclaim context. + */ + if (nr_unqueued_dirty == nr_taken) + zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY); + + /* + * If kswapd scans pages marked marked for immediate + * reclaim and under writeback (nr_immediate), it implies + * that pages are cycling through the LRU faster than + * they are written so also forcibly stall. + */ + if (nr_immediate && current_may_throttle()) + congestion_wait(BLK_RW_ASYNC, HZ/10); + } + + /* + * Stall direct reclaim for IO completions if underlying BDIs or zone + * is congested. Allow kswapd to continue until it starts encountering + * unqueued dirty pages or cycling through the LRU too quickly. + */ + if (!sc->hibernation_mode && !current_is_kswapd() && + current_may_throttle()) wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, @@ -1412,7 +1637,7 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, page = lru_to_page(list); lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(PageLRU(page)); + VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); nr_pages = hpage_nr_pages(page); @@ -1534,7 +1759,7 @@ static void shrink_active_list(unsigned long nr_to_scan, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&l_hold, 1); + free_hot_cold_page_list(&l_hold, true); } #ifdef CONFIG_SWAP @@ -1579,16 +1804,6 @@ static inline int inactive_anon_is_low(struct lruvec *lruvec) } #endif -static int inactive_file_is_low_global(struct zone *zone) -{ - unsigned long active, inactive; - - active = zone_page_state(zone, NR_ACTIVE_FILE); - inactive = zone_page_state(zone, NR_INACTIVE_FILE); - - return (active > inactive); -} - /** * inactive_file_is_low - check if file pages need to be deactivated * @lruvec: LRU vector to check @@ -1605,10 +1820,13 @@ static int inactive_file_is_low_global(struct zone *zone) */ static int inactive_file_is_low(struct lruvec *lruvec) { - if (!mem_cgroup_disabled()) - return mem_cgroup_inactive_file_is_low(lruvec); + unsigned long inactive; + unsigned long active; + + inactive = get_lru_size(lruvec, LRU_INACTIVE_FILE); + active = get_lru_size(lruvec, LRU_ACTIVE_FILE); - return inactive_file_is_low_global(lruvec_zone(lruvec)); + return active > inactive; } static int inactive_list_is_low(struct lruvec *lruvec, enum lru_list lru) @@ -1631,12 +1849,12 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } -static int vmscan_swappiness(struct scan_control *sc) -{ - if (global_reclaim(sc)) - return vm_swappiness; - return mem_cgroup_swappiness(sc->target_mem_cgroup); -} +enum scan_balance { + SCAN_EQUAL, + SCAN_FRACT, + SCAN_ANON, + SCAN_FILE, +}; /* * Determine how aggressively the anon and file LRU lists should be @@ -1650,15 +1868,18 @@ static int vmscan_swappiness(struct scan_control *sc) static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { - unsigned long anon, file, free; + struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; + u64 fraction[2]; + u64 denominator = 0; /* gcc */ + struct zone *zone = lruvec_zone(lruvec); unsigned long anon_prio, file_prio; + enum scan_balance scan_balance; + unsigned long anon, file; + bool force_scan = false; unsigned long ap, fp; - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - u64 fraction[2], denominator; enum lru_list lru; - int noswap = 0; - bool force_scan = false; - struct zone *zone = lruvec_zone(lruvec); + bool some_scanned; + int pass; /* * If the zone or memcg is small, nr[l] can be 0. This @@ -1670,17 +1891,36 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * latencies, so it's better to scan a minimum amount there as * well. */ - if (current_is_kswapd() && zone->all_unreclaimable) + if (current_is_kswapd() && !zone_reclaimable(zone)) force_scan = true; if (!global_reclaim(sc)) force_scan = true; /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || (nr_swap_pages <= 0)) { - noswap = 1; - fraction[0] = 0; - fraction[1] = 1; - denominator = 1; + if (!sc->may_swap || (get_nr_swap_pages() <= 0)) { + scan_balance = SCAN_FILE; + goto out; + } + + /* + * Global reclaim will swap to prevent OOM even with no + * swappiness, but memcg users want to use this knob to + * disable swapping for individual groups completely when + * using the memory controller's swap limit feature would be + * too expensive. + */ + if (!global_reclaim(sc) && !sc->swappiness) { + scan_balance = SCAN_FILE; + goto out; + } + + /* + * Do not apply any pressure balancing cleverness when the + * system is close to OOM, scan both anon and file equally + * (unless the swappiness setting disagrees with swapping). + */ + if (!sc->priority && sc->swappiness) { + scan_balance = SCAN_EQUAL; goto out; } @@ -1689,34 +1929,40 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + get_lru_size(lruvec, LRU_INACTIVE_FILE); + /* + * Prevent the reclaimer from falling into the cache trap: as + * cache pages start out inactive, every cache fault will tip + * the scan balance towards the file LRU. And as the file LRU + * shrinks, so does the window for rotation from references. + * This means we have a runaway feedback loop where a tiny + * thrashing file LRU becomes infinitely more attractive than + * anon pages. Try to detect this based on file LRU size. + */ if (global_reclaim(sc)) { - free = zone_page_state(zone, NR_FREE_PAGES); + unsigned long free = zone_page_state(zone, NR_FREE_PAGES); + if (unlikely(file + free <= high_wmark_pages(zone))) { - /* - * If we have very few page cache pages, force-scan - * anon pages. - */ - fraction[0] = 1; - fraction[1] = 0; - denominator = 1; - goto out; - } else if (!inactive_file_is_low_global(zone)) { - /* - * There is enough inactive page cache, do not - * reclaim anything from the working set right now. - */ - fraction[0] = 0; - fraction[1] = 1; - denominator = 1; + scan_balance = SCAN_ANON; goto out; } } /* + * There is enough inactive page cache, do not reclaim + * anything from the anonymous working set right now. + */ + if (!inactive_file_is_low(lruvec)) { + scan_balance = SCAN_FILE; + goto out; + } + + scan_balance = SCAN_FRACT; + + /* * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ - anon_prio = vmscan_swappiness(sc); + anon_prio = sc->swappiness; file_prio = 200 - anon_prio; /* @@ -1757,19 +2003,167 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, fraction[1] = fp; denominator = ap + fp + 1; out: - for_each_evictable_lru(lru) { - int file = is_file_lru(lru); - unsigned long scan; - - scan = get_lru_size(lruvec, lru); - if (sc->priority || noswap || !vmscan_swappiness(sc)) { - scan >>= sc->priority; - if (!scan && force_scan) - scan = SWAP_CLUSTER_MAX; - scan = div64_u64(scan * fraction[file], denominator); + some_scanned = false; + /* Only use force_scan on second pass. */ + for (pass = 0; !some_scanned && pass < 2; pass++) { + for_each_evictable_lru(lru) { + int file = is_file_lru(lru); + unsigned long size; + unsigned long scan; + + size = get_lru_size(lruvec, lru); + scan = size >> sc->priority; + + if (!scan && pass && force_scan) + scan = min(size, SWAP_CLUSTER_MAX); + + switch (scan_balance) { + case SCAN_EQUAL: + /* Scan lists relative to size */ + break; + case SCAN_FRACT: + /* + * Scan types proportional to swappiness and + * their relative recent reclaim efficiency. + */ + scan = div64_u64(scan * fraction[file], + denominator); + break; + case SCAN_FILE: + case SCAN_ANON: + /* Scan one type exclusively */ + if ((scan_balance == SCAN_FILE) != file) + scan = 0; + break; + default: + /* Look ma, no brain */ + BUG(); + } + nr[lru] = scan; + /* + * Skip the second pass and don't force_scan, + * if we found something to scan. + */ + some_scanned |= !!scan; + } + } +} + +/* + * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. + */ +static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + unsigned long nr[NR_LRU_LISTS]; + unsigned long targets[NR_LRU_LISTS]; + unsigned long nr_to_scan; + enum lru_list lru; + unsigned long nr_reclaimed = 0; + unsigned long nr_to_reclaim = sc->nr_to_reclaim; + struct blk_plug plug; + bool scan_adjusted; + + get_scan_count(lruvec, sc, nr); + + /* Record the original scan target for proportional adjustments later */ + memcpy(targets, nr, sizeof(nr)); + + /* + * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal + * event that can occur when there is little memory pressure e.g. + * multiple streaming readers/writers. Hence, we do not abort scanning + * when the requested number of pages are reclaimed when scanning at + * DEF_PRIORITY on the assumption that the fact we are direct + * reclaiming implies that kswapd is not keeping up and it is best to + * do a batch of work at once. For memcg reclaim one check is made to + * abort proportional reclaim if either the file or anon lru has already + * dropped to zero at the first pass. + */ + scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); + + blk_start_plug(&plug); + while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || + nr[LRU_INACTIVE_FILE]) { + unsigned long nr_anon, nr_file, percentage; + unsigned long nr_scanned; + + for_each_evictable_lru(lru) { + if (nr[lru]) { + nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); + nr[lru] -= nr_to_scan; + + nr_reclaimed += shrink_list(lru, nr_to_scan, + lruvec, sc); + } + } + + if (nr_reclaimed < nr_to_reclaim || scan_adjusted) + continue; + + /* + * For kswapd and memcg, reclaim at least the number of pages + * requested. Ensure that the anon and file LRUs are scanned + * proportionally what was requested by get_scan_count(). We + * stop reclaiming one LRU and reduce the amount scanning + * proportional to the original scan target. + */ + nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; + nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; + + /* + * It's just vindictive to attack the larger once the smaller + * has gone to zero. And given the way we stop scanning the + * smaller below, this makes sure that we only make one nudge + * towards proportionality once we've got nr_to_reclaim. + */ + if (!nr_file || !nr_anon) + break; + + if (nr_file > nr_anon) { + unsigned long scan_target = targets[LRU_INACTIVE_ANON] + + targets[LRU_ACTIVE_ANON] + 1; + lru = LRU_BASE; + percentage = nr_anon * 100 / scan_target; + } else { + unsigned long scan_target = targets[LRU_INACTIVE_FILE] + + targets[LRU_ACTIVE_FILE] + 1; + lru = LRU_FILE; + percentage = nr_file * 100 / scan_target; } - nr[lru] = scan; + + /* Stop scanning the smaller of the LRU */ + nr[lru] = 0; + nr[lru + LRU_ACTIVE] = 0; + + /* + * Recalculate the other LRU scan count based on its original + * scan target and the percentage scanning already complete + */ + lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; + nr_scanned = targets[lru] - nr[lru]; + nr[lru] = targets[lru] * (100 - percentage) / 100; + nr[lru] -= min(nr[lru], nr_scanned); + + lru += LRU_ACTIVE; + nr_scanned = targets[lru] - nr[lru]; + nr[lru] = targets[lru] * (100 - percentage) / 100; + nr[lru] -= min(nr[lru], nr_scanned); + + scan_adjusted = true; } + blk_finish_plug(&plug); + sc->nr_reclaimed += nr_reclaimed; + + /* + * Even if we did not try to evict anon pages at all, we want to + * rebalance the anon lru active/inactive ratio. + */ + if (inactive_anon_is_low(lruvec)) + shrink_active_list(SWAP_CLUSTER_MAX, lruvec, + sc, LRU_ACTIVE_ANON); + + throttle_vm_writeout(sc->gfp_mask); } /* Use reclaim/compaction for costly allocs or under memory pressure */ @@ -1790,7 +2184,7 @@ static bool in_reclaim_compaction(struct scan_control *sc) * calls try_to_compact_zone() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ -static inline bool should_continue_reclaim(struct lruvec *lruvec, +static inline bool should_continue_reclaim(struct zone *zone, unsigned long nr_reclaimed, unsigned long nr_scanned, struct scan_control *sc) @@ -1830,15 +2224,15 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec, * inactive lists are large enough, continue reclaiming */ pages_for_compaction = (2UL << sc->order); - inactive_lru_pages = get_lru_size(lruvec, LRU_INACTIVE_FILE); - if (nr_swap_pages > 0) - inactive_lru_pages += get_lru_size(lruvec, LRU_INACTIVE_ANON); + inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE); + if (get_nr_swap_pages() > 0) + inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON); if (sc->nr_reclaimed < pages_for_compaction && inactive_lru_pages > pages_for_compaction) return true; /* If compaction would go ahead or the allocation would succeed, stop */ - switch (compaction_suitable(lruvec_zone(lruvec), sc->order)) { + switch (compaction_suitable(zone, sc->order)) { case COMPACT_PARTIAL: case COMPACT_CONTINUE: return false; @@ -1847,98 +2241,54 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec, } } -/* - * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. - */ -static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +static void shrink_zone(struct zone *zone, struct scan_control *sc) { - unsigned long nr[NR_LRU_LISTS]; - unsigned long nr_to_scan; - enum lru_list lru; unsigned long nr_reclaimed, nr_scanned; - unsigned long nr_to_reclaim = sc->nr_to_reclaim; - struct blk_plug plug; - -restart: - nr_reclaimed = 0; - nr_scanned = sc->nr_scanned; - get_scan_count(lruvec, sc, nr); - - blk_start_plug(&plug); - while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || - nr[LRU_INACTIVE_FILE]) { - for_each_evictable_lru(lru) { - if (nr[lru]) { - nr_to_scan = min_t(unsigned long, - nr[lru], SWAP_CLUSTER_MAX); - nr[lru] -= nr_to_scan; - nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, sc); - } - } - /* - * On large memory systems, scan >> priority can become - * really large. This is fine for the starting priority; - * we want to put equal scanning pressure on each zone. - * However, if the VM has a harder time of freeing pages, - * with multiple processes reclaiming pages, the total - * freeing target can get unreasonably large. - */ - if (nr_reclaimed >= nr_to_reclaim && - sc->priority < DEF_PRIORITY) - break; - } - blk_finish_plug(&plug); - sc->nr_reclaimed += nr_reclaimed; + do { + struct mem_cgroup *root = sc->target_mem_cgroup; + struct mem_cgroup_reclaim_cookie reclaim = { + .zone = zone, + .priority = sc->priority, + }; + struct mem_cgroup *memcg; - /* - * Even if we did not try to evict anon pages at all, we want to - * rebalance the anon lru active/inactive ratio. - */ - if (inactive_anon_is_low(lruvec)) - shrink_active_list(SWAP_CLUSTER_MAX, lruvec, - sc, LRU_ACTIVE_ANON); + nr_reclaimed = sc->nr_reclaimed; + nr_scanned = sc->nr_scanned; - /* reclaim/compaction might need reclaim to continue */ - if (should_continue_reclaim(lruvec, nr_reclaimed, - sc->nr_scanned - nr_scanned, sc)) - goto restart; + memcg = mem_cgroup_iter(root, NULL, &reclaim); + do { + struct lruvec *lruvec; - throttle_vm_writeout(sc->gfp_mask); -} + lruvec = mem_cgroup_zone_lruvec(zone, memcg); -static void shrink_zone(struct zone *zone, struct scan_control *sc) -{ - struct mem_cgroup *root = sc->target_mem_cgroup; - struct mem_cgroup_reclaim_cookie reclaim = { - .zone = zone, - .priority = sc->priority, - }; - struct mem_cgroup *memcg; + sc->swappiness = mem_cgroup_swappiness(memcg); + shrink_lruvec(lruvec, sc); - memcg = mem_cgroup_iter(root, NULL, &reclaim); - do { - struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); + /* + * Direct reclaim and kswapd have to scan all memory + * cgroups to fulfill the overall scan target for the + * zone. + * + * Limit reclaim, on the other hand, only cares about + * nr_to_reclaim pages to be reclaimed and it will + * retry with decreasing priority if one round over the + * whole hierarchy is not sufficient. + */ + if (!global_reclaim(sc) && + sc->nr_reclaimed >= sc->nr_to_reclaim) { + mem_cgroup_iter_break(root, memcg); + break; + } + memcg = mem_cgroup_iter(root, memcg, &reclaim); + } while (memcg); - shrink_lruvec(lruvec, sc); + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, + sc->nr_scanned - nr_scanned, + sc->nr_reclaimed - nr_reclaimed); - /* - * Limit reclaim has historically picked one memcg and - * scanned it with decreasing priority levels until - * nr_to_reclaim had been reclaimed. This priority - * cycle is thus over after a single memcg. - * - * Direct reclaim and kswapd, on the other hand, have - * to scan all memory cgroups to fulfill the overall - * scan target for the zone. - */ - if (!global_reclaim(sc)) { - mem_cgroup_iter_break(root, memcg); - break; - } - memcg = mem_cgroup_iter(root, memcg, &reclaim); - } while (memcg); + } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, + sc->nr_scanned - nr_scanned, sc)); } /* Returns true if compaction should go ahead for a high-order request */ @@ -1957,9 +2307,8 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) * there is a buffer of free pages available to give compaction * a reasonable chance of completing and allocating the page */ - balance_gap = min(low_wmark_pages(zone), - (zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); + balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( + zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order); watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0); @@ -2004,16 +2353,26 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + unsigned long lru_pages = 0; bool aborted_reclaim = false; + struct reclaim_state *reclaim_state = current->reclaim_state; + gfp_t orig_mask; + struct shrink_control shrink = { + .gfp_mask = sc->gfp_mask, + }; + enum zone_type requested_highidx = gfp_zone(sc->gfp_mask); /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ + orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) sc->gfp_mask |= __GFP_HIGHMEM; + nodes_clear(shrink.nodes_to_scan); + for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { if (!populated_zone(zone)) @@ -2025,8 +2384,12 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) if (global_reclaim(sc)) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; - if (zone->all_unreclaimable && - sc->priority != DEF_PRIORITY) + + lru_pages += zone_reclaimable_pages(zone); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); + + if (sc->priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; /* Let kswapd poll it */ if (IS_ENABLED(CONFIG_COMPACTION)) { /* @@ -2038,7 +2401,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) * noticeable problem, like transparent huge * page allocations. */ - if (compaction_ready(zone, sc)) { + if ((zonelist_zone_idx(z) <= requested_highidx) + && compaction_ready(zone, sc)) { aborted_reclaim = true; continue; } @@ -2061,12 +2425,27 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) shrink_zone(zone, sc); } - return aborted_reclaim; -} + /* + * Don't shrink slabs when reclaiming memory from over limit cgroups + * but do shrink slab at least once when aborting reclaim for + * compaction to avoid unevenly scanning file/anon LRU pages over slab + * pages. + */ + if (global_reclaim(sc)) { + shrink_slab(&shrink, sc->nr_scanned, lru_pages); + if (reclaim_state) { + sc->nr_reclaimed += reclaim_state->reclaimed_slab; + reclaim_state->reclaimed_slab = 0; + } + } -static bool zone_reclaimable(struct zone *zone) -{ - return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; + /* + * Restore to original mask to avoid the impact on the caller if we + * promoted it to __GFP_HIGHMEM. + */ + sc->gfp_mask = orig_mask; + + return aborted_reclaim; } /* All zones in zonelist are unreclaimable? */ @@ -2082,7 +2461,7 @@ static bool all_unreclaimable(struct zonelist *zonelist, continue; if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; - if (!zone->all_unreclaimable) + if (zone_reclaimable(zone)) return false; } @@ -2106,13 +2485,9 @@ static bool all_unreclaimable(struct zonelist *zonelist, * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, - struct scan_control *sc, - struct shrink_control *shrink) + struct scan_control *sc) { unsigned long total_scanned = 0; - struct reclaim_state *reclaim_state = current->reclaim_state; - struct zoneref *z; - struct zone *zone; unsigned long writeback_threshold; bool aborted_reclaim; @@ -2122,34 +2497,23 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, count_vm_event(ALLOCSTALL); do { + vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, + sc->priority); sc->nr_scanned = 0; aborted_reclaim = shrink_zones(zonelist, sc); - /* - * Don't shrink slabs when reclaiming memory from - * over limit cgroups - */ - if (global_reclaim(sc)) { - unsigned long lru_pages = 0; - for_each_zone_zonelist(zone, z, zonelist, - gfp_zone(sc->gfp_mask)) { - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - continue; - - lru_pages += zone_reclaimable_pages(zone); - } - - shrink_slab(shrink, sc->nr_scanned, lru_pages); - if (reclaim_state) { - sc->nr_reclaimed += reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } - } total_scanned += sc->nr_scanned; if (sc->nr_reclaimed >= sc->nr_to_reclaim) goto out; /* + * If we're getting trouble reclaiming, start doing + * writepage even in laptop mode. + */ + if (sc->priority < DEF_PRIORITY - 2) + sc->may_writepage = 1; + + /* * Try to write back as many pages as we just scanned. This * tends to cause slow streaming writers to write data to the * disk smoothly, at the dirtying rate, which is nice. But @@ -2162,18 +2526,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, WB_REASON_TRY_TO_FREE_PAGES); sc->may_writepage = 1; } - - /* Take a nap, wait for some writeback to complete */ - if (!sc->hibernation_mode && sc->nr_scanned && - sc->priority < DEF_PRIORITY - 2) { - struct zone *preferred_zone; - - first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask), - &cpuset_current_mems_allowed, - &preferred_zone); - wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10); - } - } while (--sc->priority >= 0); + } while (--sc->priority >= 0 && !aborted_reclaim); out: delayacct_freepages_end(); @@ -2210,10 +2563,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; + if (!populated_zone(zone)) + continue; + pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } + /* If there are no reserves (unexpected config) then do not throttle */ + if (!pfmemalloc_reserve) + return true; + wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ @@ -2238,9 +2598,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { + struct zoneref *z; struct zone *zone; - int high_zoneidx = gfp_zone(gfp_mask); - pg_data_t *pgdat; + pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly @@ -2259,10 +2619,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, if (fatal_signal_pending(current)) goto out; - /* Check if the pfmemalloc reserves are ok */ - first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone); - pgdat = zone->zone_pgdat; - if (pfmemalloc_watermark_ok(pgdat)) + /* + * Check if the pfmemalloc reserves are ok by finding the first node + * with a usable ZONE_NORMAL or lower zone. The expectation is that + * GFP_KERNEL will be required for allocating network buffers when + * swapping over the network so ZONE_HIGHMEM is unusable. + * + * Throttling is based on the first usable node and throttled processes + * wait on a queue until kswapd makes progress and wakes them. There + * is an affinity then between processes waking up and where reclaim + * progress has been made assuming the process wakes on the same node. + * More importantly, processes running on remote nodes will not compete + * for remote pfmemalloc reserves and processes on different nodes + * should make reasonable progress. + */ + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_mask, nodemask) { + if (zone_idx(zone) > ZONE_NORMAL) + continue; + + /* Throttle based on the first usable node */ + pgdat = zone->zone_pgdat; + if (pfmemalloc_watermark_ok(pgdat)) + goto out; + break; + } + + /* If no zone was usable by the allocation flags then do not throttle */ + if (!pgdat) goto out; /* Account for the throttling */ @@ -2300,7 +2684,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, { unsigned long nr_reclaimed; struct scan_control sc = { - .gfp_mask = gfp_mask, + .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), .may_writepage = !laptop_mode, .nr_to_reclaim = SWAP_CLUSTER_MAX, .may_unmap = 1, @@ -2310,9 +2694,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .target_mem_cgroup = NULL, .nodemask = nodemask, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; /* * Do not enter reclaim if fatal signal was delivered while throttled. @@ -2326,7 +2707,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, sc.may_writepage, gfp_mask); - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); @@ -2348,6 +2729,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, .may_swap = !noswap, .order = 0, .priority = 0, + .swappiness = mem_cgroup_swappiness(memcg), .target_mem_cgroup = memcg, }; struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); @@ -2393,9 +2775,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; /* * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't @@ -2410,7 +2789,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.may_writepage, sc.gfp_mask); - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); @@ -2473,7 +2852,7 @@ static bool zone_balanced(struct zone *zone, int order, */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) { - unsigned long present_pages = 0; + unsigned long managed_pages = 0; unsigned long balanced_pages = 0; int i; @@ -2484,7 +2863,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) if (!populated_zone(zone)) continue; - present_pages += zone->present_pages; + managed_pages += zone->managed_pages; /* * A special case here: @@ -2493,19 +2872,19 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) * DEF_PRIORITY. Effectively, it considers them balanced so * they must be considered balanced here as well! */ - if (zone->all_unreclaimable) { - balanced_pages += zone->present_pages; + if (!zone_reclaimable(zone)) { + balanced_pages += zone->managed_pages; continue; } if (zone_balanced(zone, order, 0, i)) - balanced_pages += zone->present_pages; + balanced_pages += zone->managed_pages; else if (!order) return false; } if (order) - return balanced_pages >= (present_pages >> 2); + return balanced_pages >= (managed_pages >> 2); else return true; } @@ -2541,6 +2920,88 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, } /* + * kswapd shrinks the zone by the number of pages required to reach + * the high watermark. + * + * Returns true if kswapd scanned at least the requested number of pages to + * reclaim or if the lack of progress was due to pages under writeback. + * This is used to determine if the scanning priority needs to be raised. + */ +static bool kswapd_shrink_zone(struct zone *zone, + int classzone_idx, + struct scan_control *sc, + unsigned long lru_pages, + unsigned long *nr_attempted) +{ + int testorder = sc->order; + unsigned long balance_gap; + struct reclaim_state *reclaim_state = current->reclaim_state; + struct shrink_control shrink = { + .gfp_mask = sc->gfp_mask, + }; + bool lowmem_pressure; + + /* Reclaim above the high watermark. */ + sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone)); + + /* + * Kswapd reclaims only single pages with compaction enabled. Trying + * too hard to reclaim until contiguous free pages have become + * available can hurt performance by evicting too much useful data + * from memory. Do not reclaim more than needed for compaction. + */ + if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && + compaction_suitable(zone, sc->order) != + COMPACT_SKIPPED) + testorder = 0; + + /* + * We put equal pressure on every zone, unless one zone has way too + * many pages free already. The "too many pages" is defined as the + * high wmark plus a "gap" where the gap is either the low + * watermark or 1% of the zone, whichever is smaller. + */ + balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( + zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); + + /* + * If there is no low memory pressure or the zone is balanced then no + * reclaim is necessary + */ + lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone)); + if (!lowmem_pressure && zone_balanced(zone, testorder, + balance_gap, classzone_idx)) + return true; + + shrink_zone(zone, sc); + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); + + reclaim_state->reclaimed_slab = 0; + shrink_slab(&shrink, sc->nr_scanned, lru_pages); + sc->nr_reclaimed += reclaim_state->reclaimed_slab; + + /* Account for the number of pages attempted to reclaim */ + *nr_attempted += sc->nr_to_reclaim; + + zone_clear_flag(zone, ZONE_WRITEBACK); + + /* + * If a zone reaches its high watermark, consider it to be no longer + * congested. It's possible there are dirty pages backed by congested + * BDIs but as pressure is relieved, speculatively avoid congestion + * waits. + */ + if (zone_reclaimable(zone) && + zone_balanced(zone, testorder, 0, classzone_idx)) { + zone_clear_flag(zone, ZONE_CONGESTED); + zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); + } + + return sc->nr_scanned >= sc->nr_to_reclaim; +} + +/* * For kswapd, balance_pgdat() will work across all this node's zones until * they are all at high_wmark_pages(zone). * @@ -2564,40 +3025,28 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, static unsigned long balance_pgdat(pg_data_t *pgdat, int order, int *classzone_idx) { - struct zone *unbalanced_zone; int i; int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ - unsigned long total_scanned; - struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; struct scan_control sc = { .gfp_mask = GFP_KERNEL, + .priority = DEF_PRIORITY, .may_unmap = 1, .may_swap = 1, - /* - * kswapd doesn't want to be bailed out while reclaim. because - * we want to put equal scanning pressure on each zone. - */ - .nr_to_reclaim = ULONG_MAX, + .may_writepage = !laptop_mode, .order = order, .target_mem_cgroup = NULL, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; -loop_again: - total_scanned = 0; - sc.priority = DEF_PRIORITY; - sc.nr_reclaimed = 0; - sc.may_writepage = !laptop_mode; count_vm_event(PAGEOUTRUN); do { unsigned long lru_pages = 0; - int has_under_min_watermark_zone = 0; + unsigned long nr_attempted = 0; + bool raise_priority = true; + bool pgdat_needs_compaction = (order > 0); - unbalanced_zone = NULL; + sc.nr_reclaimed = 0; /* * Scan in the highmem->dma direction for the highest @@ -2609,8 +3058,8 @@ loop_again: if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable && - sc.priority != DEF_PRIORITY) + if (sc.priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; /* @@ -2634,20 +3083,46 @@ loop_again: end_zone = i; break; } else { - /* If balanced, clear the congested flag */ + /* + * If balanced, clear the dirty and congested + * flags + */ zone_clear_flag(zone, ZONE_CONGESTED); + zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); } } + if (i < 0) goto out; for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; + if (!populated_zone(zone)) + continue; + lru_pages += zone_reclaimable_pages(zone); + + /* + * If any zone is currently balanced then kswapd will + * not call compaction as it is expected that the + * necessary pages are already available. + */ + if (pgdat_needs_compaction && + zone_watermark_ok(zone, order, + low_wmark_pages(zone), + *classzone_idx, 0)) + pgdat_needs_compaction = false; } /* + * If we're getting trouble reclaiming, start doing writepage + * even in laptop mode. + */ + if (sc.priority < DEF_PRIORITY - 2) + sc.may_writepage = 1; + + /* * Now scan the zone in the dma->highmem direction, stopping * at the last zone which needs scanning. * @@ -2658,14 +3133,12 @@ loop_again: */ for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; - int nr_slab, testorder; - unsigned long balance_gap; if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable && - sc.priority != DEF_PRIORITY) + if (sc.priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; sc.nr_scanned = 0; @@ -2678,83 +3151,16 @@ loop_again: order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; - total_scanned += nr_soft_scanned; - - /* - * We put equal pressure on every zone, unless - * one zone has way too many pages free - * already. The "too many pages" is defined - * as the high wmark plus a "gap" where the - * gap is either the low watermark or 1% - * of the zone, whichever is smaller. - */ - balance_gap = min(low_wmark_pages(zone), - (zone->present_pages + - KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); - /* - * Kswapd reclaims only single pages with compaction - * enabled. Trying too hard to reclaim until contiguous - * free pages have become available can hurt performance - * by evicting too much useful data from memory. - * Do not reclaim more than needed for compaction. - */ - testorder = order; - if (IS_ENABLED(CONFIG_COMPACTION) && order && - compaction_suitable(zone, order) != - COMPACT_SKIPPED) - testorder = 0; - - if ((buffer_heads_over_limit && is_highmem_idx(i)) || - !zone_balanced(zone, testorder, - balance_gap, end_zone)) { - shrink_zone(zone, &sc); - - reclaim_state->reclaimed_slab = 0; - nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages); - sc.nr_reclaimed += reclaim_state->reclaimed_slab; - total_scanned += sc.nr_scanned; - - if (nr_slab == 0 && !zone_reclaimable(zone)) - zone->all_unreclaimable = 1; - } /* - * If we've done a decent amount of scanning and - * the reclaim ratio is low, start doing writepage - * even in laptop mode + * There should be no need to raise the scanning + * priority if enough pages are already being scanned + * that that high watermark would be met at 100% + * efficiency. */ - if (total_scanned > SWAP_CLUSTER_MAX * 2 && - total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) - sc.may_writepage = 1; - - if (zone->all_unreclaimable) { - if (end_zone && end_zone == i) - end_zone--; - continue; - } - - if (!zone_balanced(zone, testorder, 0, end_zone)) { - unbalanced_zone = zone; - /* - * We are still under min water mark. This - * means that we have a GFP_ATOMIC allocation - * failure risk. Hurry up! - */ - if (!zone_watermark_ok_safe(zone, order, - min_wmark_pages(zone), end_zone, 0)) - has_under_min_watermark_zone = 1; - } else { - /* - * If a zone reaches its high watermark, - * consider it to be no longer congested. It's - * possible there are dirty pages backed by - * congested BDIs but as pressure is relieved, - * speculatively avoid congestion waits - */ - zone_clear_flag(zone, ZONE_CONGESTED); - } - + if (kswapd_shrink_zone(zone, end_zone, &sc, + lru_pages, &nr_attempted)) + raise_priority = false; } /* @@ -2766,82 +3172,38 @@ loop_again: pfmemalloc_watermark_ok(pgdat)) wake_up(&pgdat->pfmemalloc_wait); - if (pgdat_balanced(pgdat, order, *classzone_idx)) - break; /* kswapd: all done */ /* - * OK, kswapd is getting into trouble. Take a nap, then take - * another pass across the zones. + * Fragmentation may mean that the system cannot be rebalanced + * for high-order allocations in all zones. If twice the + * allocation size has been reclaimed and the zones are still + * not balanced then recheck the watermarks at order-0 to + * prevent kswapd reclaiming excessively. Assume that a + * process requested a high-order can direct reclaim/compact. */ - if (total_scanned && (sc.priority < DEF_PRIORITY - 2)) { - if (has_under_min_watermark_zone) - count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT); - else if (unbalanced_zone) - wait_iff_congested(unbalanced_zone, BLK_RW_ASYNC, HZ/10); - } + if (order && sc.nr_reclaimed >= 2UL << order) + order = sc.order = 0; - /* - * We do this so kswapd doesn't build up large priorities for - * example when it is freeing in parallel with allocators. It - * matches the direct reclaim path behaviour in terms of impact - * on zone->*_priority. - */ - if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX) + /* Check if kswapd should be suspending */ + if (try_to_freeze() || kthread_should_stop()) break; - } while (--sc.priority >= 0); -out: - - if (!pgdat_balanced(pgdat, order, *classzone_idx)) { - cond_resched(); - - try_to_freeze(); /* - * Fragmentation may mean that the system cannot be - * rebalanced for high-order allocations in all zones. - * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX, - * it means the zones have been fully scanned and are still - * not balanced. For high-order allocations, there is - * little point trying all over again as kswapd may - * infinite loop. - * - * Instead, recheck all watermarks at order-0 as they - * are the most important. If watermarks are ok, kswapd will go - * back to sleep. High-order users can still perform direct - * reclaim if they wish. + * Compact if necessary and kswapd is reclaiming at least the + * high watermark number of pages as requsted */ - if (sc.nr_reclaimed < SWAP_CLUSTER_MAX) - order = sc.order = 0; - - goto loop_again; - } - - /* - * If kswapd was reclaiming at a higher order, it has the option of - * sleeping without all zones being balanced. Before it does, it must - * ensure that the watermarks for order-0 on *all* zones are met and - * that the congestion flags are cleared. The congestion flag must - * be cleared as kswapd is the only mechanism that clears the flag - * and it is potentially going to sleep here. - */ - if (order) { - int zones_need_compaction = 1; - - for (i = 0; i <= end_zone; i++) { - struct zone *zone = pgdat->node_zones + i; - - if (!populated_zone(zone)) - continue; - - /* Check if the memory needs to be defragmented. */ - if (zone_watermark_ok(zone, order, - low_wmark_pages(zone), *classzone_idx, 0)) - zones_need_compaction = 0; - } - - if (zones_need_compaction) + if (pgdat_needs_compaction && sc.nr_reclaimed > nr_attempted) compact_pgdat(pgdat, order); - } + /* + * Raise priority if scanning rate is too low or there was no + * progress in reclaiming pages + */ + if (raise_priority || !sc.nr_reclaimed) + sc.priority--; + } while (sc.priority >= 1 && + !pgdat_balanced(pgdat, order, *classzone_idx)); + +out: /* * Return the order we were reclaiming at so prepare_kswapd_sleep() * makes a decision on the order we were last reclaiming at. However, @@ -3009,7 +3371,10 @@ static int kswapd(void *p) } } + tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); current->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); + return 0; } @@ -3032,48 +3397,13 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) } if (!waitqueue_active(&pgdat->kswapd_wait)) return; - if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0)) + if (zone_balanced(zone, order, 0, 0)) return; trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); wake_up_interruptible(&pgdat->kswapd_wait); } -/* - * The reclaimable count would be mostly accurate. - * The less reclaimable pages may be - * - mlocked pages, which will be moved to unevictable list when encountered - * - mapped pages, which may require several travels to be reclaimed - * - dirty pages, which is not "instantly" reclaimable - */ -unsigned long global_reclaimable_pages(void) -{ - int nr; - - nr = global_page_state(NR_ACTIVE_FILE) + - global_page_state(NR_INACTIVE_FILE); - - if (nr_swap_pages > 0) - nr += global_page_state(NR_ACTIVE_ANON) + - global_page_state(NR_INACTIVE_ANON); - - return nr; -} - -unsigned long zone_reclaimable_pages(struct zone *zone) -{ - int nr; - - nr = zone_page_state(zone, NR_ACTIVE_FILE) + - zone_page_state(zone, NR_INACTIVE_FILE); - - if (nr_swap_pages > 0) - nr += zone_page_state(zone, NR_ACTIVE_ANON) + - zone_page_state(zone, NR_INACTIVE_ANON); - - return nr; -} - #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of @@ -3096,9 +3426,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) .order = 0, .priority = DEF_PRIORITY, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); struct task_struct *p = current; unsigned long nr_reclaimed; @@ -3108,7 +3435,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); p->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); @@ -3158,16 +3485,16 @@ int kswapd_run(int nid) if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state == SYSTEM_BOOTING); - pgdat->kswapd = NULL; pr_err("Failed to start kswapd on node %d\n", nid); ret = PTR_ERR(pgdat->kswapd); + pgdat->kswapd = NULL; } return ret; } /* * Called by memory hotplug when all memory in a node is offlined. Caller must - * hold lock_memory_hotplug(). + * hold mem_hotplug_begin/end(). */ void kswapd_stop(int nid) { @@ -3280,9 +3607,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP), .may_swap = 1, - .nr_to_reclaim = max_t(unsigned long, nr_pages, - SWAP_CLUSTER_MAX), - .gfp_mask = gfp_mask, + .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), + .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), .order = order, .priority = ZONE_RECLAIM_PRIORITY, }; @@ -3320,10 +3646,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * number of slab pages and shake the slab until it is reduced * by the same nr_pages that we used for reclaiming unmapped * pages. - * - * Note that shrink_slab will free memory on all zones and may - * take a long time. */ + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); for (;;) { unsigned long lru_pages = zone_reclaimable_pages(zone); @@ -3372,7 +3697,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages) return ZONE_RECLAIM_FULL; - if (zone->all_unreclaimable) + if (!zone_reclaimable(zone)) return ZONE_RECLAIM_FULL; /* @@ -3459,7 +3784,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) if (page_evictable(page)) { enum lru_list lru = page_lru_base_type(page); - VM_BUG_ON(PageActive(page)); + VM_BUG_ON_PAGE(PageActive(page), page); ClearPageUnevictable(page); del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); add_page_to_lru_list(page, lruvec, lru); diff --git a/mm/vmstat.c b/mm/vmstat.c index 9800306c819..b37bd49bfd5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -19,6 +19,9 @@ #include <linux/math64.h> #include <linux/writeback.h> #include <linux/compaction.h> +#include <linux/mm_inline.h> + +#include "internal.h" #ifdef CONFIG_VM_EVENT_COUNTERS DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; @@ -52,7 +55,6 @@ void all_vm_events(unsigned long *ret) } EXPORT_SYMBOL_GPL(all_vm_events); -#ifdef CONFIG_HOTPLUG /* * Fold the foreign cpu events into our own. * @@ -69,7 +71,6 @@ void vm_events_fold_cpu(int cpu) fold_state->event[i] = 0; } } -#endif /* CONFIG_HOTPLUG */ #endif /* CONFIG_VM_EVENT_COUNTERS */ @@ -142,7 +143,7 @@ int calculate_normal_threshold(struct zone *zone) * 125 1024 10 16-32 GB 9 */ - mem = zone->present_pages >> (27 - PAGE_SHIFT); + mem = zone->managed_pages >> (27 - PAGE_SHIFT); threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem)); @@ -206,7 +207,9 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, } /* - * For use when we know that interrupts are disabled. + * For use when we know that interrupts are disabled, + * or when we know that preemption is disabled and that + * particular counter cannot be updated from interrupt context. */ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, int delta) @@ -416,12 +419,17 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item) EXPORT_SYMBOL(dec_zone_page_state); #endif +static inline void fold_diff(int *diff) +{ + int i; + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (diff[i]) + atomic_long_add(diff[i], &vm_stat[i]); +} + /* - * Update the zone counters for one cpu. - * - * The cpu specified must be either the current cpu or a processor that - * is not online. If it is the current cpu then the execution thread must - * be pinned to the current cpu. + * Update the zone counters for the current cpu. * * Note that refresh_cpu_vm_stats strives to only access * node local memory. The per cpu pagesets on remote zones are placed @@ -434,33 +442,29 @@ EXPORT_SYMBOL(dec_zone_page_state); * with the global counters. These could cause remote node cache line * bouncing and will have to be only done when necessary. */ -void refresh_cpu_vm_stats(int cpu) +static void refresh_cpu_vm_stats(void) { struct zone *zone; int i; int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; for_each_populated_zone(zone) { - struct per_cpu_pageset *p; + struct per_cpu_pageset __percpu *p = zone->pageset; - p = per_cpu_ptr(zone->pageset, cpu); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + int v; - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (p->vm_stat_diff[i]) { - unsigned long flags; - int v; + v = this_cpu_xchg(p->vm_stat_diff[i], 0); + if (v) { - local_irq_save(flags); - v = p->vm_stat_diff[i]; - p->vm_stat_diff[i] = 0; - local_irq_restore(flags); atomic_long_add(v, &zone->vm_stat[i]); global_diff[i] += v; #ifdef CONFIG_NUMA /* 3 seconds idle till flush */ - p->expire = 3; + __this_cpu_write(p->expire, 3); #endif } + } cond_resched(); #ifdef CONFIG_NUMA /* @@ -470,31 +474,63 @@ void refresh_cpu_vm_stats(int cpu) * Check if there are pages remaining in this pageset * if not then there is nothing to expire. */ - if (!p->expire || !p->pcp.count) + if (!__this_cpu_read(p->expire) || + !__this_cpu_read(p->pcp.count)) continue; /* * We never drain zones local to this processor. */ if (zone_to_nid(zone) == numa_node_id()) { - p->expire = 0; + __this_cpu_write(p->expire, 0); continue; } - p->expire--; - if (p->expire) + + if (__this_cpu_dec_return(p->expire)) continue; - if (p->pcp.count) - drain_zone_pages(zone, &p->pcp); + if (__this_cpu_read(p->pcp.count)) + drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); #endif } + fold_diff(global_diff); +} - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (global_diff[i]) - atomic_long_add(global_diff[i], &vm_stat[i]); +/* + * Fold the data for an offline cpu into the global array. + * There cannot be any access by the offline cpu and therefore + * synchronization is simplified. + */ +void cpu_vm_stats_fold(int cpu) +{ + struct zone *zone; + int i; + int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; + + for_each_populated_zone(zone) { + struct per_cpu_pageset *p; + + p = per_cpu_ptr(zone->pageset, cpu); + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (p->vm_stat_diff[i]) { + int v; + + v = p->vm_stat_diff[i]; + p->vm_stat_diff[i] = 0; + atomic_long_add(v, &zone->vm_stat[i]); + global_diff[i] += v; + } + } + + fold_diff(global_diff); } +/* + * this is only called if !populated_zone(zone), which implies no other users of + * pset->vm_stat_diff[] exsist. + */ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { int i; @@ -628,7 +664,9 @@ static char * const migratetype_names[MIGRATE_TYPES] = { #ifdef CONFIG_CMA "CMA", #endif +#ifdef CONFIG_MEMORY_ISOLATION "Isolate", +#endif }; static void *frag_start(struct seq_file *m, loff_t *pos) @@ -699,6 +737,7 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, const char * const vmstat_text[] = { /* Zoned VM counters */ "nr_free_pages", + "nr_alloc_batch", "nr_inactive_anon", "nr_active_anon", "nr_inactive_file", @@ -733,6 +772,9 @@ const char * const vmstat_text[] = { "numa_local", "numa_other", #endif + "workingset_refault", + "workingset_activate", + "workingset_nodereclaim", "nr_anon_transparent_hugepages", "nr_free_cma", "nr_dirty_threshold", @@ -768,14 +810,17 @@ const char * const vmstat_text[] = { "kswapd_inodesteal", "kswapd_low_wmark_hit_quickly", "kswapd_high_wmark_hit_quickly", - "kswapd_skip_congestion_wait", "pageoutrun", "allocstall", "pgrotated", + "drop_pagecache", + "drop_slab", + #ifdef CONFIG_NUMA_BALANCING "numa_pte_updates", + "numa_huge_pte_updates", "numa_hint_faults", "numa_hint_faults_local", "numa_pages_migrated", @@ -814,7 +859,19 @@ const char * const vmstat_text[] = { "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif - +#ifdef CONFIG_DEBUG_TLBFLUSH +#ifdef CONFIG_SMP + "nr_tlb_remote_flush", + "nr_tlb_remote_flush_received", +#endif /* CONFIG_SMP */ + "nr_tlb_local_flush_all", + "nr_tlb_local_flush_one", +#endif /* CONFIG_DEBUG_TLBFLUSH */ + +#ifdef CONFIG_DEBUG_VM_VMACACHE + "vmacache_find_calls", + "vmacache_find_hits", +#endif #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ @@ -890,7 +947,7 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m, int mtype; unsigned long pfn; unsigned long start_pfn = zone->zone_start_pfn; - unsigned long end_pfn = start_pfn + zone->spanned_pages; + unsigned long end_pfn = zone_end_pfn(zone); unsigned long count[MIGRATE_TYPES] = { 0, }; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { @@ -1049,7 +1106,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n all_unreclaimable: %u" "\n start_pfn: %lu" "\n inactive_ratio: %u", - zone->all_unreclaimable, + !zone_reclaimable(zone), zone->zone_start_pfn, zone->inactive_ratio); seq_putc(m, '\n'); @@ -1174,12 +1231,12 @@ int sysctl_stat_interval __read_mostly = HZ; static void vmstat_update(struct work_struct *w) { - refresh_cpu_vm_stats(smp_processor_id()); - schedule_delayed_work(&__get_cpu_var(vmstat_work), + refresh_cpu_vm_stats(); + schedule_delayed_work(this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } -static void __cpuinit start_cpu_timer(int cpu) +static void start_cpu_timer(int cpu) { struct delayed_work *work = &per_cpu(vmstat_work, cpu); @@ -1187,11 +1244,25 @@ static void __cpuinit start_cpu_timer(int cpu) schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu)); } +static void vmstat_cpu_dead(int node) +{ + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) + if (cpu_to_node(cpu) == node) + goto end; + + node_clear_state(node, N_CPU); +end: + put_online_cpus(); +} + /* * Use the cpu notifier to insure that the thresholds are recalculated * when necessary. */ -static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, +static int vmstat_cpuup_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -1216,6 +1287,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, case CPU_DEAD: case CPU_DEAD_FROZEN: refresh_zone_stat_thresholds(); + vmstat_cpu_dead(cpu_to_node(cpu)); break; default: break; @@ -1223,7 +1295,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata vmstat_notifier = +static struct notifier_block vmstat_notifier = { &vmstat_cpuup_callback, NULL, 0 }; #endif @@ -1232,10 +1304,14 @@ static int __init setup_vmstat(void) #ifdef CONFIG_SMP int cpu; - register_cpu_notifier(&vmstat_notifier); + cpu_notifier_register_begin(); + __register_cpu_notifier(&vmstat_notifier); - for_each_online_cpu(cpu) + for_each_online_cpu(cpu) { start_cpu_timer(cpu); + node_set_state(cpu_to_node(cpu), N_CPU); + } + cpu_notifier_register_done(); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); diff --git a/mm/workingset.c b/mm/workingset.c new file mode 100644 index 00000000000..f7216fa7da2 --- /dev/null +++ b/mm/workingset.c @@ -0,0 +1,414 @@ +/* + * Workingset detection + * + * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner + */ + +#include <linux/memcontrol.h> +#include <linux/writeback.h> +#include <linux/pagemap.h> +#include <linux/atomic.h> +#include <linux/module.h> +#include <linux/swap.h> +#include <linux/fs.h> +#include <linux/mm.h> + +/* + * Double CLOCK lists + * + * Per zone, two clock lists are maintained for file pages: the + * inactive and the active list. Freshly faulted pages start out at + * the head of the inactive list and page reclaim scans pages from the + * tail. Pages that are accessed multiple times on the inactive list + * are promoted to the active list, to protect them from reclaim, + * whereas active pages are demoted to the inactive list when the + * active list grows too big. + * + * fault ------------------------+ + * | + * +--------------+ | +-------------+ + * reclaim <- | inactive | <-+-- demotion | active | <--+ + * +--------------+ +-------------+ | + * | | + * +-------------- promotion ------------------+ + * + * + * Access frequency and refault distance + * + * A workload is thrashing when its pages are frequently used but they + * are evicted from the inactive list every time before another access + * would have promoted them to the active list. + * + * In cases where the average access distance between thrashing pages + * is bigger than the size of memory there is nothing that can be + * done - the thrashing set could never fit into memory under any + * circumstance. + * + * However, the average access distance could be bigger than the + * inactive list, yet smaller than the size of memory. In this case, + * the set could fit into memory if it weren't for the currently + * active pages - which may be used more, hopefully less frequently: + * + * +-memory available to cache-+ + * | | + * +-inactive------+-active----+ + * a b | c d e f g h i | J K L M N | + * +---------------+-----------+ + * + * It is prohibitively expensive to accurately track access frequency + * of pages. But a reasonable approximation can be made to measure + * thrashing on the inactive list, after which refaulting pages can be + * activated optimistically to compete with the existing active pages. + * + * Approximating inactive page access frequency - Observations: + * + * 1. When a page is accessed for the first time, it is added to the + * head of the inactive list, slides every existing inactive page + * towards the tail by one slot, and pushes the current tail page + * out of memory. + * + * 2. When a page is accessed for the second time, it is promoted to + * the active list, shrinking the inactive list by one slot. This + * also slides all inactive pages that were faulted into the cache + * more recently than the activated page towards the tail of the + * inactive list. + * + * Thus: + * + * 1. The sum of evictions and activations between any two points in + * time indicate the minimum number of inactive pages accessed in + * between. + * + * 2. Moving one inactive page N page slots towards the tail of the + * list requires at least N inactive page accesses. + * + * Combining these: + * + * 1. When a page is finally evicted from memory, the number of + * inactive pages accessed while the page was in cache is at least + * the number of page slots on the inactive list. + * + * 2. In addition, measuring the sum of evictions and activations (E) + * at the time of a page's eviction, and comparing it to another + * reading (R) at the time the page faults back into memory tells + * the minimum number of accesses while the page was not cached. + * This is called the refault distance. + * + * Because the first access of the page was the fault and the second + * access the refault, we combine the in-cache distance with the + * out-of-cache distance to get the complete minimum access distance + * of this page: + * + * NR_inactive + (R - E) + * + * And knowing the minimum access distance of a page, we can easily + * tell if the page would be able to stay in cache assuming all page + * slots in the cache were available: + * + * NR_inactive + (R - E) <= NR_inactive + NR_active + * + * which can be further simplified to + * + * (R - E) <= NR_active + * + * Put into words, the refault distance (out-of-cache) can be seen as + * a deficit in inactive list space (in-cache). If the inactive list + * had (R - E) more page slots, the page would not have been evicted + * in between accesses, but activated instead. And on a full system, + * the only thing eating into inactive list space is active pages. + * + * + * Activating refaulting pages + * + * All that is known about the active list is that the pages have been + * accessed more than once in the past. This means that at any given + * time there is actually a good chance that pages on the active list + * are no longer in active use. + * + * So when a refault distance of (R - E) is observed and there are at + * least (R - E) active pages, the refaulting page is activated + * optimistically in the hope that (R - E) active pages are actually + * used less frequently than the refaulting page - or even not used at + * all anymore. + * + * If this is wrong and demotion kicks in, the pages which are truly + * used more frequently will be reactivated while the less frequently + * used once will be evicted from memory. + * + * But if this is right, the stale pages will be pushed out of memory + * and the used pages get to stay in cache. + * + * + * Implementation + * + * For each zone's file LRU lists, a counter for inactive evictions + * and activations is maintained (zone->inactive_age). + * + * On eviction, a snapshot of this counter (along with some bits to + * identify the zone) is stored in the now empty page cache radix tree + * slot of the evicted page. This is called a shadow entry. + * + * On cache misses for which there are shadow entries, an eligible + * refault distance will immediately activate the refaulting page. + */ + +static void *pack_shadow(unsigned long eviction, struct zone *zone) +{ + eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone); + eviction = (eviction << ZONES_SHIFT) | zone_idx(zone); + eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); + + return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); +} + +static void unpack_shadow(void *shadow, + struct zone **zone, + unsigned long *distance) +{ + unsigned long entry = (unsigned long)shadow; + unsigned long eviction; + unsigned long refault; + unsigned long mask; + int zid, nid; + + entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + zid = entry & ((1UL << ZONES_SHIFT) - 1); + entry >>= ZONES_SHIFT; + nid = entry & ((1UL << NODES_SHIFT) - 1); + entry >>= NODES_SHIFT; + eviction = entry; + + *zone = NODE_DATA(nid)->node_zones + zid; + + refault = atomic_long_read(&(*zone)->inactive_age); + mask = ~0UL >> (NODES_SHIFT + ZONES_SHIFT + + RADIX_TREE_EXCEPTIONAL_SHIFT); + /* + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. + * + * There is a special case: usually, shadow entries have a + * short lifetime and are either refaulted or reclaimed along + * with the inode before they get too old. But it is not + * impossible for the inactive_age to lap a shadow entry in + * the field, which can then can result in a false small + * refault distance, leading to a false activation should this + * old entry actually refault again. However, earlier kernels + * used to deactivate unconditionally with *every* reclaim + * invocation for the longest time, so the occasional + * inappropriate activation leading to pressure on the active + * list is not a problem. + */ + *distance = (refault - eviction) & mask; +} + +/** + * workingset_eviction - note the eviction of a page from memory + * @mapping: address space the page was backing + * @page: the page being evicted + * + * Returns a shadow entry to be stored in @mapping->page_tree in place + * of the evicted @page so that a later refault can be detected. + */ +void *workingset_eviction(struct address_space *mapping, struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long eviction; + + eviction = atomic_long_inc_return(&zone->inactive_age); + return pack_shadow(eviction, zone); +} + +/** + * workingset_refault - evaluate the refault of a previously evicted page + * @shadow: shadow entry of the evicted page + * + * Calculates and evaluates the refault distance of the previously + * evicted page in the context of the zone it was allocated in. + * + * Returns %true if the page should be activated, %false otherwise. + */ +bool workingset_refault(void *shadow) +{ + unsigned long refault_distance; + struct zone *zone; + + unpack_shadow(shadow, &zone, &refault_distance); + inc_zone_state(zone, WORKINGSET_REFAULT); + + if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) { + inc_zone_state(zone, WORKINGSET_ACTIVATE); + return true; + } + return false; +} + +/** + * workingset_activation - note a page activation + * @page: page that is being activated + */ +void workingset_activation(struct page *page) +{ + atomic_long_inc(&page_zone(page)->inactive_age); +} + +/* + * Shadow entries reflect the share of the working set that does not + * fit into memory, so their number depends on the access pattern of + * the workload. In most cases, they will refault or get reclaimed + * along with the inode, but a (malicious) workload that streams + * through files with a total size several times that of available + * memory, while preventing the inodes from being reclaimed, can + * create excessive amounts of shadow nodes. To keep a lid on this, + * track shadow nodes and reclaim them when they grow way past the + * point where they would still be useful. + */ + +struct list_lru workingset_shadow_nodes; + +static unsigned long count_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long shadow_nodes; + unsigned long max_nodes; + unsigned long pages; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + local_irq_disable(); + shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid); + local_irq_enable(); + + pages = node_present_pages(sc->nid); + /* + * Active cache pages are limited to 50% of memory, and shadow + * entries that represent a refault distance bigger than that + * do not have any effect. Limit the number of shadow nodes + * such that shadow entries do not exceed the number of active + * cache pages, assuming a worst-case node population density + * of 1/8th on average. + * + * On 64-bit with 7 radix_tree_nodes per page and 64 slots + * each, this will reclaim shadow entries when they consume + * ~2% of available memory: + * + * PAGE_SIZE / radix_tree_nodes / node_entries / PAGE_SIZE + */ + max_nodes = pages >> (1 + RADIX_TREE_MAP_SHIFT - 3); + + if (shadow_nodes <= max_nodes) + return 0; + + return shadow_nodes - max_nodes; +} + +static enum lru_status shadow_lru_isolate(struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct address_space *mapping; + struct radix_tree_node *node; + unsigned int i; + int ret; + + /* + * Page cache insertions and deletions synchroneously maintain + * the shadow node LRU under the mapping->tree_lock and the + * lru_lock. Because the page cache tree is emptied before + * the inode can be destroyed, holding the lru_lock pins any + * address_space that has radix tree nodes on the LRU. + * + * We can then safely transition to the mapping->tree_lock to + * pin only the address_space of the particular node we want + * to reclaim, take the node off-LRU, and drop the lru_lock. + */ + + node = container_of(item, struct radix_tree_node, private_list); + mapping = node->private_data; + + /* Coming from the list, invert the lock order */ + if (!spin_trylock(&mapping->tree_lock)) { + spin_unlock(lru_lock); + ret = LRU_RETRY; + goto out; + } + + list_del_init(item); + spin_unlock(lru_lock); + + /* + * The nodes should only contain one or more shadow entries, + * no pages, so we expect to be able to remove them all and + * delete and free the empty node afterwards. + */ + + BUG_ON(!node->count); + BUG_ON(node->count & RADIX_TREE_COUNT_MASK); + + for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { + if (node->slots[i]) { + BUG_ON(!radix_tree_exceptional_entry(node->slots[i])); + node->slots[i] = NULL; + BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT)); + node->count -= 1U << RADIX_TREE_COUNT_SHIFT; + BUG_ON(!mapping->nrshadows); + mapping->nrshadows--; + } + } + BUG_ON(node->count); + inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM); + if (!__radix_tree_delete_node(&mapping->page_tree, node)) + BUG(); + + spin_unlock(&mapping->tree_lock); + ret = LRU_REMOVED_RETRY; +out: + local_irq_enable(); + cond_resched(); + local_irq_disable(); + spin_lock(lru_lock); + return ret; +} + +static unsigned long scan_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long ret; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + local_irq_disable(); + ret = list_lru_walk_node(&workingset_shadow_nodes, sc->nid, + shadow_lru_isolate, NULL, &sc->nr_to_scan); + local_irq_enable(); + return ret; +} + +static struct shrinker workingset_shadow_shrinker = { + .count_objects = count_shadow_nodes, + .scan_objects = scan_shadow_nodes, + .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE, +}; + +/* + * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe + * mapping->tree_lock. + */ +static struct lock_class_key shadow_nodes_key; + +static int __init workingset_init(void) +{ + int ret; + + ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); + if (ret) + goto err; + ret = register_shrinker(&workingset_shadow_shrinker); + if (ret) + goto err_list_lru; + return 0; +err_list_lru: + list_lru_destroy(&workingset_shadow_nodes); +err: + return ret; +} +module_init(workingset_init); diff --git a/mm/zbud.c b/mm/zbud.c new file mode 100644 index 00000000000..01df13a7e2e --- /dev/null +++ b/mm/zbud.c @@ -0,0 +1,527 @@ +/* + * zbud.c + * + * Copyright (C) 2013, Seth Jennings, IBM + * + * Concepts based on zcache internal zbud allocator by Dan Magenheimer. + * + * zbud is an special purpose allocator for storing compressed pages. Contrary + * to what its name may suggest, zbud is not a buddy allocator, but rather an + * allocator that "buddies" two compressed pages together in a single memory + * page. + * + * While this design limits storage density, it has simple and deterministic + * reclaim properties that make it preferable to a higher density approach when + * reclaim will be used. + * + * zbud works by storing compressed pages, or "zpages", together in pairs in a + * single memory page called a "zbud page". The first buddy is "left + * justified" at the beginning of the zbud page, and the last buddy is "right + * justified" at the end of the zbud page. The benefit is that if either + * buddy is freed, the freed buddy space, coalesced with whatever slack space + * that existed between the buddies, results in the largest possible free region + * within the zbud page. + * + * zbud also provides an attractive lower bound on density. The ratio of zpages + * to zbud pages can not be less than 1. This ensures that zbud can never "do + * harm" by using more pages to store zpages than the uncompressed zpages would + * have used on their own. + * + * zbud pages are divided into "chunks". The size of the chunks is fixed at + * compile time and determined by NCHUNKS_ORDER below. Dividing zbud pages + * into chunks allows organizing unbuddied zbud pages into a manageable number + * of unbuddied lists according to the number of free chunks available in the + * zbud page. + * + * The zbud API differs from that of conventional allocators in that the + * allocation function, zbud_alloc(), returns an opaque handle to the user, + * not a dereferenceable pointer. The user must map the handle using + * zbud_map() in order to get a usable pointer by which to access the + * allocation data and unmap the handle with zbud_unmap() when operations + * on the allocation data are complete. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/atomic.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/preempt.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/zbud.h> + +/***************** + * Structures +*****************/ +/* + * NCHUNKS_ORDER determines the internal allocation granularity, effectively + * adjusting internal fragmentation. It also determines the number of + * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the + * allocation granularity will be in chunks of size PAGE_SIZE/64, and there + * will be 64 freelists per pool. + */ +#define NCHUNKS_ORDER 6 + +#define CHUNK_SHIFT (PAGE_SHIFT - NCHUNKS_ORDER) +#define CHUNK_SIZE (1 << CHUNK_SHIFT) +#define NCHUNKS (PAGE_SIZE >> CHUNK_SHIFT) +#define ZHDR_SIZE_ALIGNED CHUNK_SIZE + +/** + * struct zbud_pool - stores metadata for each zbud pool + * @lock: protects all pool fields and first|last_chunk fields of any + * zbud page in the pool + * @unbuddied: array of lists tracking zbud pages that only contain one buddy; + * the lists each zbud page is added to depends on the size of + * its free region. + * @buddied: list tracking the zbud pages that contain two buddies; + * these zbud pages are full + * @lru: list tracking the zbud pages in LRU order by most recently + * added buddy. + * @pages_nr: number of zbud pages in the pool. + * @ops: pointer to a structure of user defined operations specified at + * pool creation time. + * + * This structure is allocated at pool creation time and maintains metadata + * pertaining to a particular zbud pool. + */ +struct zbud_pool { + spinlock_t lock; + struct list_head unbuddied[NCHUNKS]; + struct list_head buddied; + struct list_head lru; + u64 pages_nr; + struct zbud_ops *ops; +}; + +/* + * struct zbud_header - zbud page metadata occupying the first chunk of each + * zbud page. + * @buddy: links the zbud page into the unbuddied/buddied lists in the pool + * @lru: links the zbud page into the lru list in the pool + * @first_chunks: the size of the first buddy in chunks, 0 if free + * @last_chunks: the size of the last buddy in chunks, 0 if free + */ +struct zbud_header { + struct list_head buddy; + struct list_head lru; + unsigned int first_chunks; + unsigned int last_chunks; + bool under_reclaim; +}; + +/***************** + * Helpers +*****************/ +/* Just to make the code easier to read */ +enum buddy { + FIRST, + LAST +}; + +/* Converts an allocation size in bytes to size in zbud chunks */ +static int size_to_chunks(int size) +{ + return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; +} + +#define for_each_unbuddied_list(_iter, _begin) \ + for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) + +/* Initializes the zbud header of a newly allocated zbud page */ +static struct zbud_header *init_zbud_page(struct page *page) +{ + struct zbud_header *zhdr = page_address(page); + zhdr->first_chunks = 0; + zhdr->last_chunks = 0; + INIT_LIST_HEAD(&zhdr->buddy); + INIT_LIST_HEAD(&zhdr->lru); + zhdr->under_reclaim = 0; + return zhdr; +} + +/* Resets the struct page fields and frees the page */ +static void free_zbud_page(struct zbud_header *zhdr) +{ + __free_page(virt_to_page(zhdr)); +} + +/* + * Encodes the handle of a particular buddy within a zbud page + * Pool lock should be held as this function accesses first|last_chunks + */ +static unsigned long encode_handle(struct zbud_header *zhdr, enum buddy bud) +{ + unsigned long handle; + + /* + * For now, the encoded handle is actually just the pointer to the data + * but this might not always be the case. A little information hiding. + * Add CHUNK_SIZE to the handle if it is the first allocation to jump + * over the zbud header in the first chunk. + */ + handle = (unsigned long)zhdr; + if (bud == FIRST) + /* skip over zbud header */ + handle += ZHDR_SIZE_ALIGNED; + else /* bud == LAST */ + handle += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + return handle; +} + +/* Returns the zbud page where a given handle is stored */ +static struct zbud_header *handle_to_zbud_header(unsigned long handle) +{ + return (struct zbud_header *)(handle & PAGE_MASK); +} + +/* Returns the number of free chunks in a zbud page */ +static int num_free_chunks(struct zbud_header *zhdr) +{ + /* + * Rather than branch for different situations, just use the fact that + * free buddies have a length of zero to simplify everything. -1 at the + * end for the zbud header. + */ + return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks - 1; +} + +/***************** + * API Functions +*****************/ +/** + * zbud_create_pool() - create a new zbud pool + * @gfp: gfp flags when allocating the zbud pool structure + * @ops: user-defined operations for the zbud pool + * + * Return: pointer to the new zbud pool or NULL if the metadata allocation + * failed. + */ +struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops) +{ + struct zbud_pool *pool; + int i; + + pool = kmalloc(sizeof(struct zbud_pool), gfp); + if (!pool) + return NULL; + spin_lock_init(&pool->lock); + for_each_unbuddied_list(i, 0) + INIT_LIST_HEAD(&pool->unbuddied[i]); + INIT_LIST_HEAD(&pool->buddied); + INIT_LIST_HEAD(&pool->lru); + pool->pages_nr = 0; + pool->ops = ops; + return pool; +} + +/** + * zbud_destroy_pool() - destroys an existing zbud pool + * @pool: the zbud pool to be destroyed + * + * The pool should be emptied before this function is called. + */ +void zbud_destroy_pool(struct zbud_pool *pool) +{ + kfree(pool); +} + +/** + * zbud_alloc() - allocates a region of a given size + * @pool: zbud pool from which to allocate + * @size: size in bytes of the desired allocation + * @gfp: gfp flags used if the pool needs to grow + * @handle: handle of the new allocation + * + * This function will attempt to find a free region in the pool large enough to + * satisfy the allocation request. A search of the unbuddied lists is + * performed first. If no suitable free region is found, then a new page is + * allocated and added to the pool to satisfy the request. + * + * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used + * as zbud pool pages. + * + * Return: 0 if success and handle is set, otherwise -EINVAL if the size or + * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate + * a new page. + */ +int zbud_alloc(struct zbud_pool *pool, unsigned int size, gfp_t gfp, + unsigned long *handle) +{ + int chunks, i, freechunks; + struct zbud_header *zhdr = NULL; + enum buddy bud; + struct page *page; + + if (!size || (gfp & __GFP_HIGHMEM)) + return -EINVAL; + if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) + return -ENOSPC; + chunks = size_to_chunks(size); + spin_lock(&pool->lock); + + /* First, try to find an unbuddied zbud page. */ + zhdr = NULL; + for_each_unbuddied_list(i, chunks) { + if (!list_empty(&pool->unbuddied[i])) { + zhdr = list_first_entry(&pool->unbuddied[i], + struct zbud_header, buddy); + list_del(&zhdr->buddy); + if (zhdr->first_chunks == 0) + bud = FIRST; + else + bud = LAST; + goto found; + } + } + + /* Couldn't find unbuddied zbud page, create new one */ + spin_unlock(&pool->lock); + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + spin_lock(&pool->lock); + pool->pages_nr++; + zhdr = init_zbud_page(page); + bud = FIRST; + +found: + if (bud == FIRST) + zhdr->first_chunks = chunks; + else + zhdr->last_chunks = chunks; + + if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0) { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* Add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + + /* Add/move zbud page to beginning of LRU */ + if (!list_empty(&zhdr->lru)) + list_del(&zhdr->lru); + list_add(&zhdr->lru, &pool->lru); + + *handle = encode_handle(zhdr, bud); + spin_unlock(&pool->lock); + + return 0; +} + +/** + * zbud_free() - frees the allocation associated with the given handle + * @pool: pool in which the allocation resided + * @handle: handle associated with the allocation returned by zbud_alloc() + * + * In the case that the zbud page in which the allocation resides is under + * reclaim, as indicated by the PG_reclaim flag being set, this function + * only sets the first|last_chunks to 0. The page is actually freed + * once both buddies are evicted (see zbud_reclaim_page() below). + */ +void zbud_free(struct zbud_pool *pool, unsigned long handle) +{ + struct zbud_header *zhdr; + int freechunks; + + spin_lock(&pool->lock); + zhdr = handle_to_zbud_header(handle); + + /* If first buddy, handle will be page aligned */ + if ((handle - ZHDR_SIZE_ALIGNED) & ~PAGE_MASK) + zhdr->last_chunks = 0; + else + zhdr->first_chunks = 0; + + if (zhdr->under_reclaim) { + /* zbud page is under reclaim, reclaim will free */ + spin_unlock(&pool->lock); + return; + } + + /* Remove from existing buddy list */ + list_del(&zhdr->buddy); + + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* zbud page is empty, free */ + list_del(&zhdr->lru); + free_zbud_page(zhdr); + pool->pages_nr--; + } else { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } + + spin_unlock(&pool->lock); +} + +#define list_tail_entry(ptr, type, member) \ + list_entry((ptr)->prev, type, member) + +/** + * zbud_reclaim_page() - evicts allocations from a pool page and frees it + * @pool: pool from which a page will attempt to be evicted + * @retires: number of pages on the LRU list for which eviction will + * be attempted before failing + * + * zbud reclaim is different from normal system reclaim in that the reclaim is + * done from the bottom, up. This is because only the bottom layer, zbud, has + * information on how the allocations are organized within each zbud page. This + * has the potential to create interesting locking situations between zbud and + * the user, however. + * + * To avoid these, this is how zbud_reclaim_page() should be called: + + * The user detects a page should be reclaimed and calls zbud_reclaim_page(). + * zbud_reclaim_page() will remove a zbud page from the pool LRU list and call + * the user-defined eviction handler with the pool and handle as arguments. + * + * If the handle can not be evicted, the eviction handler should return + * non-zero. zbud_reclaim_page() will add the zbud page back to the + * appropriate list and try the next zbud page on the LRU up to + * a user defined number of retries. + * + * If the handle is successfully evicted, the eviction handler should + * return 0 _and_ should have called zbud_free() on the handle. zbud_free() + * contains logic to delay freeing the page if the page is under reclaim, + * as indicated by the setting of the PG_reclaim flag on the underlying page. + * + * If all buddies in the zbud page are successfully evicted, then the + * zbud page can be freed. + * + * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are + * no pages to evict or an eviction handler is not registered, -EAGAIN if + * the retry limit was hit. + */ +int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) +{ + int i, ret, freechunks; + struct zbud_header *zhdr; + unsigned long first_handle = 0, last_handle = 0; + + spin_lock(&pool->lock); + if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || + retries == 0) { + spin_unlock(&pool->lock); + return -EINVAL; + } + for (i = 0; i < retries; i++) { + zhdr = list_tail_entry(&pool->lru, struct zbud_header, lru); + list_del(&zhdr->lru); + list_del(&zhdr->buddy); + /* Protect zbud page against free */ + zhdr->under_reclaim = true; + /* + * We need encode the handles before unlocking, since we can + * race with free that will set (first|last)_chunks to 0 + */ + first_handle = 0; + last_handle = 0; + if (zhdr->first_chunks) + first_handle = encode_handle(zhdr, FIRST); + if (zhdr->last_chunks) + last_handle = encode_handle(zhdr, LAST); + spin_unlock(&pool->lock); + + /* Issue the eviction callback(s) */ + if (first_handle) { + ret = pool->ops->evict(pool, first_handle); + if (ret) + goto next; + } + if (last_handle) { + ret = pool->ops->evict(pool, last_handle); + if (ret) + goto next; + } +next: + spin_lock(&pool->lock); + zhdr->under_reclaim = false; + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* + * Both buddies are now free, free the zbud page and + * return success. + */ + free_zbud_page(zhdr); + pool->pages_nr--; + spin_unlock(&pool->lock); + return 0; + } else if (zhdr->first_chunks == 0 || + zhdr->last_chunks == 0) { + /* add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + + /* add to beginning of LRU */ + list_add(&zhdr->lru, &pool->lru); + } + spin_unlock(&pool->lock); + return -EAGAIN; +} + +/** + * zbud_map() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be mapped + * + * While trivial for zbud, the mapping functions for others allocators + * implementing this allocation API could have more complex information encoded + * in the handle and could create temporary mappings to make the data + * accessible to the user. + * + * Returns: a pointer to the mapped allocation + */ +void *zbud_map(struct zbud_pool *pool, unsigned long handle) +{ + return (void *)(handle); +} + +/** + * zbud_unmap() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be unmapped + */ +void zbud_unmap(struct zbud_pool *pool, unsigned long handle) +{ +} + +/** + * zbud_get_pool_size() - gets the zbud pool size in pages + * @pool: pool whose size is being queried + * + * Returns: size in pages of the given pool. The pool lock need not be + * taken to access pages_nr. + */ +u64 zbud_get_pool_size(struct zbud_pool *pool) +{ + return pool->pages_nr; +} + +static int __init init_zbud(void) +{ + /* Make sure the zbud header will fit in one chunk */ + BUILD_BUG_ON(sizeof(struct zbud_header) > ZHDR_SIZE_ALIGNED); + pr_info("loaded\n"); + return 0; +} + +static void __exit exit_zbud(void) +{ + pr_info("unloaded\n"); +} + +module_init(init_zbud); +module_exit(exit_zbud); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Seth Jennings <sjenning@linux.vnet.ibm.com>"); +MODULE_DESCRIPTION("Buddy Allocator for Compressed Pages"); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c new file mode 100644 index 00000000000..fe78189624c --- /dev/null +++ b/mm/zsmalloc.c @@ -0,0 +1,1117 @@ +/* + * zsmalloc memory allocator + * + * Copyright (C) 2011 Nitin Gupta + * Copyright (C) 2012, 2013 Minchan Kim + * + * This code is released using a dual license strategy: BSD/GPL + * You can choose the license that better fits your requirements. + * + * Released under the terms of 3-clause BSD License + * Released under the terms of GNU General Public License Version 2.0 + */ + +/* + * This allocator is designed for use with zram. Thus, the allocator is + * supposed to work well under low memory conditions. In particular, it + * never attempts higher order page allocation which is very likely to + * fail under memory pressure. On the other hand, if we just use single + * (0-order) pages, it would suffer from very high fragmentation -- + * any object of size PAGE_SIZE/2 or larger would occupy an entire page. + * This was one of the major issues with its predecessor (xvmalloc). + * + * To overcome these issues, zsmalloc allocates a bunch of 0-order pages + * and links them together using various 'struct page' fields. These linked + * pages act as a single higher-order page i.e. an object can span 0-order + * page boundaries. The code refers to these linked pages as a single entity + * called zspage. + * + * For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE + * since this satisfies the requirements of all its current users (in the + * worst case, page is incompressible and is thus stored "as-is" i.e. in + * uncompressed form). For allocation requests larger than this size, failure + * is returned (see zs_malloc). + * + * Additionally, zs_malloc() does not return a dereferenceable pointer. + * Instead, it returns an opaque handle (unsigned long) which encodes actual + * location of the allocated object. The reason for this indirection is that + * zsmalloc does not keep zspages permanently mapped since that would cause + * issues on 32-bit systems where the VA region for kernel space mappings + * is very small. So, before using the allocating memory, the object has to + * be mapped using zs_map_object() to get a usable pointer and subsequently + * unmapped using zs_unmap_object(). + * + * Following is how we use various fields and flags of underlying + * struct page(s) to form a zspage. + * + * Usage of struct page fields: + * page->first_page: points to the first component (0-order) page + * page->index (union with page->freelist): offset of the first object + * starting in this page. For the first page, this is + * always 0, so we use this field (aka freelist) to point + * to the first free object in zspage. + * page->lru: links together all component pages (except the first page) + * of a zspage + * + * For _first_ page only: + * + * page->private (union with page->first_page): refers to the + * component page after the first page + * page->freelist: points to the first free object in zspage. + * Free objects are linked together using in-place + * metadata. + * page->objects: maximum number of objects we can store in this + * zspage (class->zspage_order * PAGE_SIZE / class->size) + * page->lru: links together first pages of various zspages. + * Basically forming list of zspages in a fullness group. + * page->mapping: class index and fullness group of the zspage + * + * Usage of struct page flags: + * PG_private: identifies the first component page + * PG_private2: identifies the last component page + * + */ + +#ifdef CONFIG_ZSMALLOC_DEBUG +#define DEBUG +#endif + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/errno.h> +#include <linux/highmem.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <asm/tlbflush.h> +#include <asm/pgtable.h> +#include <linux/cpumask.h> +#include <linux/cpu.h> +#include <linux/vmalloc.h> +#include <linux/hardirq.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/zsmalloc.h> + +/* + * This must be power of 2 and greater than of equal to sizeof(link_free). + * These two conditions ensure that any 'struct link_free' itself doesn't + * span more than 1 page which avoids complex case of mapping 2 pages simply + * to restore link_free pointer values. + */ +#define ZS_ALIGN 8 + +/* + * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single) + * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N. + */ +#define ZS_MAX_ZSPAGE_ORDER 2 +#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) + +/* + * Object location (<PFN>, <obj_idx>) is encoded as + * as single (unsigned long) handle value. + * + * Note that object index <obj_idx> is relative to system + * page <PFN> it is stored in, so for each sub-page belonging + * to a zspage, obj_idx starts with 0. + * + * This is made more complicated by various memory models and PAE. + */ + +#ifndef MAX_PHYSMEM_BITS +#ifdef CONFIG_HIGHMEM64G +#define MAX_PHYSMEM_BITS 36 +#else /* !CONFIG_HIGHMEM64G */ +/* + * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just + * be PAGE_SHIFT + */ +#define MAX_PHYSMEM_BITS BITS_PER_LONG +#endif +#endif +#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS) +#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) + +#define MAX(a, b) ((a) >= (b) ? (a) : (b)) +/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ +#define ZS_MIN_ALLOC_SIZE \ + MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) +#define ZS_MAX_ALLOC_SIZE PAGE_SIZE + +/* + * On systems with 4K page size, this gives 255 size classes! There is a + * trader-off here: + * - Large number of size classes is potentially wasteful as free page are + * spread across these classes + * - Small number of size classes causes large internal fragmentation + * - Probably its better to use specific size classes (empirically + * determined). NOTE: all those class sizes must be set as multiple of + * ZS_ALIGN to make sure link_free itself never has to span 2 pages. + * + * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN + * (reason above) + */ +#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8) +#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \ + ZS_SIZE_CLASS_DELTA + 1) + +/* + * We do not maintain any list for completely empty or full pages + */ +enum fullness_group { + ZS_ALMOST_FULL, + ZS_ALMOST_EMPTY, + _ZS_NR_FULLNESS_GROUPS, + + ZS_EMPTY, + ZS_FULL +}; + +/* + * We assign a page to ZS_ALMOST_EMPTY fullness group when: + * n <= N / f, where + * n = number of allocated objects + * N = total number of objects zspage can store + * f = 1/fullness_threshold_frac + * + * Similarly, we assign zspage to: + * ZS_ALMOST_FULL when n > N / f + * ZS_EMPTY when n == 0 + * ZS_FULL when n == N + * + * (see: fix_fullness_group()) + */ +static const int fullness_threshold_frac = 4; + +struct size_class { + /* + * Size of objects stored in this class. Must be multiple + * of ZS_ALIGN. + */ + int size; + unsigned int index; + + /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ + int pages_per_zspage; + + spinlock_t lock; + + /* stats */ + u64 pages_allocated; + + struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS]; +}; + +/* + * Placed within free objects to form a singly linked list. + * For every zspage, first_page->freelist gives head of this list. + * + * This must be power of 2 and less than or equal to ZS_ALIGN + */ +struct link_free { + /* Handle of next free chunk (encodes <PFN, obj_idx>) */ + void *next; +}; + +struct zs_pool { + struct size_class size_class[ZS_SIZE_CLASSES]; + + gfp_t flags; /* allocation flags used when growing pool */ +}; + +/* + * A zspage's class index and fullness group + * are encoded in its (first)page->mapping + */ +#define CLASS_IDX_BITS 28 +#define FULLNESS_BITS 4 +#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1) +#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1) + +struct mapping_area { +#ifdef CONFIG_PGTABLE_MAPPING + struct vm_struct *vm; /* vm area for mapping object that span pages */ +#else + char *vm_buf; /* copy buffer for objects that span pages */ +#endif + char *vm_addr; /* address of kmap_atomic()'ed pages */ + enum zs_mapmode vm_mm; /* mapping mode */ +}; + + +/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ +static DEFINE_PER_CPU(struct mapping_area, zs_map_area); + +static int is_first_page(struct page *page) +{ + return PagePrivate(page); +} + +static int is_last_page(struct page *page) +{ + return PagePrivate2(page); +} + +static void get_zspage_mapping(struct page *page, unsigned int *class_idx, + enum fullness_group *fullness) +{ + unsigned long m; + BUG_ON(!is_first_page(page)); + + m = (unsigned long)page->mapping; + *fullness = m & FULLNESS_MASK; + *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK; +} + +static void set_zspage_mapping(struct page *page, unsigned int class_idx, + enum fullness_group fullness) +{ + unsigned long m; + BUG_ON(!is_first_page(page)); + + m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) | + (fullness & FULLNESS_MASK); + page->mapping = (struct address_space *)m; +} + +/* + * zsmalloc divides the pool into various size classes where each + * class maintains a list of zspages where each zspage is divided + * into equal sized chunks. Each allocation falls into one of these + * classes depending on its size. This function returns index of the + * size class which has chunk size big enough to hold the give size. + */ +static int get_size_class_index(int size) +{ + int idx = 0; + + if (likely(size > ZS_MIN_ALLOC_SIZE)) + idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE, + ZS_SIZE_CLASS_DELTA); + + return idx; +} + +/* + * For each size class, zspages are divided into different groups + * depending on how "full" they are. This was done so that we could + * easily find empty or nearly empty zspages when we try to shrink + * the pool (not yet implemented). This function returns fullness + * status of the given page. + */ +static enum fullness_group get_fullness_group(struct page *page) +{ + int inuse, max_objects; + enum fullness_group fg; + BUG_ON(!is_first_page(page)); + + inuse = page->inuse; + max_objects = page->objects; + + if (inuse == 0) + fg = ZS_EMPTY; + else if (inuse == max_objects) + fg = ZS_FULL; + else if (inuse <= max_objects / fullness_threshold_frac) + fg = ZS_ALMOST_EMPTY; + else + fg = ZS_ALMOST_FULL; + + return fg; +} + +/* + * Each size class maintains various freelists and zspages are assigned + * to one of these freelists based on the number of live objects they + * have. This functions inserts the given zspage into the freelist + * identified by <class, fullness_group>. + */ +static void insert_zspage(struct page *page, struct size_class *class, + enum fullness_group fullness) +{ + struct page **head; + + BUG_ON(!is_first_page(page)); + + if (fullness >= _ZS_NR_FULLNESS_GROUPS) + return; + + head = &class->fullness_list[fullness]; + if (*head) + list_add_tail(&page->lru, &(*head)->lru); + + *head = page; +} + +/* + * This function removes the given zspage from the freelist identified + * by <class, fullness_group>. + */ +static void remove_zspage(struct page *page, struct size_class *class, + enum fullness_group fullness) +{ + struct page **head; + + BUG_ON(!is_first_page(page)); + + if (fullness >= _ZS_NR_FULLNESS_GROUPS) + return; + + head = &class->fullness_list[fullness]; + BUG_ON(!*head); + if (list_empty(&(*head)->lru)) + *head = NULL; + else if (*head == page) + *head = (struct page *)list_entry((*head)->lru.next, + struct page, lru); + + list_del_init(&page->lru); +} + +/* + * Each size class maintains zspages in different fullness groups depending + * on the number of live objects they contain. When allocating or freeing + * objects, the fullness status of the page can change, say, from ALMOST_FULL + * to ALMOST_EMPTY when freeing an object. This function checks if such + * a status change has occurred for the given page and accordingly moves the + * page from the freelist of the old fullness group to that of the new + * fullness group. + */ +static enum fullness_group fix_fullness_group(struct zs_pool *pool, + struct page *page) +{ + int class_idx; + struct size_class *class; + enum fullness_group currfg, newfg; + + BUG_ON(!is_first_page(page)); + + get_zspage_mapping(page, &class_idx, &currfg); + newfg = get_fullness_group(page); + if (newfg == currfg) + goto out; + + class = &pool->size_class[class_idx]; + remove_zspage(page, class, currfg); + insert_zspage(page, class, newfg); + set_zspage_mapping(page, class_idx, newfg); + +out: + return newfg; +} + +/* + * We have to decide on how many pages to link together + * to form a zspage for each size class. This is important + * to reduce wastage due to unusable space left at end of + * each zspage which is given as: + * wastage = Zp - Zp % size_class + * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ... + * + * For example, for size class of 3/8 * PAGE_SIZE, we should + * link together 3 PAGE_SIZE sized pages to form a zspage + * since then we can perfectly fit in 8 such objects. + */ +static int get_pages_per_zspage(int class_size) +{ + int i, max_usedpc = 0; + /* zspage order which gives maximum used size per KB */ + int max_usedpc_order = 1; + + for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) { + int zspage_size; + int waste, usedpc; + + zspage_size = i * PAGE_SIZE; + waste = zspage_size % class_size; + usedpc = (zspage_size - waste) * 100 / zspage_size; + + if (usedpc > max_usedpc) { + max_usedpc = usedpc; + max_usedpc_order = i; + } + } + + return max_usedpc_order; +} + +/* + * A single 'zspage' is composed of many system pages which are + * linked together using fields in struct page. This function finds + * the first/head page, given any component page of a zspage. + */ +static struct page *get_first_page(struct page *page) +{ + if (is_first_page(page)) + return page; + else + return page->first_page; +} + +static struct page *get_next_page(struct page *page) +{ + struct page *next; + + if (is_last_page(page)) + next = NULL; + else if (is_first_page(page)) + next = (struct page *)page_private(page); + else + next = list_entry(page->lru.next, struct page, lru); + + return next; +} + +/* + * Encode <page, obj_idx> as a single handle value. + * On hardware platforms with physical memory starting at 0x0 the pfn + * could be 0 so we ensure that the handle will never be 0 by adjusting the + * encoded obj_idx value before encoding. + */ +static void *obj_location_to_handle(struct page *page, unsigned long obj_idx) +{ + unsigned long handle; + + if (!page) { + BUG_ON(obj_idx); + return NULL; + } + + handle = page_to_pfn(page) << OBJ_INDEX_BITS; + handle |= ((obj_idx + 1) & OBJ_INDEX_MASK); + + return (void *)handle; +} + +/* + * Decode <page, obj_idx> pair from the given object handle. We adjust the + * decoded obj_idx back to its original value since it was adjusted in + * obj_location_to_handle(). + */ +static void obj_handle_to_location(unsigned long handle, struct page **page, + unsigned long *obj_idx) +{ + *page = pfn_to_page(handle >> OBJ_INDEX_BITS); + *obj_idx = (handle & OBJ_INDEX_MASK) - 1; +} + +static unsigned long obj_idx_to_offset(struct page *page, + unsigned long obj_idx, int class_size) +{ + unsigned long off = 0; + + if (!is_first_page(page)) + off = page->index; + + return off + obj_idx * class_size; +} + +static void reset_page(struct page *page) +{ + clear_bit(PG_private, &page->flags); + clear_bit(PG_private_2, &page->flags); + set_page_private(page, 0); + page->mapping = NULL; + page->freelist = NULL; + page_mapcount_reset(page); +} + +static void free_zspage(struct page *first_page) +{ + struct page *nextp, *tmp, *head_extra; + + BUG_ON(!is_first_page(first_page)); + BUG_ON(first_page->inuse); + + head_extra = (struct page *)page_private(first_page); + + reset_page(first_page); + __free_page(first_page); + + /* zspage with only 1 system page */ + if (!head_extra) + return; + + list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) { + list_del(&nextp->lru); + reset_page(nextp); + __free_page(nextp); + } + reset_page(head_extra); + __free_page(head_extra); +} + +/* Initialize a newly allocated zspage */ +static void init_zspage(struct page *first_page, struct size_class *class) +{ + unsigned long off = 0; + struct page *page = first_page; + + BUG_ON(!is_first_page(first_page)); + while (page) { + struct page *next_page; + struct link_free *link; + unsigned int i, objs_on_page; + + /* + * page->index stores offset of first object starting + * in the page. For the first page, this is always 0, + * so we use first_page->index (aka ->freelist) to store + * head of corresponding zspage's freelist. + */ + if (page != first_page) + page->index = off; + + link = (struct link_free *)kmap_atomic(page) + + off / sizeof(*link); + objs_on_page = (PAGE_SIZE - off) / class->size; + + for (i = 1; i <= objs_on_page; i++) { + off += class->size; + if (off < PAGE_SIZE) { + link->next = obj_location_to_handle(page, i); + link += class->size / sizeof(*link); + } + } + + /* + * We now come to the last (full or partial) object on this + * page, which must point to the first object on the next + * page (if present) + */ + next_page = get_next_page(page); + link->next = obj_location_to_handle(next_page, 0); + kunmap_atomic(link); + page = next_page; + off = (off + class->size) % PAGE_SIZE; + } +} + +/* + * Allocate a zspage for the given size class + */ +static struct page *alloc_zspage(struct size_class *class, gfp_t flags) +{ + int i, error; + struct page *first_page = NULL, *uninitialized_var(prev_page); + + /* + * Allocate individual pages and link them together as: + * 1. first page->private = first sub-page + * 2. all sub-pages are linked together using page->lru + * 3. each sub-page is linked to the first page using page->first_page + * + * For each size class, First/Head pages are linked together using + * page->lru. Also, we set PG_private to identify the first page + * (i.e. no other sub-page has this flag set) and PG_private_2 to + * identify the last page. + */ + error = -ENOMEM; + for (i = 0; i < class->pages_per_zspage; i++) { + struct page *page; + + page = alloc_page(flags); + if (!page) + goto cleanup; + + INIT_LIST_HEAD(&page->lru); + if (i == 0) { /* first page */ + SetPagePrivate(page); + set_page_private(page, 0); + first_page = page; + first_page->inuse = 0; + } + if (i == 1) + set_page_private(first_page, (unsigned long)page); + if (i >= 1) + page->first_page = first_page; + if (i >= 2) + list_add(&page->lru, &prev_page->lru); + if (i == class->pages_per_zspage - 1) /* last page */ + SetPagePrivate2(page); + prev_page = page; + } + + init_zspage(first_page, class); + + first_page->freelist = obj_location_to_handle(first_page, 0); + /* Maximum number of objects we can store in this zspage */ + first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size; + + error = 0; /* Success */ + +cleanup: + if (unlikely(error) && first_page) { + free_zspage(first_page); + first_page = NULL; + } + + return first_page; +} + +static struct page *find_get_zspage(struct size_class *class) +{ + int i; + struct page *page; + + for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) { + page = class->fullness_list[i]; + if (page) + break; + } + + return page; +} + +#ifdef CONFIG_PGTABLE_MAPPING +static inline int __zs_cpu_up(struct mapping_area *area) +{ + /* + * Make sure we don't leak memory if a cpu UP notification + * and zs_init() race and both call zs_cpu_up() on the same cpu + */ + if (area->vm) + return 0; + area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL); + if (!area->vm) + return -ENOMEM; + return 0; +} + +static inline void __zs_cpu_down(struct mapping_area *area) +{ + if (area->vm) + free_vm_area(area->vm); + area->vm = NULL; +} + +static inline void *__zs_map_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages)); + area->vm_addr = area->vm->addr; + return area->vm_addr + off; +} + +static inline void __zs_unmap_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + unsigned long addr = (unsigned long)area->vm_addr; + + unmap_kernel_range(addr, PAGE_SIZE * 2); +} + +#else /* CONFIG_PGTABLE_MAPPING */ + +static inline int __zs_cpu_up(struct mapping_area *area) +{ + /* + * Make sure we don't leak memory if a cpu UP notification + * and zs_init() race and both call zs_cpu_up() on the same cpu + */ + if (area->vm_buf) + return 0; + area->vm_buf = (char *)__get_free_page(GFP_KERNEL); + if (!area->vm_buf) + return -ENOMEM; + return 0; +} + +static inline void __zs_cpu_down(struct mapping_area *area) +{ + if (area->vm_buf) + free_page((unsigned long)area->vm_buf); + area->vm_buf = NULL; +} + +static void *__zs_map_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + int sizes[2]; + void *addr; + char *buf = area->vm_buf; + + /* disable page faults to match kmap_atomic() return conditions */ + pagefault_disable(); + + /* no read fastpath */ + if (area->vm_mm == ZS_MM_WO) + goto out; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = size - sizes[0]; + + /* copy object to per-cpu buffer */ + addr = kmap_atomic(pages[0]); + memcpy(buf, addr + off, sizes[0]); + kunmap_atomic(addr); + addr = kmap_atomic(pages[1]); + memcpy(buf + sizes[0], addr, sizes[1]); + kunmap_atomic(addr); +out: + return area->vm_buf; +} + +static void __zs_unmap_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + int sizes[2]; + void *addr; + char *buf = area->vm_buf; + + /* no write fastpath */ + if (area->vm_mm == ZS_MM_RO) + goto out; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = size - sizes[0]; + + /* copy per-cpu buffer to object */ + addr = kmap_atomic(pages[0]); + memcpy(addr + off, buf, sizes[0]); + kunmap_atomic(addr); + addr = kmap_atomic(pages[1]); + memcpy(addr, buf + sizes[0], sizes[1]); + kunmap_atomic(addr); + +out: + /* enable page faults to match kunmap_atomic() return conditions */ + pagefault_enable(); +} + +#endif /* CONFIG_PGTABLE_MAPPING */ + +static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action, + void *pcpu) +{ + int ret, cpu = (long)pcpu; + struct mapping_area *area; + + switch (action) { + case CPU_UP_PREPARE: + area = &per_cpu(zs_map_area, cpu); + ret = __zs_cpu_up(area); + if (ret) + return notifier_from_errno(ret); + break; + case CPU_DEAD: + case CPU_UP_CANCELED: + area = &per_cpu(zs_map_area, cpu); + __zs_cpu_down(area); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block zs_cpu_nb = { + .notifier_call = zs_cpu_notifier +}; + +static void zs_exit(void) +{ + int cpu; + + cpu_notifier_register_begin(); + + for_each_online_cpu(cpu) + zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu); + __unregister_cpu_notifier(&zs_cpu_nb); + + cpu_notifier_register_done(); +} + +static int zs_init(void) +{ + int cpu, ret; + + cpu_notifier_register_begin(); + + __register_cpu_notifier(&zs_cpu_nb); + for_each_online_cpu(cpu) { + ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu); + if (notifier_to_errno(ret)) { + cpu_notifier_register_done(); + goto fail; + } + } + + cpu_notifier_register_done(); + + return 0; +fail: + zs_exit(); + return notifier_to_errno(ret); +} + +/** + * zs_create_pool - Creates an allocation pool to work from. + * @flags: allocation flags used to allocate pool metadata + * + * This function must be called before anything when using + * the zsmalloc allocator. + * + * On success, a pointer to the newly created pool is returned, + * otherwise NULL. + */ +struct zs_pool *zs_create_pool(gfp_t flags) +{ + int i, ovhd_size; + struct zs_pool *pool; + + ovhd_size = roundup(sizeof(*pool), PAGE_SIZE); + pool = kzalloc(ovhd_size, GFP_KERNEL); + if (!pool) + return NULL; + + for (i = 0; i < ZS_SIZE_CLASSES; i++) { + int size; + struct size_class *class; + + size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA; + if (size > ZS_MAX_ALLOC_SIZE) + size = ZS_MAX_ALLOC_SIZE; + + class = &pool->size_class[i]; + class->size = size; + class->index = i; + spin_lock_init(&class->lock); + class->pages_per_zspage = get_pages_per_zspage(size); + + } + + pool->flags = flags; + + return pool; +} +EXPORT_SYMBOL_GPL(zs_create_pool); + +void zs_destroy_pool(struct zs_pool *pool) +{ + int i; + + for (i = 0; i < ZS_SIZE_CLASSES; i++) { + int fg; + struct size_class *class = &pool->size_class[i]; + + for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) { + if (class->fullness_list[fg]) { + pr_info("Freeing non-empty class with size %db, fullness group %d\n", + class->size, fg); + } + } + } + kfree(pool); +} +EXPORT_SYMBOL_GPL(zs_destroy_pool); + +/** + * zs_malloc - Allocate block of given size from pool. + * @pool: pool to allocate from + * @size: size of block to allocate + * + * On success, handle to the allocated object is returned, + * otherwise 0. + * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. + */ +unsigned long zs_malloc(struct zs_pool *pool, size_t size) +{ + unsigned long obj; + struct link_free *link; + int class_idx; + struct size_class *class; + + struct page *first_page, *m_page; + unsigned long m_objidx, m_offset; + + if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) + return 0; + + class_idx = get_size_class_index(size); + class = &pool->size_class[class_idx]; + BUG_ON(class_idx != class->index); + + spin_lock(&class->lock); + first_page = find_get_zspage(class); + + if (!first_page) { + spin_unlock(&class->lock); + first_page = alloc_zspage(class, pool->flags); + if (unlikely(!first_page)) + return 0; + + set_zspage_mapping(first_page, class->index, ZS_EMPTY); + spin_lock(&class->lock); + class->pages_allocated += class->pages_per_zspage; + } + + obj = (unsigned long)first_page->freelist; + obj_handle_to_location(obj, &m_page, &m_objidx); + m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); + + link = (struct link_free *)kmap_atomic(m_page) + + m_offset / sizeof(*link); + first_page->freelist = link->next; + memset(link, POISON_INUSE, sizeof(*link)); + kunmap_atomic(link); + + first_page->inuse++; + /* Now move the zspage to another fullness group, if required */ + fix_fullness_group(pool, first_page); + spin_unlock(&class->lock); + + return obj; +} +EXPORT_SYMBOL_GPL(zs_malloc); + +void zs_free(struct zs_pool *pool, unsigned long obj) +{ + struct link_free *link; + struct page *first_page, *f_page; + unsigned long f_objidx, f_offset; + + int class_idx; + struct size_class *class; + enum fullness_group fullness; + + if (unlikely(!obj)) + return; + + obj_handle_to_location(obj, &f_page, &f_objidx); + first_page = get_first_page(f_page); + + get_zspage_mapping(first_page, &class_idx, &fullness); + class = &pool->size_class[class_idx]; + f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); + + spin_lock(&class->lock); + + /* Insert this object in containing zspage's freelist */ + link = (struct link_free *)((unsigned char *)kmap_atomic(f_page) + + f_offset); + link->next = first_page->freelist; + kunmap_atomic(link); + first_page->freelist = (void *)obj; + + first_page->inuse--; + fullness = fix_fullness_group(pool, first_page); + + if (fullness == ZS_EMPTY) + class->pages_allocated -= class->pages_per_zspage; + + spin_unlock(&class->lock); + + if (fullness == ZS_EMPTY) + free_zspage(first_page); +} +EXPORT_SYMBOL_GPL(zs_free); + +/** + * zs_map_object - get address of allocated object from handle. + * @pool: pool from which the object was allocated + * @handle: handle returned from zs_malloc + * + * Before using an object allocated from zs_malloc, it must be mapped using + * this function. When done with the object, it must be unmapped using + * zs_unmap_object. + * + * Only one object can be mapped per cpu at a time. There is no protection + * against nested mappings. + * + * This function returns with preemption and page faults disabled. + */ +void *zs_map_object(struct zs_pool *pool, unsigned long handle, + enum zs_mapmode mm) +{ + struct page *page; + unsigned long obj_idx, off; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + struct page *pages[2]; + + BUG_ON(!handle); + + /* + * Because we use per-cpu mapping areas shared among the + * pools/users, we can't allow mapping in interrupt context + * because it can corrupt another users mappings. + */ + BUG_ON(in_interrupt()); + + obj_handle_to_location(handle, &page, &obj_idx); + get_zspage_mapping(get_first_page(page), &class_idx, &fg); + class = &pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + + area = &get_cpu_var(zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ + area->vm_addr = kmap_atomic(page); + return area->vm_addr + off; + } + + /* this object spans two pages */ + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + return __zs_map_object(area, pages, off, class->size); +} +EXPORT_SYMBOL_GPL(zs_map_object); + +void zs_unmap_object(struct zs_pool *pool, unsigned long handle) +{ + struct page *page; + unsigned long obj_idx, off; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + + BUG_ON(!handle); + + obj_handle_to_location(handle, &page, &obj_idx); + get_zspage_mapping(get_first_page(page), &class_idx, &fg); + class = &pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + + area = this_cpu_ptr(&zs_map_area); + if (off + class->size <= PAGE_SIZE) + kunmap_atomic(area->vm_addr); + else { + struct page *pages[2]; + + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + __zs_unmap_object(area, pages, off, class->size); + } + put_cpu_var(zs_map_area); +} +EXPORT_SYMBOL_GPL(zs_unmap_object); + +u64 zs_get_total_size_bytes(struct zs_pool *pool) +{ + int i; + u64 npages = 0; + + for (i = 0; i < ZS_SIZE_CLASSES; i++) + npages += pool->size_class[i].pages_allocated; + + return npages << PAGE_SHIFT; +} +EXPORT_SYMBOL_GPL(zs_get_total_size_bytes); + +module_init(zs_init); +module_exit(zs_exit); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>"); diff --git a/mm/zswap.c b/mm/zswap.c new file mode 100644 index 00000000000..008388fe7b0 --- /dev/null +++ b/mm/zswap.c @@ -0,0 +1,940 @@ +/* + * zswap.c - zswap driver file + * + * zswap is a backend for frontswap that takes pages that are in the process + * of being swapped out and attempts to compress and store them in a + * RAM-based memory pool. This can result in a significant I/O reduction on + * the swap device and, in the case where decompressing from RAM is faster + * than reading from the swap device, can also improve workload performance. + * + * Copyright (C) 2012 Seth Jennings <sjenning@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. +*/ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/highmem.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/atomic.h> +#include <linux/frontswap.h> +#include <linux/rbtree.h> +#include <linux/swap.h> +#include <linux/crypto.h> +#include <linux/mempool.h> +#include <linux/zbud.h> + +#include <linux/mm_types.h> +#include <linux/page-flags.h> +#include <linux/swapops.h> +#include <linux/writeback.h> +#include <linux/pagemap.h> + +/********************************* +* statistics +**********************************/ +/* Number of memory pages used by the compressed pool */ +static u64 zswap_pool_pages; +/* The number of compressed pages currently stored in zswap */ +static atomic_t zswap_stored_pages = ATOMIC_INIT(0); + +/* + * The statistics below are not protected from concurrent access for + * performance reasons so they may not be a 100% accurate. However, + * they do provide useful information on roughly how many times a + * certain event is occurring. +*/ + +/* Pool limit was hit (see zswap_max_pool_percent) */ +static u64 zswap_pool_limit_hit; +/* Pages written back when pool limit was reached */ +static u64 zswap_written_back_pages; +/* Store failed due to a reclaim failure after pool limit was reached */ +static u64 zswap_reject_reclaim_fail; +/* Compressed page was too big for the allocator to (optimally) store */ +static u64 zswap_reject_compress_poor; +/* Store failed because underlying allocator could not get memory */ +static u64 zswap_reject_alloc_fail; +/* Store failed because the entry metadata could not be allocated (rare) */ +static u64 zswap_reject_kmemcache_fail; +/* Duplicate store was encountered (rare) */ +static u64 zswap_duplicate_entry; + +/********************************* +* tunables +**********************************/ +/* Enable/disable zswap (disabled by default, fixed at boot for now) */ +static bool zswap_enabled __read_mostly; +module_param_named(enabled, zswap_enabled, bool, 0444); + +/* Compressor to be used by zswap (fixed at boot for now) */ +#define ZSWAP_COMPRESSOR_DEFAULT "lzo" +static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT; +module_param_named(compressor, zswap_compressor, charp, 0444); + +/* The maximum percentage of memory that the compressed pool can occupy */ +static unsigned int zswap_max_pool_percent = 20; +module_param_named(max_pool_percent, + zswap_max_pool_percent, uint, 0644); + +/* zbud_pool is shared by all of zswap backend */ +static struct zbud_pool *zswap_pool; + +/********************************* +* compression functions +**********************************/ +/* per-cpu compression transforms */ +static struct crypto_comp * __percpu *zswap_comp_pcpu_tfms; + +enum comp_op { + ZSWAP_COMPOP_COMPRESS, + ZSWAP_COMPOP_DECOMPRESS +}; + +static int zswap_comp_op(enum comp_op op, const u8 *src, unsigned int slen, + u8 *dst, unsigned int *dlen) +{ + struct crypto_comp *tfm; + int ret; + + tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, get_cpu()); + switch (op) { + case ZSWAP_COMPOP_COMPRESS: + ret = crypto_comp_compress(tfm, src, slen, dst, dlen); + break; + case ZSWAP_COMPOP_DECOMPRESS: + ret = crypto_comp_decompress(tfm, src, slen, dst, dlen); + break; + default: + ret = -EINVAL; + } + + put_cpu(); + return ret; +} + +static int __init zswap_comp_init(void) +{ + if (!crypto_has_comp(zswap_compressor, 0, 0)) { + pr_info("%s compressor not available\n", zswap_compressor); + /* fall back to default compressor */ + zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT; + if (!crypto_has_comp(zswap_compressor, 0, 0)) + /* can't even load the default compressor */ + return -ENODEV; + } + pr_info("using %s compressor\n", zswap_compressor); + + /* alloc percpu transforms */ + zswap_comp_pcpu_tfms = alloc_percpu(struct crypto_comp *); + if (!zswap_comp_pcpu_tfms) + return -ENOMEM; + return 0; +} + +static void zswap_comp_exit(void) +{ + /* free percpu transforms */ + if (zswap_comp_pcpu_tfms) + free_percpu(zswap_comp_pcpu_tfms); +} + +/********************************* +* data structures +**********************************/ +/* + * struct zswap_entry + * + * This structure contains the metadata for tracking a single compressed + * page within zswap. + * + * rbnode - links the entry into red-black tree for the appropriate swap type + * refcount - the number of outstanding reference to the entry. This is needed + * to protect against premature freeing of the entry by code + * concurrent calls to load, invalidate, and writeback. The lock + * for the zswap_tree structure that contains the entry must + * be held while changing the refcount. Since the lock must + * be held, there is no reason to also make refcount atomic. + * offset - the swap offset for the entry. Index into the red-black tree. + * handle - zbud allocation handle that stores the compressed page data + * length - the length in bytes of the compressed page data. Needed during + * decompression + */ +struct zswap_entry { + struct rb_node rbnode; + pgoff_t offset; + int refcount; + unsigned int length; + unsigned long handle; +}; + +struct zswap_header { + swp_entry_t swpentry; +}; + +/* + * The tree lock in the zswap_tree struct protects a few things: + * - the rbtree + * - the refcount field of each entry in the tree + */ +struct zswap_tree { + struct rb_root rbroot; + spinlock_t lock; +}; + +static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; + +/********************************* +* zswap entry functions +**********************************/ +static struct kmem_cache *zswap_entry_cache; + +static int zswap_entry_cache_create(void) +{ + zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); + return zswap_entry_cache == NULL; +} + +static void zswap_entry_cache_destory(void) +{ + kmem_cache_destroy(zswap_entry_cache); +} + +static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp) +{ + struct zswap_entry *entry; + entry = kmem_cache_alloc(zswap_entry_cache, gfp); + if (!entry) + return NULL; + entry->refcount = 1; + RB_CLEAR_NODE(&entry->rbnode); + return entry; +} + +static void zswap_entry_cache_free(struct zswap_entry *entry) +{ + kmem_cache_free(zswap_entry_cache, entry); +} + +/********************************* +* rbtree functions +**********************************/ +static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset) +{ + struct rb_node *node = root->rb_node; + struct zswap_entry *entry; + + while (node) { + entry = rb_entry(node, struct zswap_entry, rbnode); + if (entry->offset > offset) + node = node->rb_left; + else if (entry->offset < offset) + node = node->rb_right; + else + return entry; + } + return NULL; +} + +/* + * In the case that a entry with the same offset is found, a pointer to + * the existing entry is stored in dupentry and the function returns -EEXIST + */ +static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry, + struct zswap_entry **dupentry) +{ + struct rb_node **link = &root->rb_node, *parent = NULL; + struct zswap_entry *myentry; + + while (*link) { + parent = *link; + myentry = rb_entry(parent, struct zswap_entry, rbnode); + if (myentry->offset > entry->offset) + link = &(*link)->rb_left; + else if (myentry->offset < entry->offset) + link = &(*link)->rb_right; + else { + *dupentry = myentry; + return -EEXIST; + } + } + rb_link_node(&entry->rbnode, parent, link); + rb_insert_color(&entry->rbnode, root); + return 0; +} + +static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry) +{ + if (!RB_EMPTY_NODE(&entry->rbnode)) { + rb_erase(&entry->rbnode, root); + RB_CLEAR_NODE(&entry->rbnode); + } +} + +/* + * Carries out the common pattern of freeing and entry's zbud allocation, + * freeing the entry itself, and decrementing the number of stored pages. + */ +static void zswap_free_entry(struct zswap_entry *entry) +{ + zbud_free(zswap_pool, entry->handle); + zswap_entry_cache_free(entry); + atomic_dec(&zswap_stored_pages); + zswap_pool_pages = zbud_get_pool_size(zswap_pool); +} + +/* caller must hold the tree lock */ +static void zswap_entry_get(struct zswap_entry *entry) +{ + entry->refcount++; +} + +/* caller must hold the tree lock +* remove from the tree and free it, if nobody reference the entry +*/ +static void zswap_entry_put(struct zswap_tree *tree, + struct zswap_entry *entry) +{ + int refcount = --entry->refcount; + + BUG_ON(refcount < 0); + if (refcount == 0) { + zswap_rb_erase(&tree->rbroot, entry); + zswap_free_entry(entry); + } +} + +/* caller must hold the tree lock */ +static struct zswap_entry *zswap_entry_find_get(struct rb_root *root, + pgoff_t offset) +{ + struct zswap_entry *entry = NULL; + + entry = zswap_rb_search(root, offset); + if (entry) + zswap_entry_get(entry); + + return entry; +} + +/********************************* +* per-cpu code +**********************************/ +static DEFINE_PER_CPU(u8 *, zswap_dstmem); + +static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu) +{ + struct crypto_comp *tfm; + u8 *dst; + + switch (action) { + case CPU_UP_PREPARE: + tfm = crypto_alloc_comp(zswap_compressor, 0, 0); + if (IS_ERR(tfm)) { + pr_err("can't allocate compressor transform\n"); + return NOTIFY_BAD; + } + *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = tfm; + dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!dst) { + pr_err("can't allocate compressor buffer\n"); + crypto_free_comp(tfm); + *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL; + return NOTIFY_BAD; + } + per_cpu(zswap_dstmem, cpu) = dst; + break; + case CPU_DEAD: + case CPU_UP_CANCELED: + tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu); + if (tfm) { + crypto_free_comp(tfm); + *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL; + } + dst = per_cpu(zswap_dstmem, cpu); + kfree(dst); + per_cpu(zswap_dstmem, cpu) = NULL; + break; + default: + break; + } + return NOTIFY_OK; +} + +static int zswap_cpu_notifier(struct notifier_block *nb, + unsigned long action, void *pcpu) +{ + unsigned long cpu = (unsigned long)pcpu; + return __zswap_cpu_notifier(action, cpu); +} + +static struct notifier_block zswap_cpu_notifier_block = { + .notifier_call = zswap_cpu_notifier +}; + +static int zswap_cpu_init(void) +{ + unsigned long cpu; + + cpu_notifier_register_begin(); + for_each_online_cpu(cpu) + if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK) + goto cleanup; + __register_cpu_notifier(&zswap_cpu_notifier_block); + cpu_notifier_register_done(); + return 0; + +cleanup: + for_each_online_cpu(cpu) + __zswap_cpu_notifier(CPU_UP_CANCELED, cpu); + cpu_notifier_register_done(); + return -ENOMEM; +} + +/********************************* +* helpers +**********************************/ +static bool zswap_is_full(void) +{ + return totalram_pages * zswap_max_pool_percent / 100 < + zswap_pool_pages; +} + +/********************************* +* writeback code +**********************************/ +/* return enum for zswap_get_swap_cache_page */ +enum zswap_get_swap_ret { + ZSWAP_SWAPCACHE_NEW, + ZSWAP_SWAPCACHE_EXIST, + ZSWAP_SWAPCACHE_FAIL, +}; + +/* + * zswap_get_swap_cache_page + * + * This is an adaption of read_swap_cache_async() + * + * This function tries to find a page with the given swap entry + * in the swapper_space address space (the swap cache). If the page + * is found, it is returned in retpage. Otherwise, a page is allocated, + * added to the swap cache, and returned in retpage. + * + * If success, the swap cache page is returned in retpage + * Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache + * Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated, + * the new page is added to swapcache and locked + * Returns ZSWAP_SWAPCACHE_FAIL on error + */ +static int zswap_get_swap_cache_page(swp_entry_t entry, + struct page **retpage) +{ + struct page *found_page, *new_page = NULL; + struct address_space *swapper_space = swap_address_space(entry); + int err; + + *retpage = NULL; + do { + /* + * First check the swap cache. Since this is normally + * called after lookup_swap_cache() failed, re-calling + * that would confuse statistics. + */ + found_page = find_get_page(swapper_space, entry.val); + if (found_page) + break; + + /* + * Get a new page to read into from swap. + */ + if (!new_page) { + new_page = alloc_page(GFP_KERNEL); + if (!new_page) + break; /* Out of memory */ + } + + /* + * call radix_tree_preload() while we can wait. + */ + err = radix_tree_preload(GFP_KERNEL); + if (err) + break; + + /* + * Swap entry may have been freed since our caller observed it. + */ + err = swapcache_prepare(entry); + if (err == -EEXIST) { /* seems racy */ + radix_tree_preload_end(); + continue; + } + if (err) { /* swp entry is obsolete ? */ + radix_tree_preload_end(); + break; + } + + /* May fail (-ENOMEM) if radix-tree node allocation failed. */ + __set_page_locked(new_page); + SetPageSwapBacked(new_page); + err = __add_to_swap_cache(new_page, entry); + if (likely(!err)) { + radix_tree_preload_end(); + lru_cache_add_anon(new_page); + *retpage = new_page; + return ZSWAP_SWAPCACHE_NEW; + } + radix_tree_preload_end(); + ClearPageSwapBacked(new_page); + __clear_page_locked(new_page); + /* + * add_to_swap_cache() doesn't return -EEXIST, so we can safely + * clear SWAP_HAS_CACHE flag. + */ + swapcache_free(entry, NULL); + } while (err != -ENOMEM); + + if (new_page) + page_cache_release(new_page); + if (!found_page) + return ZSWAP_SWAPCACHE_FAIL; + *retpage = found_page; + return ZSWAP_SWAPCACHE_EXIST; +} + +/* + * Attempts to free an entry by adding a page to the swap cache, + * decompressing the entry data into the page, and issuing a + * bio write to write the page back to the swap device. + * + * This can be thought of as a "resumed writeback" of the page + * to the swap device. We are basically resuming the same swap + * writeback path that was intercepted with the frontswap_store() + * in the first place. After the page has been decompressed into + * the swap cache, the compressed version stored by zswap can be + * freed. + */ +static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle) +{ + struct zswap_header *zhdr; + swp_entry_t swpentry; + struct zswap_tree *tree; + pgoff_t offset; + struct zswap_entry *entry; + struct page *page; + u8 *src, *dst; + unsigned int dlen; + int ret; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + }; + + /* extract swpentry from data */ + zhdr = zbud_map(pool, handle); + swpentry = zhdr->swpentry; /* here */ + zbud_unmap(pool, handle); + tree = zswap_trees[swp_type(swpentry)]; + offset = swp_offset(swpentry); + + /* find and ref zswap entry */ + spin_lock(&tree->lock); + entry = zswap_entry_find_get(&tree->rbroot, offset); + if (!entry) { + /* entry was invalidated */ + spin_unlock(&tree->lock); + return 0; + } + spin_unlock(&tree->lock); + BUG_ON(offset != entry->offset); + + /* try to allocate swap cache page */ + switch (zswap_get_swap_cache_page(swpentry, &page)) { + case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */ + ret = -ENOMEM; + goto fail; + + case ZSWAP_SWAPCACHE_EXIST: + /* page is already in the swap cache, ignore for now */ + page_cache_release(page); + ret = -EEXIST; + goto fail; + + case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* decompress */ + dlen = PAGE_SIZE; + src = (u8 *)zbud_map(zswap_pool, entry->handle) + + sizeof(struct zswap_header); + dst = kmap_atomic(page); + ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, + entry->length, dst, &dlen); + kunmap_atomic(dst); + zbud_unmap(zswap_pool, entry->handle); + BUG_ON(ret); + BUG_ON(dlen != PAGE_SIZE); + + /* page is up to date */ + SetPageUptodate(page); + } + + /* move it to the tail of the inactive list after end_writeback */ + SetPageReclaim(page); + + /* start writeback */ + __swap_writepage(page, &wbc, end_swap_bio_write); + page_cache_release(page); + zswap_written_back_pages++; + + spin_lock(&tree->lock); + /* drop local reference */ + zswap_entry_put(tree, entry); + + /* + * There are two possible situations for entry here: + * (1) refcount is 1(normal case), entry is valid and on the tree + * (2) refcount is 0, entry is freed and not on the tree + * because invalidate happened during writeback + * search the tree and free the entry if find entry + */ + if (entry == zswap_rb_search(&tree->rbroot, offset)) + zswap_entry_put(tree, entry); + spin_unlock(&tree->lock); + + goto end; + + /* + * if we get here due to ZSWAP_SWAPCACHE_EXIST + * a load may happening concurrently + * it is safe and okay to not free the entry + * if we free the entry in the following put + * it it either okay to return !0 + */ +fail: + spin_lock(&tree->lock); + zswap_entry_put(tree, entry); + spin_unlock(&tree->lock); + +end: + return ret; +} + +/********************************* +* frontswap hooks +**********************************/ +/* attempts to compress and store an single page */ +static int zswap_frontswap_store(unsigned type, pgoff_t offset, + struct page *page) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry, *dupentry; + int ret; + unsigned int dlen = PAGE_SIZE, len; + unsigned long handle; + char *buf; + u8 *src, *dst; + struct zswap_header *zhdr; + + if (!tree) { + ret = -ENODEV; + goto reject; + } + + /* reclaim space if needed */ + if (zswap_is_full()) { + zswap_pool_limit_hit++; + if (zbud_reclaim_page(zswap_pool, 8)) { + zswap_reject_reclaim_fail++; + ret = -ENOMEM; + goto reject; + } + } + + /* allocate entry */ + entry = zswap_entry_cache_alloc(GFP_KERNEL); + if (!entry) { + zswap_reject_kmemcache_fail++; + ret = -ENOMEM; + goto reject; + } + + /* compress */ + dst = get_cpu_var(zswap_dstmem); + src = kmap_atomic(page); + ret = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen); + kunmap_atomic(src); + if (ret) { + ret = -EINVAL; + goto freepage; + } + + /* store */ + len = dlen + sizeof(struct zswap_header); + ret = zbud_alloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN, + &handle); + if (ret == -ENOSPC) { + zswap_reject_compress_poor++; + goto freepage; + } + if (ret) { + zswap_reject_alloc_fail++; + goto freepage; + } + zhdr = zbud_map(zswap_pool, handle); + zhdr->swpentry = swp_entry(type, offset); + buf = (u8 *)(zhdr + 1); + memcpy(buf, dst, dlen); + zbud_unmap(zswap_pool, handle); + put_cpu_var(zswap_dstmem); + + /* populate entry */ + entry->offset = offset; + entry->handle = handle; + entry->length = dlen; + + /* map */ + spin_lock(&tree->lock); + do { + ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry); + if (ret == -EEXIST) { + zswap_duplicate_entry++; + /* remove from rbtree */ + zswap_rb_erase(&tree->rbroot, dupentry); + zswap_entry_put(tree, dupentry); + } + } while (ret == -EEXIST); + spin_unlock(&tree->lock); + + /* update stats */ + atomic_inc(&zswap_stored_pages); + zswap_pool_pages = zbud_get_pool_size(zswap_pool); + + return 0; + +freepage: + put_cpu_var(zswap_dstmem); + zswap_entry_cache_free(entry); +reject: + return ret; +} + +/* + * returns 0 if the page was successfully decompressed + * return -1 on entry not found or error +*/ +static int zswap_frontswap_load(unsigned type, pgoff_t offset, + struct page *page) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry; + u8 *src, *dst; + unsigned int dlen; + int ret; + + /* find */ + spin_lock(&tree->lock); + entry = zswap_entry_find_get(&tree->rbroot, offset); + if (!entry) { + /* entry was written back */ + spin_unlock(&tree->lock); + return -1; + } + spin_unlock(&tree->lock); + + /* decompress */ + dlen = PAGE_SIZE; + src = (u8 *)zbud_map(zswap_pool, entry->handle) + + sizeof(struct zswap_header); + dst = kmap_atomic(page); + ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length, + dst, &dlen); + kunmap_atomic(dst); + zbud_unmap(zswap_pool, entry->handle); + BUG_ON(ret); + + spin_lock(&tree->lock); + zswap_entry_put(tree, entry); + spin_unlock(&tree->lock); + + return 0; +} + +/* frees an entry in zswap */ +static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry; + + /* find */ + spin_lock(&tree->lock); + entry = zswap_rb_search(&tree->rbroot, offset); + if (!entry) { + /* entry was written back */ + spin_unlock(&tree->lock); + return; + } + + /* remove from rbtree */ + zswap_rb_erase(&tree->rbroot, entry); + + /* drop the initial reference from entry creation */ + zswap_entry_put(tree, entry); + + spin_unlock(&tree->lock); +} + +/* frees all zswap entries for the given swap type */ +static void zswap_frontswap_invalidate_area(unsigned type) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry, *n; + + if (!tree) + return; + + /* walk the tree and free everything */ + spin_lock(&tree->lock); + rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) + zswap_free_entry(entry); + tree->rbroot = RB_ROOT; + spin_unlock(&tree->lock); + kfree(tree); + zswap_trees[type] = NULL; +} + +static struct zbud_ops zswap_zbud_ops = { + .evict = zswap_writeback_entry +}; + +static void zswap_frontswap_init(unsigned type) +{ + struct zswap_tree *tree; + + tree = kzalloc(sizeof(struct zswap_tree), GFP_KERNEL); + if (!tree) { + pr_err("alloc failed, zswap disabled for swap type %d\n", type); + return; + } + + tree->rbroot = RB_ROOT; + spin_lock_init(&tree->lock); + zswap_trees[type] = tree; +} + +static struct frontswap_ops zswap_frontswap_ops = { + .store = zswap_frontswap_store, + .load = zswap_frontswap_load, + .invalidate_page = zswap_frontswap_invalidate_page, + .invalidate_area = zswap_frontswap_invalidate_area, + .init = zswap_frontswap_init +}; + +/********************************* +* debugfs functions +**********************************/ +#ifdef CONFIG_DEBUG_FS +#include <linux/debugfs.h> + +static struct dentry *zswap_debugfs_root; + +static int __init zswap_debugfs_init(void) +{ + if (!debugfs_initialized()) + return -ENODEV; + + zswap_debugfs_root = debugfs_create_dir("zswap", NULL); + if (!zswap_debugfs_root) + return -ENOMEM; + + debugfs_create_u64("pool_limit_hit", S_IRUGO, + zswap_debugfs_root, &zswap_pool_limit_hit); + debugfs_create_u64("reject_reclaim_fail", S_IRUGO, + zswap_debugfs_root, &zswap_reject_reclaim_fail); + debugfs_create_u64("reject_alloc_fail", S_IRUGO, + zswap_debugfs_root, &zswap_reject_alloc_fail); + debugfs_create_u64("reject_kmemcache_fail", S_IRUGO, + zswap_debugfs_root, &zswap_reject_kmemcache_fail); + debugfs_create_u64("reject_compress_poor", S_IRUGO, + zswap_debugfs_root, &zswap_reject_compress_poor); + debugfs_create_u64("written_back_pages", S_IRUGO, + zswap_debugfs_root, &zswap_written_back_pages); + debugfs_create_u64("duplicate_entry", S_IRUGO, + zswap_debugfs_root, &zswap_duplicate_entry); + debugfs_create_u64("pool_pages", S_IRUGO, + zswap_debugfs_root, &zswap_pool_pages); + debugfs_create_atomic_t("stored_pages", S_IRUGO, + zswap_debugfs_root, &zswap_stored_pages); + + return 0; +} + +static void __exit zswap_debugfs_exit(void) +{ + debugfs_remove_recursive(zswap_debugfs_root); +} +#else +static int __init zswap_debugfs_init(void) +{ + return 0; +} + +static void __exit zswap_debugfs_exit(void) { } +#endif + +/********************************* +* module init and exit +**********************************/ +static int __init init_zswap(void) +{ + if (!zswap_enabled) + return 0; + + pr_info("loading zswap\n"); + + zswap_pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops); + if (!zswap_pool) { + pr_err("zbud pool creation failed\n"); + goto error; + } + + if (zswap_entry_cache_create()) { + pr_err("entry cache creation failed\n"); + goto cachefail; + } + if (zswap_comp_init()) { + pr_err("compressor initialization failed\n"); + goto compfail; + } + if (zswap_cpu_init()) { + pr_err("per-cpu initialization failed\n"); + goto pcpufail; + } + + frontswap_register_ops(&zswap_frontswap_ops); + if (zswap_debugfs_init()) + pr_warn("debugfs initialization failed\n"); + return 0; +pcpufail: + zswap_comp_exit(); +compfail: + zswap_entry_cache_destory(); +cachefail: + zbud_destroy_pool(zswap_pool); +error: + return -ENOMEM; +} +/* must be late so crypto has time to come up */ +late_initcall(init_zswap); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Seth Jennings <sjenning@linux.vnet.ibm.com>"); +MODULE_DESCRIPTION("Compressed cache for swap pages"); |