From 01b931cda0bdb5c32c1f8c72b9c02ffcad5b601f Mon Sep 17 00:00:00 2001 From: Ke Liu Date: Wed, 12 Apr 2023 09:59:14 +0800 Subject: [PATCH 1/3] mm: Add memory monitor feature ohos inclusion category: feature issue: #I6UY1M CVE: NA -------------------------------- Add memory monitor feature, now use kswapd monitor in it. Signed-off-by: Ke Liu Change-Id: I2a3437b1efcaf12a9e127b6adbea18031c7c705f --- mm/Kconfig | 8 +++++++ mm/Makefile | 1 + mm/internal.h | 3 +++ mm/memory_monitor.c | 58 +++++++++++++++++++++++++++++++++++++++++++++ mm/vmscan.c | 3 +++ 5 files changed, 73 insertions(+) create mode 100644 mm/memory_monitor.c diff --git a/mm/Kconfig b/mm/Kconfig index 518378cb1267..66bcc5ac920e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -63,6 +63,14 @@ config SPARSEMEM_MANUAL endchoice +config MEMORY_MONITOR + bool "ENABLE MEMORY_MONITOR" + depends on PROC_FS + default n + help + MEMORY_MONITOR is a monitor of some memory reclaim method. + Now, kswapd wake up monitor use it. + config HYPERHOLD_FILE_LRU bool "Enable HyperHold FILE LRU" depends on HYPERHOLD && MEMCG diff --git a/mm/Makefile b/mm/Makefile index bebdabe1fce5..b0d224f52b2c 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -129,3 +129,4 @@ obj-$(CONFIG_HYPERHOLD_MEMCG) += memcg_control.o obj-$(CONFIG_HYPERHOLD_ZSWAPD) += zswapd.o zswapd_control.o obj-$(CONFIG_RECLAIM_ACCT) += reclaim_acct.o reclaimacct_show.o obj-$(CONFIG_MEM_PURGEABLE) += purgeable.o +obj-$(CONFIG_MEMORY_MONITOR) += memory_monitor.o diff --git a/mm/internal.h b/mm/internal.h index 58d60d5472d0..9fc8978e62f3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -227,6 +227,9 @@ extern unsigned long highest_memmap_pfn; /* * in mm/vmscan.c: */ +#ifdef CONFIG_MEMORY_MONITOR +extern void kswapd_monitor_wake_up_queue(void); +#endif extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); extern unsigned int shrink_page_list(struct list_head *page_list, struct pglist_data *pgdat, diff --git a/mm/memory_monitor.c b/mm/memory_monitor.c new file mode 100644 index 000000000000..88fb97466b24 --- /dev/null +++ b/mm/memory_monitor.c @@ -0,0 +1,58 @@ +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +static atomic_t kswapd_monitor = ATOMIC_INIT(0); +static DECLARE_WAIT_QUEUE_HEAD(kswapd_poll_wait); + +void kswapd_monitor_wake_up_queue(void) +{ + atomic_inc(&kswapd_monitor); + wake_up_interruptible(&kswapd_poll_wait); +} + +static __poll_t kswapd_monitor_poll(struct file *file, struct poll_table_struct *wait) +{ + struct seq_file *seq = file->private_data; + + poll_wait(file, &kswapd_poll_wait, wait); + + if (seq->poll_event != atomic_read(&kswapd_monitor)) { + seq->poll_event = atomic_read(&kswapd_monitor); + return EPOLLPRI; + } + + return EPOLLIN | EPOLLRDNORM; +} + +static int kswapd_monitor_show(struct seq_file *m, void *v) +{ + seq_printf(m, "kswapd_monitor_show kswapd_monitor %d\n", atomic_read(&kswapd_monitor)); + return 0; +} + +static int kswapd_monitor_open(struct inode *inode, struct file *file) +{ + return single_open(file, kswapd_monitor_show, NULL); +} + +static const struct proc_ops proc_kswapd_monitor_operations = { + .proc_open = kswapd_monitor_open, + .proc_poll = kswapd_monitor_poll, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init memory_monitor_init(void) +{ + proc_create("kswapd_monitor", 0, NULL, &proc_kswapd_monitor_operations); + return 0; +} + +__initcall(memory_monitor_init) diff --git a/mm/vmscan.c b/mm/vmscan.c index 5e9434b2896f..f0d1410bc76a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3949,6 +3949,9 @@ static int kswapd(void *p) */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); +#ifdef CONFIG_MEMORY_MONITOR + kswapd_monitor_wake_up_queue(); +#endif #ifdef CONFIG_RECLAIM_ACCT reclaimacct_start(KSWAPD_RECLAIM, &ra); #endif -- Gitee From 47a375a4137da3f31b9c77b27ced6e662663711e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E4=BB=BB=E6=B3=BD=E5=8D=8E?= Date: Mon, 8 May 2023 07:50:14 +0000 Subject: [PATCH 2/3] =?UTF-8?q?=E5=88=A0=E9=99=A4=E6=96=87=E4=BB=B6=20mm/K?= =?UTF-8?q?config?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- mm/Kconfig | 984 ----------------------------------------------------- 1 file changed, 984 deletions(-) delete mode 100644 mm/Kconfig diff --git a/mm/Kconfig b/mm/Kconfig deleted file mode 100644 index 66bcc5ac920e..000000000000 --- a/mm/Kconfig +++ /dev/null @@ -1,984 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only - -menu "Memory Management options" - -config SELECT_MEMORY_MODEL - def_bool y - depends on ARCH_SELECT_MEMORY_MODEL - -choice - prompt "Memory model" - depends on SELECT_MEMORY_MODEL - default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT - default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT - default FLATMEM_MANUAL - help - This option allows you to change some of the ways that - Linux manages its memory internally. Most users will - only have one option here selected by the architecture - configuration. This is normal. - -config FLATMEM_MANUAL - bool "Flat Memory" - depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE - help - This option is best suited for non-NUMA systems with - flat address space. The FLATMEM is the most efficient - system in terms of performance and resource consumption - and it is the best option for smaller systems. - - For systems that have holes in their physical address - spaces and for features like NUMA and memory hotplug, - choose "Sparse Memory". - - If unsure, choose this option (Flat Memory) over any other. - -config DISCONTIGMEM_MANUAL - bool "Discontiguous Memory" - depends on ARCH_DISCONTIGMEM_ENABLE - help - This option provides enhanced support for discontiguous - memory systems, over FLATMEM. These systems have holes - in their physical address spaces, and this option provides - more efficient handling of these holes. - - Although "Discontiguous Memory" is still used by several - architectures, it is considered deprecated in favor of - "Sparse Memory". - - If unsure, choose "Sparse Memory" over this option. - -config SPARSEMEM_MANUAL - bool "Sparse Memory" - depends on ARCH_SPARSEMEM_ENABLE - help - This will be the only option for some systems, including - memory hot-plug systems. This is normal. - - This option provides efficient support for systems with - holes is their physical address space and allows memory - hot-plug and hot-remove. - - If unsure, choose "Flat Memory" over this option. - -endchoice - -config MEMORY_MONITOR - bool "ENABLE MEMORY_MONITOR" - depends on PROC_FS - default n - help - MEMORY_MONITOR is a monitor of some memory reclaim method. - Now, kswapd wake up monitor use it. - -config HYPERHOLD_FILE_LRU - bool "Enable HyperHold FILE LRU" - depends on HYPERHOLD && MEMCG - select HYPERHOLD_MEMCG - default n - help - File-LRU is a mechanism that put file page in global lru list, - and anon page in memcg lru list(if MEMCG is enable), what's - more, recliam of anonymous pages and file page are separated. - -config HYPERHOLD_MEMCG - bool "Enable Memcg Management in HyperHold" - depends on HYPERHOLD && MEMCG - help - Add more attributes in memory cgroup, these attribute is used - to show information, shrink memory, swapin page and so on. - -config HYPERHOLD_ZSWAPD - bool "Enable zswapd thread to reclaim anon pages in background" - depends on HYPERHOLD && ZRAM - default n - help - zswapd is a kernel thread that reclaim anonymous pages in the - background. When the use of swap pages reaches the watermark - and the refault of anonymous pages is high, the content of - zram will exchanged to eswap by a certain percentage. - -config PAGE_TRACING - bool "Enable Page Tracing" - default n - help - This option enables page tracing. - -config RECLAIM_ACCT - bool "Memory reclaim delay accounting" - default n - help - Memory reclaim delay accounting. Never use it as a kernel module. - -config DISCONTIGMEM - def_bool y - depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL - -config SPARSEMEM - def_bool y - depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL - -config FLATMEM - def_bool y - depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL - -config FLAT_NODE_MEM_MAP - def_bool y - depends on !SPARSEMEM - -# -# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's -# to represent different areas of memory. This variable allows -# those dependencies to exist individually. -# -config NEED_MULTIPLE_NODES - def_bool y - depends on DISCONTIGMEM || NUMA - -# -# SPARSEMEM_EXTREME (which is the default) does some bootmem -# allocations when sparse_init() is called. If this cannot -# be done on your architecture, select this option. However, -# statically allocating the mem_section[] array can potentially -# consume vast quantities of .bss, so be careful. -# -# This option will also potentially produce smaller runtime code -# with gcc 3.4 and later. -# -config SPARSEMEM_STATIC - bool - -# -# Architecture platforms which require a two level mem_section in SPARSEMEM -# must select this option. This is usually for architecture platforms with -# an extremely sparse physical address space. -# -config SPARSEMEM_EXTREME - def_bool y - depends on SPARSEMEM && !SPARSEMEM_STATIC - -config SPARSEMEM_VMEMMAP_ENABLE - bool - -config SPARSEMEM_VMEMMAP - bool "Sparse Memory virtual memmap" - depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE - default y - help - SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise - pfn_to_page and page_to_pfn operations. This is the most - efficient option when sufficient kernel resources are available. - -config HAVE_MEMBLOCK_PHYS_MAP - bool - -config HAVE_FAST_GUP - depends on MMU - bool - -config HOLES_IN_ZONE - bool - -# Don't discard allocated memory used to track "memory" and "reserved" memblocks -# after early boot, so it can still be used to test for validity of memory. -# Also, memblocks are updated with memory hot(un)plug. -config ARCH_KEEP_MEMBLOCK - bool - -# Keep arch NUMA mapping infrastructure post-init. -config NUMA_KEEP_MEMINFO - bool - -config MEMORY_ISOLATION - bool - -# -# 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 ARCH_ENABLE_MEMORY_HOTPLUG - depends on 64BIT || BROKEN - select NUMA_KEEP_MEMINFO if NUMA - -config MEMORY_HOTPLUG_SPARSE - def_bool y - depends on SPARSEMEM && MEMORY_HOTPLUG - -config MEMORY_HOTPLUG_DEFAULT_ONLINE - bool "Online the newly added memory blocks by default" - depends on MEMORY_HOTPLUG - help - This option sets the default policy setting for memory hotplug - onlining policy (/sys/devices/system/memory/auto_online_blocks) which - determines what happens to newly added memory regions. Policy setting - can always be changed at runtime. - See Documentation/admin-guide/mm/memory-hotplug.rst for more information. - - Say Y here if you want all hot-plugged memory blocks to appear in - 'online' state by default. - Say N here if you want the default policy to keep all hot-plugged - memory blocks in 'offline' state. - -config MEMORY_HOTREMOVE - bool "Allow for memory hot remove" - select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) - depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE - depends on MIGRATION - -# Heavily threaded applications may benefit from splitting the mm-wide -# page_table_lock, so that faults on different parts of the user address -# space can be handled with less contention: split it at this NR_CPUS. -# Default to 4 for wider testing, though 8 might be more appropriate. -# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. -# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes. -# SPARC32 allocates multiple pte tables within a single page, and therefore -# a per-page lock leads to problems when multiple tables need to be locked -# at the same time (e.g. copy_page_range()). -# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. -# -config SPLIT_PTLOCK_CPUS - int - default "999999" if !MMU - default "999999" if ARM && !CPU_CACHE_VIPT - default "999999" if PARISC && !PA20 - default "999999" if SPARC32 - default "4" - -config ARCH_ENABLE_SPLIT_PMD_PTLOCK - bool - -# -# support for memory balloon -config MEMORY_BALLOON - bool - -# -# support for memory balloon compaction -config BALLOON_COMPACTION - bool "Allow for balloon memory compaction/migration" - def_bool y - depends on COMPACTION && MEMORY_BALLOON - help - Memory fragmentation introduced by ballooning might reduce - significantly the number of 2MB contiguous memory blocks that can be - used within a guest, thus imposing performance penalties associated - with the reduced number of transparent huge pages that could be used - by the guest workload. Allowing the compaction & migration for memory - pages enlisted as being part of memory balloon devices avoids the - scenario aforementioned and helps improving memory defragmentation. - -# -# support for memory compaction -config COMPACTION - bool "Allow for memory compaction" - def_bool y - select MIGRATION - depends on MMU - help - Compaction is the only memory management component to form - high order (larger physically contiguous) memory blocks - reliably. The page allocator relies on compaction heavily and - the lack of the feature can lead to unexpected OOM killer - invocations for high order memory requests. You shouldn't - disable this option unless there really is a strong reason for - it and then we would be really interested to hear about that at - linux-mm@kvack.org. - -# -# support for free page reporting -config PAGE_REPORTING - bool "Free page reporting" - def_bool n - help - Free page reporting allows for the incremental acquisition of - free pages from the buddy allocator for the purpose of reporting - those pages to another entity, such as a hypervisor, so that the - memory can be freed within the host for other uses. - -# -# support for page migration -# -config MIGRATION - bool "Page migration" - def_bool y - 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 - two situations. The first is on NUMA systems to put pages nearer - to the processors accessing. The second is when allocating huge - pages as migration can relocate pages to satisfy a huge page - allocation instead of reclaiming. - -config ARCH_ENABLE_HUGEPAGE_MIGRATION - bool - -config ARCH_ENABLE_THP_MIGRATION - bool - -config CONTIG_ALLOC - def_bool (MEMORY_ISOLATION && COMPACTION) || CMA - -config PHYS_ADDR_T_64BIT - def_bool 64BIT - -config BOUNCE - 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. - -config 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 - select SRCU - select INTERVAL_TREE - -config KSM - bool "Enable KSM for page merging" - depends on MMU - select XXHASH - help - Enable Kernel Samepage Merging: KSM periodically scans those areas - of an application's address space that an app has advised may be - mergeable. When it finds pages of identical content, it replaces - the many instances by a single page with that content, so - saving memory until one or another app needs to modify the content. - Recommended for use with KVM, or with other duplicative applications. - See Documentation/vm/ksm.rst for more information: KSM is inactive - until a program has madvised that an area is MADV_MERGEABLE, and - root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). - -config DEFAULT_MMAP_MIN_ADDR - int "Low address space to protect from user allocation" - depends on MMU - default 4096 - help - This is the portion of low virtual memory which should be protected - from userspace allocation. Keeping a user from writing to low pages - can help reduce the impact of kernel NULL pointer bugs. - - For most ia64, ppc64 and x86 users with lots of address space - a value of 65536 is reasonable and should cause no problems. - On arm and other archs it should not be higher than 32768. - Programs which use vm86 functionality or have some need to map - this low address space will need CAP_SYS_RAWIO or disable this - protection by setting the value to 0. - - This value can be changed after boot using the - /proc/sys/vm/mmap_min_addr tunable. - -config ARCH_SUPPORTS_MEMORY_FAILURE - bool - -config MEMORY_FAILURE - depends on MMU - depends on ARCH_SUPPORTS_MEMORY_FAILURE - bool "Enable recovery from hardware memory errors" - select MEMORY_ISOLATION - select RAS - help - Enables code to recover from some memory failures on systems - with MCA recovery. This allows a system to continue running - even when some of its memory has uncorrected errors. This requires - special hardware support and typically ECC memory. - -config HWPOISON_INJECT - tristate "HWPoison pages injector" - depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS - select PROC_PAGE_MONITOR - -config NOMMU_INITIAL_TRIM_EXCESS - int "Turn on mmap() excess space trimming before booting" - depends on !MMU - default 1 - help - The NOMMU mmap() frequently needs to allocate large contiguous chunks - of memory on which to store mappings, but it can only ask the system - allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently - more than it requires. To deal with this, mmap() is able to trim off - the excess and return it to the allocator. - - If trimming is enabled, the excess is trimmed off and returned to the - system allocator, which can cause extra fragmentation, particularly - if there are a lot of transient processes. - - If trimming is disabled, the excess is kept, but not used, which for - long-term mappings means that the space is wasted. - - Trimming can be dynamically controlled through a sysctl option - (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of - excess pages there must be before trimming should occur, or zero if - no trimming is to occur. - - This option specifies the initial value of this option. The default - of 1 says that all excess pages should be trimmed. - - See Documentation/admin-guide/mm/nommu-mmap.rst for more information. - -config TRANSPARENT_HUGEPAGE - bool "Transparent Hugepage Support" - depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE - select COMPACTION - select XARRAY_MULTI - help - Transparent Hugepages allows the kernel to use huge pages and - huge tlb transparently to the applications whenever possible. - This feature can improve computing performance to certain - applications by speeding up page faults during memory - allocation, by reducing the number of tlb misses and by speeding - up the pagetable walking. - - If memory constrained on embedded, you may want to say N. - -choice - prompt "Transparent Hugepage Support sysfs defaults" - depends on TRANSPARENT_HUGEPAGE - default TRANSPARENT_HUGEPAGE_ALWAYS - help - Selects the sysfs defaults for Transparent Hugepage Support. - - config TRANSPARENT_HUGEPAGE_ALWAYS - bool "always" - help - Enabling Transparent Hugepage always, can increase the - memory footprint of applications without a guaranteed - benefit but it will work automatically for all applications. - - config TRANSPARENT_HUGEPAGE_MADVISE - bool "madvise" - help - Enabling Transparent Hugepage madvise, will only provide a - performance improvement benefit to the applications using - madvise(MADV_HUGEPAGE) but it won't risk to increase the - memory footprint of applications without a guaranteed - benefit. -endchoice - -config ARCH_WANTS_THP_SWAP - def_bool n - -config THP_SWAP - def_bool y - depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP - help - Swap transparent huge pages in one piece, without splitting. - XXX: For now, swap cluster backing transparent huge page - will be split after swapout. - - For selection by architectures with reasonable THP sizes. - -# -# UP and nommu archs use km based percpu allocator -# -config NEED_PER_CPU_KM - depends on !SMP - bool - default y - -config CLEANCACHE - bool "Enable cleancache driver to cache clean pages if tmem is present" - help - Cleancache can be thought of as a page-granularity victim cache - for clean pages that the kernel's pageframe replacement algorithm - (PFRA) would like to keep around, but can't since there isn't enough - memory. So when the PFRA "evicts" a page, it first attempts to use - cleancache code to put the data contained in that page into - "transcendent memory", memory that is not directly accessible or - addressable by the kernel and is of unknown and possibly - time-varying size. And when a cleancache-enabled - filesystem wishes to access a page in a file on disk, it first - checks cleancache to see if it already contains it; if it does, - the page is copied into the kernel and a disk access is avoided. - When a transcendent memory driver is available (such as zcache or - Xen transcendent memory), a significant I/O reduction - may be achieved. When none is available, all cleancache calls - are reduced to a single pointer-compare-against-NULL resulting - in a negligible performance hit. - - If unsure, say Y to enable cleancache - -config FRONTSWAP - bool "Enable frontswap to cache swap pages if tmem is present" - depends on SWAP - help - Frontswap is so named because it can be thought of as the opposite - of a "backing" store for a swap device. The data is stored into - "transcendent memory", memory that is not directly accessible or - addressable by the kernel and is of unknown and possibly - time-varying size. When space in transcendent memory is available, - a significant swap I/O reduction may be achieved. When none is - available, all frontswap calls are reduced to a single pointer- - compare-against-NULL resulting in a negligible performance hit - 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 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 CMA_DEBUGFS - bool "CMA debugfs interface" - depends on CMA && DEBUG_FS - help - Turns on the DebugFS interface for CMA. - -config CMA_AREAS - int "Maximum count of the CMA areas" - depends on CMA - default 19 if NUMA - default 7 - help - CMA allows to create CMA areas for particular purpose, mainly, - used as device private area. This parameter sets the maximum - number of CMA area in the system. - - If unsure, leave the default value "7" in UMA and "19" in NUMA. - -config CMA_REUSE - bool "CMA reuse feature" - depends on CMA - help - If enabled, it will add MIGRATE_CMA to pcp lists and movable - allocations with __GFP_CMA flag will use cma areas prior to - movable areas. - - It improves the utilization ratio of cma areas. - -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/admin-guide/mm/soft-dirty.rst for more details. - -config ZSWAP - bool "Compressed cache for swap pages (EXPERIMENTAL)" - depends on FRONTSWAP && CRYPTO=y - select ZPOOL - 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. - -choice - prompt "Compressed cache for swap pages default compressor" - depends on ZSWAP - default ZSWAP_COMPRESSOR_DEFAULT_LZO - help - Selects the default compression algorithm for the compressed cache - for swap pages. - - For an overview what kind of performance can be expected from - a particular compression algorithm please refer to the benchmarks - available at the following LWN page: - https://lwn.net/Articles/751795/ - - If in doubt, select 'LZO'. - - The selection made here can be overridden by using the kernel - command line 'zswap.compressor=' option. - -config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE - bool "Deflate" - select CRYPTO_DEFLATE - help - Use the Deflate algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_LZO - bool "LZO" - select CRYPTO_LZO - help - Use the LZO algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_842 - bool "842" - select CRYPTO_842 - help - Use the 842 algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_LZ4 - bool "LZ4" - select CRYPTO_LZ4 - help - Use the LZ4 algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC - bool "LZ4HC" - select CRYPTO_LZ4HC - help - Use the LZ4HC algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_ZSTD - bool "zstd" - select CRYPTO_ZSTD - help - Use the zstd algorithm as the default compression algorithm. -endchoice - -config ZSWAP_COMPRESSOR_DEFAULT - string - depends on ZSWAP - default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE - default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO - default "842" if ZSWAP_COMPRESSOR_DEFAULT_842 - default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4 - default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC - default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD - default "" - -choice - prompt "Compressed cache for swap pages default allocator" - depends on ZSWAP - default ZSWAP_ZPOOL_DEFAULT_ZBUD - help - Selects the default allocator for the compressed cache for - swap pages. - The default is 'zbud' for compatibility, however please do - read the description of each of the allocators below before - making a right choice. - - The selection made here can be overridden by using the kernel - command line 'zswap.zpool=' option. - -config ZSWAP_ZPOOL_DEFAULT_ZBUD - bool "zbud" - select ZBUD - help - Use the zbud allocator as the default allocator. - -config ZSWAP_ZPOOL_DEFAULT_Z3FOLD - bool "z3fold" - select Z3FOLD - help - Use the z3fold allocator as the default allocator. - -config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC - bool "zsmalloc" - select ZSMALLOC - help - Use the zsmalloc allocator as the default allocator. -endchoice - -config ZSWAP_ZPOOL_DEFAULT - string - depends on ZSWAP - default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD - default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD - default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC - default "" - -config ZSWAP_DEFAULT_ON - bool "Enable the compressed cache for swap pages by default" - depends on ZSWAP - help - If selected, the compressed cache for swap pages will be enabled - at boot, otherwise it will be disabled. - - The selection made here can be overridden by using the kernel - command line 'zswap.enabled=' option. - -config ZPOOL - tristate "Common API for compressed memory storage" - help - Compressed memory storage API. This allows using either zbud or - zsmalloc. - -config ZBUD - tristate "Low (Up to 2x) density storage for compressed pages" - 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 Z3FOLD - tristate "Up to 3x density storage for compressed pages" - depends on ZPOOL - help - A special purpose allocator for storing compressed pages. - It is designed to store up to three compressed pages per physical - page. It is a ZBUD derivative so the simplicity and determinism are - still there. - -config ZSMALLOC - tristate "Memory allocator for compressed pages" - depends on MMU - 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 ZSMALLOC_STAT - bool "Export zsmalloc statistics" - depends on ZSMALLOC - select DEBUG_FS - help - This option enables code in the zsmalloc to collect various - statistics about whats happening in zsmalloc and exports that - information to userspace via debugfs. - If unsure, say N. - -config GENERIC_EARLY_IOREMAP - bool - -config MAX_STACK_SIZE_MB - int "Maximum user stack size for 32-bit processes (MB)" - default 80 - 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 - 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. - -config DEFERRED_STRUCT_PAGE_INIT - bool "Defer initialisation of struct pages to kthreads" - depends on SPARSEMEM - depends on !NEED_PER_CPU_KM - depends on 64BIT - select PADATA - help - Ordinarily all struct pages are initialised during early boot in a - single thread. On very large machines this can take a considerable - amount of time. If this option is set, large machines will bring up - a subset of memmap at boot and then initialise the rest in parallel. - This has a potential performance impact on tasks running early in the - lifetime of the system until these kthreads finish the - initialisation. - -config IDLE_PAGE_TRACKING - bool "Enable idle page tracking" - depends on SYSFS && MMU - select PAGE_EXTENSION if !64BIT - help - This feature allows to estimate the amount of user pages that have - not been touched during a given period of time. This information can - be useful to tune memory cgroup limits and/or for job placement - within a compute cluster. - - See Documentation/admin-guide/mm/idle_page_tracking.rst for - more details. - -config ARCH_HAS_PTE_DEVMAP - bool - -config ZONE_DEVICE - bool "Device memory (pmem, HMM, etc...) hotplug support" - depends on MEMORY_HOTPLUG - depends on MEMORY_HOTREMOVE - depends on SPARSEMEM_VMEMMAP - depends on ARCH_HAS_PTE_DEVMAP - select XARRAY_MULTI - - help - Device memory hotplug support allows for establishing pmem, - or other device driver discovered memory regions, in the - memmap. This allows pfn_to_page() lookups of otherwise - "device-physical" addresses which is needed for using a DAX - mapping in an O_DIRECT operation, among other things. - - If FS_DAX is enabled, then say Y. - -config DEV_PAGEMAP_OPS - bool - -# -# Helpers to mirror range of the CPU page tables of a process into device page -# tables. -# -config HMM_MIRROR - bool - depends on MMU - -config DEVICE_PRIVATE - bool "Unaddressable device memory (GPU memory, ...)" - depends on ZONE_DEVICE - select DEV_PAGEMAP_OPS - - help - Allows creation of struct pages to represent unaddressable device - memory; i.e., memory that is only accessible from the device (or - group of devices). You likely also want to select HMM_MIRROR. - -config VMAP_PFN - bool - -config FRAME_VECTOR - bool - -config ARCH_USES_HIGH_VMA_FLAGS - bool -config ARCH_HAS_PKEYS - bool - -config PERCPU_STATS - bool "Collect percpu memory statistics" - help - This feature collects and exposes statistics via debugfs. The - information includes global and per chunk statistics, which can - be used to help understand percpu memory usage. - -config GUP_BENCHMARK - bool "Enable infrastructure for get_user_pages() and related calls benchmarking" - help - Provides /sys/kernel/debug/gup_benchmark that helps with testing - performance of get_user_pages() and related calls. - - See tools/testing/selftests/vm/gup_benchmark.c - -config GUP_GET_PTE_LOW_HIGH - bool - -config READ_ONLY_THP_FOR_FS - bool "Read-only THP for filesystems (EXPERIMENTAL)" - depends on TRANSPARENT_HUGEPAGE && SHMEM - - help - Allow khugepaged to put read-only file-backed pages in THP. - - This is marked experimental because it is a new feature. Write - support of file THPs will be developed in the next few release - cycles. - -config ARCH_HAS_PTE_SPECIAL - bool - -# -# Some architectures require a special hugepage directory format that is -# required to support multiple hugepage sizes. For example a4fe3ce76 -# "powerpc/mm: Allow more flexible layouts for hugepage pagetables" -# introduced it on powerpc. This allows for a more flexible hugepage -# pagetable layouts. -# -config ARCH_HAS_HUGEPD - bool - -config MAPPING_DIRTY_HELPERS - bool - -config ANON_VMA_NAME - bool "Anonymous VMA name support" - depends on PROC_FS && ADVISE_SYSCALLS && MMU - - help - Allow naming anonymous virtual memory areas. - - This feature allows assigning names to virtual memory areas. Assigned - names can be later retrieved from /proc/pid/maps and /proc/pid/smaps - and help identifying individual anonymous memory areas. - Assigning a name to anonymous virtual memory area might prevent that - area from being merged with adjacent virtual memory areas due to the - difference in their name. -# -# For lmkd to trigger in-kernel lowmem info -# -config LOWMEM - bool "Low Memory Killer" - default n - help - Enables lowmem killer parameter tuning - -config LMKD_DBG - bool "Low Memory Killer Debug" - default n - help - print processes info when lmk happen per several seconds -# -# Show the process ashmem for debug -# -config MEMTRACE_ASHMEM - bool "Ashmem Process Info Show" - depends on ASHMEM - default n - help - Enable the Ashmem Process Info Show - -# -# Use rss_threshold to monitoring RSS -# -config RSS_THRESHOLD - bool "Enable /proc//rss and /proc//rss_threshold to monitoring RSS" - default n - depends on PROC_FS && MEMCG - help - Set a threshold to monitoring RSS in per pid - -config MEM_PURGEABLE - bool "Purgeable memory feature" - default n - depends on 64BIT - select ARCH_USES_HIGH_VMA_FLAGS - help - Support purgeable pages for process - -config MEM_PURGEABLE_DEBUG - bool "Purgeable memory debug" - default n - depends on MEM_PURGEABLE - help - Debug info for purgeable memory - -endmenu -- Gitee From f2bfc996165666966657c52b82e324616995dbbe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E4=BB=BB=E6=B3=BD=E5=8D=8E?= Date: Mon, 8 May 2023 07:50:23 +0000 Subject: [PATCH 3/3] =?UTF-8?q?=E5=88=A0=E9=99=A4=E6=96=87=E4=BB=B6=20mm/v?= =?UTF-8?q?mscan.c?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- mm/vmscan.c | 4432 --------------------------------------------------- 1 file changed, 4432 deletions(-) delete mode 100644 mm/vmscan.c diff --git a/mm/vmscan.c b/mm/vmscan.c deleted file mode 100644 index eed31ad36f5c..000000000000 --- a/mm/vmscan.c +++ /dev/null @@ -1,4432 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * linux/mm/vmscan.c - * - * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds - * - * Swap reorganised 29.12.95, Stephen Tweedie. - * kswapd added: 7.1.96 sct - * Removed kswapd_ctl limits, and swap out as many pages as needed - * to bring the system back to freepages.high: 2.4.97, Rik van Riel. - * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). - * Multiqueue VM started 5.8.00, Rik van Riel. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include /* for try_to_release_page(), - buffer_heads_over_limit */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#include -#include - -#include "internal.h" - -#define CREATE_TRACE_POINTS -#include - -#ifdef CONFIG_HYPERHOLD_FILE_LRU -#include -#endif - -#ifdef CONFIG_RECLAIM_ACCT -#include -#endif - -#ifdef ARCH_HAS_PREFETCHW -#define prefetchw_prev_lru_page(_page, _base, _field) \ - do { \ - if ((_page)->lru.prev != _base) { \ - struct page *prev; \ - \ - prev = lru_to_page(&(_page->lru)); \ - prefetchw(&prev->_field); \ - } \ - } while (0) -#else -#define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0) -#endif - -#ifdef CONFIG_HYPERHOLD_FILE_LRU -unsigned int enough_inactive_file = 1; -#endif - -/* - * From 0 .. 200. Higher means more swappy. - */ -int vm_swappiness = 60; - -static void set_task_reclaim_state(struct task_struct *task, - struct reclaim_state *rs) -{ - /* Check for an overwrite */ - WARN_ON_ONCE(rs && task->reclaim_state); - - /* Check for the nulling of an already-nulled member */ - WARN_ON_ONCE(!rs && !task->reclaim_state); - - task->reclaim_state = rs; -} - -static LIST_HEAD(shrinker_list); -static DECLARE_RWSEM(shrinker_rwsem); - -#ifdef CONFIG_MEMCG - -static DEFINE_IDR(shrinker_idr); -static int shrinker_nr_max; - -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - int id, ret = -ENOMEM; - - down_write(&shrinker_rwsem); - /* This may call shrinker, so it must use down_read_trylock() */ - id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); - if (id < 0) - goto unlock; - - if (id >= shrinker_nr_max) { - if (memcg_expand_shrinker_maps(id)) { - idr_remove(&shrinker_idr, id); - goto unlock; - } - - shrinker_nr_max = id + 1; - } - shrinker->id = id; - ret = 0; -unlock: - up_write(&shrinker_rwsem); - return ret; -} - -static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ - int id = shrinker->id; - - BUG_ON(id < 0); - - lockdep_assert_held(&shrinker_rwsem); - - idr_remove(&shrinker_idr, id); -} - -bool cgroup_reclaim(struct scan_control *sc) -{ - return sc->target_mem_cgroup; -} - -/** - * writeback_throttling_sane - is the usual dirty throttling mechanism available? - * @sc: scan_control in question - * - * The normal page dirty throttling mechanism in balance_dirty_pages() is - * completely broken with the legacy memcg and direct stalling in - * shrink_page_list() is used for throttling instead, which lacks all the - * niceties such as fairness, adaptive pausing, bandwidth proportional - * allocation and configurability. - * - * This function tests whether the vmscan currently in progress can assume - * that the normal dirty throttling mechanism is operational. - */ -bool writeback_throttling_sane(struct scan_control *sc) -{ - if (!cgroup_reclaim(sc)) - return true; -#ifdef CONFIG_CGROUP_WRITEBACK - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return true; -#endif - return false; -} -#else -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - return 0; -} - -static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ -} - -bool cgroup_reclaim(struct scan_control *sc) -{ - return false; -} - -bool writeback_throttling_sane(struct scan_control *sc) -{ - return true; -} -#endif - -/* - * This misses isolated pages which are not accounted for to save counters. - * As the data only determines if reclaim or compaction continues, it is - * not expected that isolated pages will be a dominating factor. - */ -unsigned long zone_reclaimable_pages(struct zone *zone) -{ - unsigned long nr; - - nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + - zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); - if (get_nr_swap_pages() > 0) - nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + - zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); - - return nr; -} - -/** - * lruvec_lru_size - Returns the number of pages on the given LRU list. - * @lruvec: lru vector - * @lru: lru to use - * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list) - */ -unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) -{ - unsigned long size = 0; - int zid; - -#ifdef CONFIG_HYPERHOLD_FILE_LRU - if (!mem_cgroup_disabled() && is_node_lruvec(lruvec)) { - for (zid = 0; zid <= zone_idx && zid < MAX_NR_ZONES; zid++) { - struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; - - if (!managed_zone(zone)) - continue; - - size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); - } - - return size; - } -#endif - for (zid = 0; zid <= zone_idx && zid < MAX_NR_ZONES; zid++) { - struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; - - if (!managed_zone(zone)) - continue; - - if (!mem_cgroup_disabled()) - size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); - else - size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); - } - return size; -} - -/* - * Add a shrinker callback to be called from the vm. - */ -int prealloc_shrinker(struct shrinker *shrinker) -{ - unsigned int size = sizeof(*shrinker->nr_deferred); - - if (shrinker->flags & SHRINKER_NUMA_AWARE) - size *= nr_node_ids; - - shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); - if (!shrinker->nr_deferred) - return -ENOMEM; - - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - if (prealloc_memcg_shrinker(shrinker)) - goto free_deferred; - } - - return 0; - -free_deferred: - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; - return -ENOMEM; -} - -void free_prealloced_shrinker(struct shrinker *shrinker) -{ - if (!shrinker->nr_deferred) - return; - - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - down_write(&shrinker_rwsem); - unregister_memcg_shrinker(shrinker); - up_write(&shrinker_rwsem); - } - - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; -} - -void register_shrinker_prepared(struct shrinker *shrinker) -{ - down_write(&shrinker_rwsem); - list_add_tail(&shrinker->list, &shrinker_list); - shrinker->flags |= SHRINKER_REGISTERED; - up_write(&shrinker_rwsem); -} - -int register_shrinker(struct shrinker *shrinker) -{ - int err = prealloc_shrinker(shrinker); - - if (err) - return err; - register_shrinker_prepared(shrinker); - return 0; -} -EXPORT_SYMBOL(register_shrinker); - -/* - * Remove one - */ -void unregister_shrinker(struct shrinker *shrinker) -{ - if (!(shrinker->flags & SHRINKER_REGISTERED)) - return; - - down_write(&shrinker_rwsem); - list_del(&shrinker->list); - shrinker->flags &= ~SHRINKER_REGISTERED; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - unregister_memcg_shrinker(shrinker); - up_write(&shrinker_rwsem); - - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; -} -EXPORT_SYMBOL(unregister_shrinker); - -#define SHRINK_BATCH 128 - -static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, - struct shrinker *shrinker, int priority) -{ - 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; - long scanned = 0, next_deferred; - - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - - freeable = shrinker->count_objects(shrinker, shrinkctl); - if (freeable == 0 || freeable == SHRINK_EMPTY) - return freeable; - - /* - * 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; - if (shrinker->seeks) { - delta = freeable >> priority; - delta *= 4; - do_div(delta, shrinker->seeks); - } else { - /* - * These objects don't require any IO to create. Trim - * them aggressively under memory pressure to keep - * them from causing refetches in the IO caches. - */ - delta = freeable / 2; - } - - total_scan += delta; - if (total_scan < 0) { - pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n", - shrinker->scan_objects, total_scan); - total_scan = freeable; - next_deferred = nr; - } else - next_deferred = total_scan; - - /* - * 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, - freeable, delta, total_scan, priority); - - /* - * 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; - shrinkctl->nr_scanned = nr_to_scan; - ret = shrinker->scan_objects(shrinker, shrinkctl); - if (ret == SHRINK_STOP) - break; - freed += ret; - - count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); - total_scan -= shrinkctl->nr_scanned; - scanned += shrinkctl->nr_scanned; - - cond_resched(); - } - - if (next_deferred >= scanned) - next_deferred -= scanned; - else - next_deferred = 0; - /* - * 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 (next_deferred > 0) - new_nr = atomic_long_add_return(next_deferred, - &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; -} - -#ifdef CONFIG_MEMCG -static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) -{ - struct memcg_shrinker_map *map; - unsigned long ret, freed = 0; - int i; - - if (!mem_cgroup_online(memcg)) - return 0; - - if (!down_read_trylock(&shrinker_rwsem)) - return 0; - - map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, - true); - if (unlikely(!map)) - goto unlock; - - for_each_set_bit(i, map->map, shrinker_nr_max) { - struct shrink_control sc = { - .gfp_mask = gfp_mask, - .nid = nid, - .memcg = memcg, - }; - struct shrinker *shrinker; - - shrinker = idr_find(&shrinker_idr, i); - if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { - if (!shrinker) - clear_bit(i, map->map); - continue; - } - - /* Call non-slab shrinkers even though kmem is disabled */ - if (!memcg_kmem_enabled() && - !(shrinker->flags & SHRINKER_NONSLAB)) - continue; - - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) { - clear_bit(i, map->map); - /* - * After the shrinker reported that it had no objects to - * free, but before we cleared the corresponding bit in - * the memcg shrinker map, a new object might have been - * added. To make sure, we have the bit set in this - * case, we invoke the shrinker one more time and reset - * the bit if it reports that it is not empty anymore. - * The memory barrier here pairs with the barrier in - * memcg_set_shrinker_bit(): - * - * list_lru_add() shrink_slab_memcg() - * list_add_tail() clear_bit() - * - * set_bit() do_shrink_slab() - */ - smp_mb__after_atomic(); - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; - else - memcg_set_shrinker_bit(memcg, nid, i); - } - freed += ret; - - if (rwsem_is_contended(&shrinker_rwsem)) { - freed = freed ? : 1; - break; - } - } -unlock: - up_read(&shrinker_rwsem); - return freed; -} -#else /* CONFIG_MEMCG */ -static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) -{ - return 0; -} -#endif /* CONFIG_MEMCG */ - -/** - * shrink_slab - shrink slab caches - * @gfp_mask: allocation context - * @nid: node whose slab caches to target - * @memcg: memory cgroup whose slab caches to target - * @priority: the reclaim priority - * - * Call the shrink functions to age shrinkable caches. - * - * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, - * unaware shrinkers will receive a node id of 0 instead. - * - * @memcg specifies the memory cgroup to target. Unaware shrinkers - * are called only if it is the root cgroup. - * - * @priority is sc->priority, we take the number of objects and >> by priority - * in order to get the scan target. - * - * Returns the number of reclaimed slab objects. - */ -unsigned long shrink_slab(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, - int priority) -{ - unsigned long ret, freed = 0; - struct shrinker *shrinker; - - /* - * The root memcg might be allocated even though memcg is disabled - * via "cgroup_disable=memory" boot parameter. This could make - * mem_cgroup_is_root() return false, then just run memcg slab - * shrink, but skip global shrink. This may result in premature - * oom. - */ - if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) - return shrink_slab_memcg(gfp_mask, nid, memcg, priority); - - if (!down_read_trylock(&shrinker_rwsem)) - goto out; - - list_for_each_entry(shrinker, &shrinker_list, list) { - struct shrink_control sc = { - .gfp_mask = gfp_mask, - .nid = nid, - .memcg = memcg, - }; - -#ifdef CONFIG_RECLAIM_ACCT - reclaimacct_substage_start(RA_SHRINKSLAB); -#endif - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; - freed += ret; -#ifdef CONFIG_RECLAIM_ACCT - reclaimacct_substage_end(RA_SHRINKSLAB, ret, shrinker); -#endif - /* - * Bail out if someone want to register a new shrinker to - * prevent the registration from being stalled for long periods - * by parallel ongoing shrinking. - */ - if (rwsem_is_contended(&shrinker_rwsem)) { - freed = freed ? : 1; - break; - } - } - - up_read(&shrinker_rwsem); -out: - cond_resched(); - return freed; -} - -void drop_slab_node(int nid) -{ - unsigned long freed; - int shift = 0; - - do { - struct mem_cgroup *memcg = NULL; - - if (fatal_signal_pending(current)) - return; - - freed = 0; - memcg = mem_cgroup_iter(NULL, NULL, NULL); - do { - freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); - } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); - } while ((freed >> shift++) > 1); -} - -void drop_slab(void) -{ - int nid; - - for_each_online_node(nid) - drop_slab_node(nid); -} - -static inline int is_page_cache_freeable(struct page *page) -{ - /* - * A freeable page cache page is referenced only by the caller - * that isolated the page, the page cache and optional buffer - * heads at page->private. - */ - int page_cache_pins = thp_nr_pages(page); - return page_count(page) - page_has_private(page) == 1 + page_cache_pins; -} - -static int may_write_to_inode(struct inode *inode) -{ - if (current->flags & PF_SWAPWRITE) - return 1; - if (!inode_write_congested(inode)) - return 1; - if (inode_to_bdi(inode) == current->backing_dev_info) - return 1; - return 0; -} - -/* - * We detected a synchronous write error writing a page out. Probably - * -ENOSPC. We need to propagate that into the address_space for a subsequent - * fsync(), msync() or close(). - * - * The tricky part is that after writepage we cannot touch the mapping: nothing - * prevents it from being freed up. But we have a ref on the page and once - * that page is locked, the mapping is pinned. - * - * We're allowed to run sleeping lock_page() here because we know the caller has - * __GFP_FS. - */ -static void handle_write_error(struct address_space *mapping, - struct page *page, int error) -{ - lock_page(page); - if (page_mapping(page) == mapping) - mapping_set_error(mapping, error); - unlock_page(page); -} - -/* possible outcome of pageout() */ -typedef enum { - /* failed to write page out, page is locked */ - PAGE_KEEP, - /* move page to the active list, page is locked */ - PAGE_ACTIVATE, - /* page has been sent to the disk successfully, page is unlocked */ - PAGE_SUCCESS, - /* page is clean and locked */ - PAGE_CLEAN, -} pageout_t; - -/* - * pageout is called by shrink_page_list() for each dirty page. - * Calls ->writepage(). - */ -static pageout_t pageout(struct page *page, struct address_space *mapping) -{ - /* - * If the page is dirty, only perform writeback if that write - * will be non-blocking. To prevent this allocation from being - * stalled by pagecache activity. But note that there may be - * stalls if we need to run get_block(). We could test - * PagePrivate for that. - * - * If this process is currently in __generic_file_write_iter() against - * this page's queue, we can perform writeback even if that - * will block. - * - * If the page is swapcache, write it back even if that would - * block, for some throttling. This happens by accident, because - * swap_backing_dev_info is bust: it doesn't reflect the - * congestion state of the swapdevs. Easy to fix, if needed. - */ - if (!is_page_cache_freeable(page)) - return PAGE_KEEP; - if (!mapping) { - /* - * Some data journaling orphaned pages can have - * page->mapping == NULL while being dirty with clean buffers. - */ - if (page_has_private(page)) { - if (try_to_free_buffers(page)) { - ClearPageDirty(page); - pr_info("%s: orphaned page\n", __func__); - return PAGE_CLEAN; - } - } - return PAGE_KEEP; - } - if (mapping->a_ops->writepage == NULL) - return PAGE_ACTIVATE; - if (!may_write_to_inode(mapping->host)) - return PAGE_KEEP; - - if (clear_page_dirty_for_io(page)) { - int res; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - .nr_to_write = SWAP_CLUSTER_MAX, - .range_start = 0, - .range_end = LLONG_MAX, - .for_reclaim = 1, - }; - - SetPageReclaim(page); - res = mapping->a_ops->writepage(page, &wbc); - if (res < 0) - handle_write_error(mapping, page, res); - if (res == AOP_WRITEPAGE_ACTIVATE) { - ClearPageReclaim(page); - return PAGE_ACTIVATE; - } - - if (!PageWriteback(page)) { - /* synchronous write or broken a_ops? */ - ClearPageReclaim(page); - } - trace_mm_vmscan_writepage(page); - inc_node_page_state(page, NR_VMSCAN_WRITE); - return PAGE_SUCCESS; - } - - return PAGE_CLEAN; -} - -/* - * 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, - bool reclaimed, struct mem_cgroup *target_memcg) -{ - unsigned long flags; - int refcount; - void *shadow = NULL; - - BUG_ON(!PageLocked(page)); - BUG_ON(mapping != page_mapping(page)); - - xa_lock_irqsave(&mapping->i_pages, flags); - /* - * The non racy check for a busy page. - * - * Must be careful with the order of the tests. When someone has - * a ref to the page, it may be possible that they dirty it then - * drop the reference. So if PageDirty is tested before page_count - * here, then the following race may occur: - * - * get_user_pages(&page); - * [user mapping goes away] - * write_to(page); - * !PageDirty(page) [good] - * SetPageDirty(page); - * put_page(page); - * !page_count(page) [good, discard it] - * - * [oops, our write_to data is lost] - * - * Reversing the order of the tests ensures such a situation cannot - * escape unnoticed. The smp_rmb is needed to ensure the page->flags - * load is not satisfied before that of page->_refcount. - * - * Note that if SetPageDirty is always performed via set_page_dirty, - * and thus under the i_pages lock, then this ordering is not required. - */ - refcount = 1 + compound_nr(page); - if (!page_ref_freeze(page, refcount)) - goto cannot_free; - /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ - if (unlikely(PageDirty(page))) { - page_ref_unfreeze(page, refcount); - goto cannot_free; - } - - if (PageSwapCache(page)) { - swp_entry_t swap = { .val = page_private(page) }; - mem_cgroup_swapout(page, swap); - if (reclaimed && !mapping_exiting(mapping)) - shadow = workingset_eviction(page, target_memcg); - __delete_from_swap_cache(page, swap, shadow); - xa_unlock_irqrestore(&mapping->i_pages, flags); - put_swap_page(page, swap); - } else { - void (*freepage)(struct page *); - - freepage = mapping->a_ops->freepage; - /* - * 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 optimization, - * inode reclaim needs to empty out the radix tree or - * the nodes are lost. Don't plant shadows behind its - * back. - * - * We also don't store shadows for DAX mappings because the - * only page cache pages found in these are zero pages - * covering holes, and because we don't want to mix DAX - * exceptional entries and shadow exceptional entries in the - * same address_space. - */ - if (reclaimed && page_is_file_lru(page) && - !mapping_exiting(mapping) && !dax_mapping(mapping)) - shadow = workingset_eviction(page, target_memcg); - __delete_from_page_cache(page, shadow); - xa_unlock_irqrestore(&mapping->i_pages, flags); - - if (freepage != NULL) - freepage(page); - } - - return 1; - -cannot_free: - xa_unlock_irqrestore(&mapping->i_pages, flags); - return 0; -} - -/* - * Attempt to detach a locked page from its ->mapping. If it is dirty or if - * someone else has a ref on the page, abort and return 0. If it was - * successfully detached, return 1. Assumes the caller has a single ref on - * this page. - */ -int remove_mapping(struct address_space *mapping, struct page *page) -{ - if (__remove_mapping(mapping, page, false, NULL)) { - /* - * Unfreezing the refcount with 1 rather than 2 effectively - * drops the pagecache ref for us without requiring another - * atomic operation. - */ - page_ref_unfreeze(page, 1); - return 1; - } - return 0; -} - -/** - * putback_lru_page - put previously isolated page onto appropriate LRU list - * @page: page to be put back to appropriate lru list - * - * Add previously isolated @page to appropriate LRU list. - * Page may still be unevictable for other reasons. - * - * lru_lock must not be held, interrupts must be enabled. - */ -void putback_lru_page(struct page *page) -{ - lru_cache_add(page); - put_page(page); /* drop ref from isolate */ -} - -enum page_references { - PAGEREF_RECLAIM, - PAGEREF_RECLAIM_CLEAN, - PAGEREF_RECLAIM_PURGEABLE, - PAGEREF_KEEP, - PAGEREF_ACTIVATE, -}; - -static enum page_references page_check_references(struct page *page, - struct scan_control *sc) -{ - int referenced_ptes, referenced_page; - unsigned long vm_flags; - - referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup, - &vm_flags); - referenced_page = TestClearPageReferenced(page); - - /* - * Mlock lost the isolation race with us. Let try_to_unmap() - * move the page to the unevictable list. - */ - if (vm_flags & VM_LOCKED) - return PAGEREF_RECLAIM; - -#ifdef CONFIG_MEM_PURGEABLE - if (vm_flags & VM_PURGEABLE) - return PAGEREF_RECLAIM_PURGEABLE; -#endif - if (referenced_ptes) { - /* - * All mapped pages start out with page table - * references from the instantiating fault, so we need - * to look twice if a mapped file page is used more - * than once. - * - * Mark it and spare it for another trip around the - * inactive list. Another page table reference will - * lead to its activation. - * - * Note: the mark is set for activated pages as well - * so that recently deactivated but used pages are - * quickly recovered. - */ - SetPageReferenced(page); - - if (referenced_page || referenced_ptes > 1) - return PAGEREF_ACTIVATE; - - /* - * Activate file-backed executable pages after first usage. - */ - if ((vm_flags & VM_EXEC) && !PageSwapBacked(page)) - return PAGEREF_ACTIVATE; - - return PAGEREF_KEEP; - } - - /* Reclaim if clean, defer dirty pages to writeback */ - if (referenced_page && !PageSwapBacked(page)) - return PAGEREF_RECLAIM_CLEAN; - - 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_lru(page) || - (PageAnon(page) && !PageSwapBacked(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 - */ -unsigned int shrink_page_list(struct list_head *page_list, - struct pglist_data *pgdat, - struct scan_control *sc, - struct reclaim_stat *stat, - bool ignore_references) -{ - LIST_HEAD(ret_pages); - LIST_HEAD(free_pages); - unsigned int nr_reclaimed = 0; - unsigned int pgactivate = 0; - - memset(stat, 0, sizeof(*stat)); - cond_resched(); - - while (!list_empty(page_list)) { - struct address_space *mapping; - struct page *page; - enum page_references references = PAGEREF_RECLAIM; - bool dirty, writeback, may_enter_fs; - unsigned int nr_pages; - - cond_resched(); - - page = lru_to_page(page_list); - list_del(&page->lru); - - if (!trylock_page(page)) - goto keep; - - VM_BUG_ON_PAGE(PageActive(page), page); - - nr_pages = compound_nr(page); - - /* Account the number of base pages even though THP */ - sc->nr_scanned += nr_pages; - - if (unlikely(!page_evictable(page))) - goto activate_locked; - - if (!sc->may_unmap && page_mapped(page)) - goto keep_locked; - - may_enter_fs = (sc->gfp_mask & __GFP_FS) || - (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); - - /* - * The number of dirty pages determines if a node 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) - stat->nr_dirty++; - - if (dirty && !writeback) - stat->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 (((dirty || writeback) && mapping && - inode_write_congested(mapping->host)) || - (writeback && PageReclaim(page))) - stat->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 or new memcg reclaim encounters a page that is - * not marked for immediate reclaim, or the caller does not - * have __GFP_FS (or __GFP_IO if it's simply going to swap, - * not to fs). In this case mark the page for immediate - * reclaim and continue scanning. - * - * Require may_enter_fs because we would wait on fs, which - * may not have submitted IO yet. And the loop driver 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. - * - * 3) Legacy memcg encounters a page that is 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. - * - * In cases 1) and 2) we activate the pages to get them out of - * the way while we continue scanning for clean pages on the - * inactive list and refilling from the active list. The - * observation here is that waiting for disk writes is more - * expensive than potentially causing reloads down the line. - * Since they're marked for immediate reclaim, they won't put - * memory pressure on the cache working set any longer than it - * takes to write them to disk. - */ - if (PageWriteback(page)) { - /* Case 1 above */ - if (current_is_kswapd() && - PageReclaim(page) && - test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { - stat->nr_immediate++; - goto activate_locked; - - /* Case 2 above */ - } else if (writeback_throttling_sane(sc) || - !PageReclaim(page) || !may_enter_fs) { - /* - * This is slightly racy - end_page_writeback() - * might have just cleared PageReclaim, then - * setting PageReclaim here end up interpreted - * as PageReadahead - but that does not matter - * enough to care. What we do want is for this - * page to have PageReclaim set next time memcg - * reclaim reaches the tests above, so it will - * then wait_on_page_writeback() to avoid OOM; - * and it's also appropriate in global reclaim. - */ - SetPageReclaim(page); - stat->nr_writeback++; - goto activate_locked; - - /* Case 3 above */ - } else { - unlock_page(page); - wait_on_page_writeback(page); - /* then go back and try same page again */ - list_add_tail(&page->lru, page_list); - continue; - } - } - - if (!ignore_references) - references = page_check_references(page, sc); - - switch (references) { - case PAGEREF_ACTIVATE: - goto activate_locked; - case PAGEREF_KEEP: - stat->nr_ref_keep += nr_pages; - goto keep_locked; - case PAGEREF_RECLAIM: - case PAGEREF_RECLAIM_CLEAN: - case PAGEREF_RECLAIM_PURGEABLE: - ; /* try to reclaim the page below */ - } - - /* - * Anonymous process memory has backing store? - * Try to allocate it some swap space here. - * Lazyfree page could be freed directly - */ - if (PageAnon(page) && PageSwapBacked(page)) { - if (!PageSwapCache(page) && references != PAGEREF_RECLAIM_PURGEABLE) { - if (!(sc->gfp_mask & __GFP_IO)) - goto keep_locked; - if (page_maybe_dma_pinned(page)) - goto keep_locked; - if (PageTransHuge(page)) { - /* cannot split THP, skip it */ - if (!can_split_huge_page(page, NULL)) - goto activate_locked; - /* - * Split pages without a PMD map right - * away. Chances are some or all of the - * tail pages can be freed without IO. - */ - if (!compound_mapcount(page) && - split_huge_page_to_list(page, - page_list)) - goto activate_locked; - } - if (!add_to_swap(page)) { - if (!PageTransHuge(page)) - goto activate_locked_split; - /* Fallback to swap normal pages */ - if (split_huge_page_to_list(page, - page_list)) - goto activate_locked; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - count_vm_event(THP_SWPOUT_FALLBACK); -#endif - if (!add_to_swap(page)) - goto activate_locked_split; - } - - may_enter_fs = true; - - /* Adding to swap updated mapping */ - mapping = page_mapping(page); - } - } else if (unlikely(PageTransHuge(page))) { - /* Split file THP */ - if (split_huge_page_to_list(page, page_list)) - goto keep_locked; - } - - /* - * THP may get split above, need minus tail pages and update - * nr_pages to avoid accounting tail pages twice. - * - * The tail pages that are added into swap cache successfully - * reach here. - */ - if ((nr_pages > 1) && !PageTransHuge(page)) { - sc->nr_scanned -= (nr_pages - 1); - nr_pages = 1; - } - - /* - * The page is mapped into the page tables of one or more - * processes. Try to unmap it here. - */ - if (page_mapped(page)) { - enum ttu_flags flags = TTU_BATCH_FLUSH; - bool was_swapbacked = PageSwapBacked(page); - - if (unlikely(PageTransHuge(page))) - flags |= TTU_SPLIT_HUGE_PMD; - - if (!try_to_unmap(page, flags)) { - stat->nr_unmap_fail += nr_pages; - if (!was_swapbacked && PageSwapBacked(page)) - stat->nr_lazyfree_fail += nr_pages; - goto activate_locked; - } - } - - if (PageDirty(page) && references != PAGEREF_RECLAIM_PURGEABLE) { - /* - * Only kswapd can writeback filesystem pages - * to avoid risk of stack overflow. But avoid - * injecting inefficient single-page IO into - * flusher writeback as much as possible: only - * write pages when we've encountered many - * dirty pages, and when we've already scanned - * the rest of the LRU for clean pages and see - * the same dirty pages again (PageReclaim). - */ - if (page_is_file_lru(page) && - (!current_is_kswapd() || !PageReclaim(page) || - !test_bit(PGDAT_DIRTY, &pgdat->flags))) { - /* - * Immediately reclaim when written back. - * Similar in principal to deactivate_page() - * except we already have the page isolated - * and know it's dirty - */ - inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); - SetPageReclaim(page); - - goto activate_locked; - } - - if (references == PAGEREF_RECLAIM_CLEAN) - goto keep_locked; - if (!may_enter_fs) - goto keep_locked; - if (!sc->may_writepage) - goto keep_locked; - - /* - * Page is dirty. Flush the TLB if a writable entry - * potentially exists to avoid CPU writes after IO - * starts and then write it out here. - */ - try_to_unmap_flush_dirty(); - switch (pageout(page, mapping)) { - case PAGE_KEEP: - goto keep_locked; - case PAGE_ACTIVATE: - goto activate_locked; - case PAGE_SUCCESS: - stat->nr_pageout += thp_nr_pages(page); - - if (PageWriteback(page)) - goto keep; - if (PageDirty(page)) - goto keep; - - /* - * A synchronous write - probably a ramdisk. Go - * ahead and try to reclaim the page. - */ - if (!trylock_page(page)) - goto keep; - if (PageDirty(page) || PageWriteback(page)) - goto keep_locked; - mapping = page_mapping(page); - case PAGE_CLEAN: - ; /* try to free the page below */ - } - } - - /* - * If the page has buffers, try to free the buffer mappings - * associated with this page. If we succeed we try to free - * the page as well. - * - * We do this even if the page is PageDirty(). - * try_to_release_page() does not perform I/O, but it is - * possible for a page to have PageDirty set, but it is actually - * clean (all its buffers are clean). This happens if the - * buffers were written out directly, with submit_bh(). ext3 - * will do this, as well as the blockdev mapping. - * try_to_release_page() will discover that cleanness and will - * drop the buffers and mark the page clean - it can be freed. - * - * Rarely, pages can have buffers and no ->mapping. These are - * the pages which were not successfully invalidated in - * truncate_complete_page(). We try to drop those buffers here - * and if that worked, and the page is no longer mapped into - * process address space (page_count == 1) it can be freed. - * Otherwise, leave the page on the LRU so it is swappable. - */ - if (page_has_private(page)) { - if (!try_to_release_page(page, sc->gfp_mask)) - goto activate_locked; - if (!mapping && page_count(page) == 1) { - unlock_page(page); - if (put_page_testzero(page)) - goto free_it; - else { - /* - * rare race with speculative reference. - * the speculative reference will free - * this page shortly, so we may - * increment nr_reclaimed here (and - * leave it off the LRU). - */ - nr_reclaimed++; - continue; - } - } - } - - if (PageAnon(page) && - (!PageSwapBacked(page) || - references == PAGEREF_RECLAIM_PURGEABLE)) { - /* follow __remove_mapping for reference */ - if (!page_ref_freeze(page, 1)) - goto keep_locked; - if (PageDirty(page) && references != PAGEREF_RECLAIM_PURGEABLE) { - page_ref_unfreeze(page, 1); - goto keep_locked; - } - - count_vm_event(PGLAZYFREED); - count_memcg_page_event(page, PGLAZYFREED); - } else if (!mapping || !__remove_mapping(mapping, page, true, - sc->target_mem_cgroup)) - goto keep_locked; - - unlock_page(page); -free_it: - /* - * THP may get swapped out in a whole, need account - * all base pages. - */ - nr_reclaimed += nr_pages; - - /* - * Is there need to periodically free_page_list? It would - * appear not as the counts should be low - */ - if (unlikely(PageTransHuge(page))) - destroy_compound_page(page); - else - list_add(&page->lru, &free_pages); - continue; - -activate_locked_split: - /* - * The tail pages that are failed to add into swap cache - * reach here. Fixup nr_scanned and nr_pages. - */ - if (nr_pages > 1) { - sc->nr_scanned -= (nr_pages - 1); - nr_pages = 1; - } -activate_locked: - /* Not a candidate for swapping, so reclaim swap space. */ - if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || - PageMlocked(page))) - try_to_free_swap(page); - VM_BUG_ON_PAGE(PageActive(page), page); - if (!PageMlocked(page)) { - int type = page_is_file_lru(page); - SetPageActive(page); - stat->nr_activate[type] += nr_pages; - count_memcg_page_event(page, PGACTIVATE); - } -keep_locked: - unlock_page(page); -keep: - list_add(&page->lru, &ret_pages); - VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); - } - - pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; - - mem_cgroup_uncharge_list(&free_pages); - try_to_unmap_flush(); - free_unref_page_list(&free_pages); - - list_splice(&ret_pages, page_list); - count_vm_events(PGACTIVATE, pgactivate); - - return nr_reclaimed; -} - -unsigned int reclaim_clean_pages_from_list(struct zone *zone, - struct list_head *page_list) -{ - struct scan_control sc = { - .gfp_mask = GFP_KERNEL, - .priority = DEF_PRIORITY, - .may_unmap = 1, - }; - struct reclaim_stat stat; - unsigned int nr_reclaimed; - struct page *page, *next; - LIST_HEAD(clean_pages); - - list_for_each_entry_safe(page, next, page_list, lru) { - if (page_is_file_lru(page) && !PageDirty(page) && - !__PageMovable(page) && !PageUnevictable(page)) { - ClearPageActive(page); - list_move(&page->lru, &clean_pages); - } - } - - nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, - &stat, true); - list_splice(&clean_pages, page_list); - mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, - -(long)nr_reclaimed); - /* - * Since lazyfree pages are isolated from file LRU from the beginning, - * they will rotate back to anonymous LRU in the end if it failed to - * discard so isolated count will be mismatched. - * Compensate the isolated count for both LRU lists. - */ - mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, - stat.nr_lazyfree_fail); - mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, - -(long)stat.nr_lazyfree_fail); - return nr_reclaimed; -} - -/* - * Attempt to remove the specified page from its LRU. Only take this page - * if it is of the appropriate PageActive status. Pages which are being - * freed elsewhere are also ignored. - * - * page: page to consider - * mode: one of the LRU isolation modes defined above - * - * returns 0 on success, -ve errno on failure. - */ -int __isolate_lru_page(struct page *page, isolate_mode_t mode) -{ - int ret = -EINVAL; - - /* Only take pages on the LRU. */ - if (!PageLRU(page)) - return ret; - - /* Compaction should not handle unevictable pages but CMA can do so */ - if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE)) - return ret; - - ret = -EBUSY; - - /* - * To minimise LRU disruption, the caller can indicate that it only - * wants to isolate pages it will be able to operate on without - * blocking - clean pages for the most part. - * - * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages - * that it is possible to migrate without blocking - */ - if (mode & ISOLATE_ASYNC_MIGRATE) { - /* All the caller can do on PageWriteback is block */ - if (PageWriteback(page)) - return ret; - - if (PageDirty(page)) { - struct address_space *mapping; - bool migrate_dirty; - - /* - * Only pages without mappings or that have a - * ->migratepage callback are possible to migrate - * without blocking. However, we can be racing with - * truncation so it's necessary to lock the page - * to stabilise the mapping as truncation holds - * the page lock until after the page is removed - * from the page cache. - */ - if (!trylock_page(page)) - return ret; - - mapping = page_mapping(page); - migrate_dirty = !mapping || mapping->a_ops->migratepage; - unlock_page(page); - if (!migrate_dirty) - return ret; - } - } - - if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) - return ret; - - if (likely(get_page_unless_zero(page))) { - /* - * Be careful not to clear PageLRU until after we're - * sure the page is not being freed elsewhere -- the - * page release code relies on it. - */ - ClearPageLRU(page); - ret = 0; - } - - return ret; -} - - -/* - * Update LRU sizes after isolating pages. The LRU size updates must - * be complete before mem_cgroup_update_lru_size due to a sanity check. - */ -static __always_inline void update_lru_sizes(struct lruvec *lruvec, - enum lru_list lru, unsigned long *nr_zone_taken) -{ - int zid; - - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - if (!nr_zone_taken[zid]) - continue; - - update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); - } - -} - -/** - * pgdat->lru_lock is heavily contended. Some of the functions that - * shrink the lists perform better by taking out a batch of pages - * and working on them outside the LRU lock. - * - * For pagecache intensive workloads, this function is the hottest - * spot in the kernel (apart from copy_*_user functions). - * - * Appropriate locks must be held before calling this function. - * - * @nr_to_scan: The number of eligible pages to look through on the list. - * @lruvec: The LRU vector to pull pages from. - * @dst: The temp list to put pages on to. - * @nr_scanned: The number of pages that were scanned. - * @sc: The scan_control struct for this reclaim session - * @lru: LRU list id for isolating - * - * returns how many pages were moved onto *@dst. - */ -unsigned long isolate_lru_pages(unsigned long nr_to_scan, - struct lruvec *lruvec, struct list_head *dst, - unsigned long *nr_scanned, struct scan_control *sc, - enum lru_list lru) -{ - struct list_head *src = &lruvec->lists[lru]; - unsigned long nr_taken = 0; - unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; - unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; - unsigned long skipped = 0; - unsigned long scan, total_scan, nr_pages; - LIST_HEAD(pages_skipped); - isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED); - - total_scan = 0; - scan = 0; - while (scan < nr_to_scan && !list_empty(src)) { - struct page *page; - - page = lru_to_page(src); - prefetchw_prev_lru_page(page, src, flags); - - VM_BUG_ON_PAGE(!PageLRU(page), page); - - nr_pages = compound_nr(page); - total_scan += nr_pages; - - if (page_zonenum(page) > sc->reclaim_idx) { - list_move(&page->lru, &pages_skipped); - nr_skipped[page_zonenum(page)] += nr_pages; - continue; - } - - /* - * Do not count skipped pages because that makes the function - * return with no isolated pages if the LRU mostly contains - * ineligible pages. This causes the VM to not reclaim any - * pages, triggering a premature OOM. - * - * Account all tail pages of THP. This would not cause - * premature OOM since __isolate_lru_page() returns -EBUSY - * only when the page is being freed somewhere else. - */ - scan += nr_pages; - switch (__isolate_lru_page(page, mode)) { - case 0: - nr_taken += nr_pages; - nr_zone_taken[page_zonenum(page)] += nr_pages; - list_move(&page->lru, dst); - break; - - case -EBUSY: - /* else it is being freed elsewhere */ - list_move(&page->lru, src); - continue; - - default: - BUG(); - } - } - - /* - * Splice any skipped pages to the start of the LRU list. Note that - * this disrupts the LRU order when reclaiming for lower zones but - * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX - * scanning would soon rescan the same pages to skip and put the - * system at risk of premature OOM. - */ - if (!list_empty(&pages_skipped)) { - int zid; - - list_splice(&pages_skipped, src); - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - if (!nr_skipped[zid]) - continue; - - __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); - skipped += nr_skipped[zid]; - } - } - *nr_scanned = total_scan; - trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, - total_scan, skipped, nr_taken, mode, lru); - update_lru_sizes(lruvec, lru, nr_zone_taken); - return nr_taken; -} - -/** - * isolate_lru_page - tries to isolate a page from its LRU list - * @page: page to isolate from its LRU list - * - * Isolates a @page from an LRU list, clears PageLRU and adjusts the - * vmstat statistic corresponding to whatever LRU list the page was on. - * - * Returns 0 if the page was removed from an LRU list. - * Returns -EBUSY if the page was not on an LRU list. - * - * The returned page will have PageLRU() cleared. If it was found on - * the active list, it will have PageActive set. If it was found on - * the unevictable list, it will have the PageUnevictable bit set. That flag - * may need to be cleared by the caller before letting the page go. - * - * The vmstat statistic corresponding to the list on which the page was - * found will be decremented. - * - * Restrictions: - * - * (1) Must be called with an elevated refcount on the page. This is a - * fundamental difference from isolate_lru_pages (which is called - * without a stable reference). - * (2) the lru_lock must not be held. - * (3) interrupts must be enabled. - */ -int isolate_lru_page(struct page *page) -{ - int ret = -EBUSY; - - VM_BUG_ON_PAGE(!page_count(page), page); - WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); - - if (PageLRU(page)) { - pg_data_t *pgdat = page_pgdat(page); - struct lruvec *lruvec; - - spin_lock_irq(&pgdat->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, pgdat); - if (PageLRU(page)) { - int lru = page_lru(page); - get_page(page); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, lru); - ret = 0; - } - spin_unlock_irq(&pgdat->lru_lock); - } - return ret; -} - -/* - * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and - * then get rescheduled. When there are massive number of tasks doing page - * allocation, such sleeping direct reclaimers may keep piling up on each CPU, - * the LRU list will go small and be scanned faster than necessary, leading to - * unnecessary swapping, thrashing and OOM. - */ -static int too_many_isolated(struct pglist_data *pgdat, int file, - struct scan_control *sc) -{ - unsigned long inactive, isolated; - - if (current_is_kswapd()) - return 0; - - if (!writeback_throttling_sane(sc)) - return 0; - - if (file) { - inactive = node_page_state(pgdat, NR_INACTIVE_FILE); - isolated = node_page_state(pgdat, NR_ISOLATED_FILE); - } else { - inactive = node_page_state(pgdat, NR_INACTIVE_ANON); - isolated = node_page_state(pgdat, NR_ISOLATED_ANON); - } - - /* - * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they - * won't get blocked by normal direct-reclaimers, forming a circular - * deadlock. - */ - if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) - inactive >>= 3; - - return isolated > inactive; -} - -/* - * This moves pages from @list to corresponding LRU list. - * - * We move them the other way if the page is referenced by one or more - * processes, from rmap. - * - * If the pages are mostly unmapped, the processing is fast and it is - * appropriate to hold zone_lru_lock across the whole operation. But if - * the pages are mapped, the processing is slow (page_referenced()) so we - * should drop zone_lru_lock around each page. It's impossible to balance - * this, so instead we remove the pages from the LRU while processing them. - * It is safe to rely on PG_active against the non-LRU pages in here because - * nobody will play with that bit on a non-LRU page. - * - * The downside is that we have to touch page->_refcount against each page. - * But we had to alter page->flags anyway. - * - * Returns the number of pages moved to the given lruvec. - */ - -unsigned move_pages_to_lru(struct lruvec *lruvec, struct list_head *list) -{ - struct pglist_data *pgdat = lruvec_pgdat(lruvec); - int nr_pages, nr_moved = 0; - LIST_HEAD(pages_to_free); - struct page *page; - enum lru_list lru; -#ifdef CONFIG_HYPERHOLD_FILE_LRU - bool prot; - bool file; -#endif - - while (!list_empty(list)) { - page = lru_to_page(list); - VM_BUG_ON_PAGE(PageLRU(page), page); - if (unlikely(!page_evictable(page))) { - list_del(&page->lru); - spin_unlock_irq(&pgdat->lru_lock); - putback_lru_page(page); - spin_lock_irq(&pgdat->lru_lock); - continue; - } - lruvec = mem_cgroup_page_lruvec(page, pgdat); - - SetPageLRU(page); - lru = page_lru(page); - - nr_pages = thp_nr_pages(page); - update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); - list_move(&page->lru, &lruvec->lists[lru]); - - if (put_page_testzero(page)) { - __ClearPageLRU(page); - __ClearPageActive(page); - del_page_from_lru_list(page, lruvec, lru); - - if (unlikely(PageCompound(page))) { - spin_unlock_irq(&pgdat->lru_lock); - destroy_compound_page(page); - spin_lock_irq(&pgdat->lru_lock); - } else - list_add(&page->lru, &pages_to_free); - } else { - nr_moved += nr_pages; -#ifdef CONFIG_HYPERHOLD_FILE_LRU - if (PageActive(page)) { - prot = is_prot_page(page); - file = page_is_file_lru(page); - if (!prot && file) { - lruvec = node_lruvec(pgdat); - workingset_age_nonresident(lruvec, - nr_pages); - } else { - workingset_age_nonresident(lruvec, - nr_pages); - } - } -#else - if (PageActive(page)) - workingset_age_nonresident(lruvec, nr_pages); -#endif - } - } - - /* - * To save our caller's stack, now use input list for pages to free. - */ - list_splice(&pages_to_free, list); - - return nr_moved; -} - -/* - * If a kernel thread (such as nfsd for loop-back mounts) services - * a backing device by writing to the page cache it sets PF_LOCAL_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. - */ -int current_may_throttle(void) -{ - return !(current->flags & PF_LOCAL_THROTTLE) || - current->backing_dev_info == NULL || - bdi_write_congested(current->backing_dev_info); -} - -/* - * shrink_inactive_list() is a helper for shrink_node(). It returns the number - * of reclaimed pages - */ -unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, - struct scan_control *sc, enum lru_list lru) -{ - LIST_HEAD(page_list); - unsigned long nr_scanned; - unsigned int nr_reclaimed = 0; - unsigned long nr_taken; - struct reclaim_stat stat; - bool file = is_file_lru(lru); - enum vm_event_item item; - struct pglist_data *pgdat = lruvec_pgdat(lruvec); - bool stalled = false; - - while (unlikely(too_many_isolated(pgdat, file, sc))) { - if (stalled) - return 0; - -#ifdef CONFIG_HYPERHOLD_FILE_LRU - sc->isolate_count++; -#endif - /* wait a bit for the reclaimer. */ - msleep(100); - stalled = true; - - /* We are about to die and free our memory. Return now. */ - if (fatal_signal_pending(current)) - return SWAP_CLUSTER_MAX; - } - - lru_add_drain(); - - spin_lock_irq(&pgdat->lru_lock); - - nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, - &nr_scanned, sc, lru); - - __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); - item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; - if (!cgroup_reclaim(sc)) - __count_vm_events(item, nr_scanned); - __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); - __count_vm_events(PGSCAN_ANON + file, nr_scanned); - - spin_unlock_irq(&pgdat->lru_lock); - - if (nr_taken == 0) - return 0; - - nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false); - - spin_lock_irq(&pgdat->lru_lock); - - move_pages_to_lru(lruvec, &page_list); - - __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); -#ifdef CONFIG_HYPERHOLD_FILE_LRU - if (file) - lru_note_cost(node_lruvec(pgdat), file, stat.nr_pageout); - else - lru_note_cost(lruvec, file, stat.nr_pageout); -#else - lru_note_cost(lruvec, file, stat.nr_pageout); - -#endif - - item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; - if (!cgroup_reclaim(sc)) - __count_vm_events(item, nr_reclaimed); - __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); - __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); - - spin_unlock_irq(&pgdat->lru_lock); - - mem_cgroup_uncharge_list(&page_list); - free_unref_page_list(&page_list); - - /* - * If dirty pages are scanned that are not queued for IO, it - * implies that flushers are not doing their job. This can - * happen when memory pressure pushes dirty pages to the end of - * the LRU before the dirty limits are breached and the dirty - * data has expired. It can also happen when the proportion of - * dirty pages grows not through writes but through memory - * pressure reclaiming all the clean cache. And in some cases, - * the flushers simply cannot keep up with the allocation - * rate. Nudge the flusher threads in case they are asleep. - */ - if (stat.nr_unqueued_dirty == nr_taken) - wakeup_flusher_threads(WB_REASON_VMSCAN); - - sc->nr.dirty += stat.nr_dirty; - sc->nr.congested += stat.nr_congested; - sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; - sc->nr.writeback += stat.nr_writeback; - sc->nr.immediate += stat.nr_immediate; - sc->nr.taken += nr_taken; - if (file) - sc->nr.file_taken += nr_taken; - - trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, - nr_scanned, nr_reclaimed, &stat, sc->priority, file); - return nr_reclaimed; -} - -void shrink_active_list(unsigned long nr_to_scan, - struct lruvec *lruvec, - struct scan_control *sc, - enum lru_list lru) -{ - unsigned long nr_taken; - unsigned long nr_scanned; - unsigned long vm_flags; - LIST_HEAD(l_hold); /* The pages which were snipped off */ - LIST_HEAD(l_active); - LIST_HEAD(l_inactive); - struct page *page; - unsigned nr_deactivate, nr_activate; - unsigned nr_rotated = 0; - int file = is_file_lru(lru); - struct pglist_data *pgdat = lruvec_pgdat(lruvec); - - lru_add_drain(); - - spin_lock_irq(&pgdat->lru_lock); - - nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, - &nr_scanned, sc, lru); - - __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); - - if (!cgroup_reclaim(sc)) - __count_vm_events(PGREFILL, nr_scanned); - __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); - - spin_unlock_irq(&pgdat->lru_lock); - - while (!list_empty(&l_hold)) { - cond_resched(); - page = lru_to_page(&l_hold); - list_del(&page->lru); - - if (unlikely(!page_evictable(page))) { - putback_lru_page(page); - continue; - } - - if (unlikely(buffer_heads_over_limit)) { - if (page_has_private(page) && trylock_page(page)) { - if (page_has_private(page)) - try_to_release_page(page, 0); - unlock_page(page); - } - } - - if (page_referenced(page, 0, sc->target_mem_cgroup, - &vm_flags)) { - /* - * Identify referenced, file-backed active pages and - * give them one more trip around the active list. So - * that executable code get better chances to stay in - * memory under moderate memory pressure. Anon pages - * are not likely to be evicted by use-once streaming - * IO, plus JVM can create lots of anon VM_EXEC pages, - * so we ignore them here. - */ - if ((vm_flags & VM_EXEC) && page_is_file_lru(page)) { - nr_rotated += thp_nr_pages(page); - list_add(&page->lru, &l_active); - continue; - } - } - - ClearPageActive(page); /* we are de-activating */ - SetPageWorkingset(page); - list_add(&page->lru, &l_inactive); - } - - /* - * Move pages back to the lru list. - */ - spin_lock_irq(&pgdat->lru_lock); - - nr_activate = move_pages_to_lru(lruvec, &l_active); - nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); - /* Keep all free pages in l_active list */ - list_splice(&l_inactive, &l_active); - - __count_vm_events(PGDEACTIVATE, nr_deactivate); - __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); - - __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); - spin_unlock_irq(&pgdat->lru_lock); - - mem_cgroup_uncharge_list(&l_active); - free_unref_page_list(&l_active); - trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, - nr_deactivate, nr_rotated, sc->priority, file); -} - -unsigned long reclaim_pages(struct list_head *page_list) -{ - int nid = NUMA_NO_NODE; - unsigned int nr_reclaimed = 0; - LIST_HEAD(node_page_list); - struct reclaim_stat dummy_stat; - struct page *page; - struct scan_control sc = { - .gfp_mask = GFP_KERNEL, - .priority = DEF_PRIORITY, - .may_writepage = 1, - .may_unmap = 1, - .may_swap = 1, - }; - - while (!list_empty(page_list)) { - page = lru_to_page(page_list); - if (nid == NUMA_NO_NODE) { - nid = page_to_nid(page); - INIT_LIST_HEAD(&node_page_list); - } - - if (nid == page_to_nid(page)) { - ClearPageActive(page); - list_move(&page->lru, &node_page_list); - continue; - } - - nr_reclaimed += shrink_page_list(&node_page_list, - NODE_DATA(nid), - &sc, &dummy_stat, false); - while (!list_empty(&node_page_list)) { - page = lru_to_page(&node_page_list); - list_del(&page->lru); - putback_lru_page(page); - } - - nid = NUMA_NO_NODE; - } - - if (!list_empty(&node_page_list)) { - nr_reclaimed += shrink_page_list(&node_page_list, - NODE_DATA(nid), - &sc, &dummy_stat, false); - while (!list_empty(&node_page_list)) { - page = lru_to_page(&node_page_list); - list_del(&page->lru); - putback_lru_page(page); - } - } - - return nr_reclaimed; -} - -unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, - struct lruvec *lruvec, struct scan_control *sc) -{ -#ifdef CONFIG_RECLAIM_ACCT - unsigned long nr_reclaimed; - unsigned int stub; - - stub = is_file_lru(lru) ? RA_SHRINKFILE : RA_SHRINKANON; - reclaimacct_substage_start(stub); -#endif - if (is_active_lru(lru)) { - if (sc->may_deactivate & (1 << is_file_lru(lru))) - shrink_active_list(nr_to_scan, lruvec, sc, lru); - else - sc->skipped_deactivate = 1; -#ifdef CONFIG_RECLAIM_ACCT - reclaimacct_substage_end(stub, 0, NULL); -#endif - return 0; - } - -#ifdef CONFIG_RECLAIM_ACCT - nr_reclaimed = shrink_inactive_list(nr_to_scan, lruvec, sc, lru); - reclaimacct_substage_end(stub, nr_reclaimed, NULL); - return nr_reclaimed; -#else - return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); -#endif -} - -/* - * The inactive anon list should be small enough that the VM never has - * to do too much work. - * - * The inactive file list should be small enough to leave most memory - * to the established workingset on the scan-resistant active list, - * but large enough to avoid thrashing the aggregate readahead window. - * - * Both inactive lists should also be large enough that each inactive - * page has a chance to be referenced again before it is reclaimed. - * - * If that fails and refaulting is observed, the inactive list grows. - * - * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages - * on this LRU, maintained by the pageout code. An inactive_ratio - * of 3 means 3:1 or 25% of the pages are kept on the inactive list. - * - * total target max - * memory ratio inactive - * ------------------------------------- - * 10MB 1 5MB - * 100MB 1 50MB - * 1GB 3 250MB - * 10GB 10 0.9GB - * 100GB 31 3GB - * 1TB 101 10GB - * 10TB 320 32GB - */ -bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) -{ - enum lru_list active_lru = inactive_lru + LRU_ACTIVE; - unsigned long inactive, active; - unsigned long inactive_ratio; - unsigned long gb; - - inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); - active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); - - gb = (inactive + active) >> (30 - PAGE_SHIFT); - if (gb) - inactive_ratio = int_sqrt(10 * gb); - else - inactive_ratio = 1; - - return inactive * inactive_ratio < active; -} - -/* - * Determine how aggressively the anon and file LRU lists should be - * scanned. The relative value of each set of LRU lists is determined - * by looking at the fraction of the pages scanned we did rotate back - * onto the active list instead of evict. - * - * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan - * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan - */ -#ifndef CONFIG_HYPERHOLD_FILE_LRU -static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, - unsigned long *nr) -{ - struct mem_cgroup *memcg = lruvec_memcg(lruvec); - unsigned long anon_cost, file_cost, total_cost; - int swappiness = mem_cgroup_swappiness(memcg); - u64 fraction[ANON_AND_FILE]; - u64 denominator = 0; /* gcc */ - enum scan_balance scan_balance; - unsigned long ap, fp; - enum lru_list lru; - - /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 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 (cgroup_reclaim(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 && swappiness) { - scan_balance = SCAN_EQUAL; - goto out; - } - - /* - * If the system is almost out of file pages, force-scan anon. - */ - if (sc->file_is_tiny) { - scan_balance = SCAN_ANON; - goto out; - } - - /* - * If there is enough inactive page cache, we do not reclaim - * anything from the anonymous working right now. - */ - if (sc->cache_trim_mode) { - scan_balance = SCAN_FILE; - goto out; - } - - scan_balance = SCAN_FRACT; - /* - * Calculate the pressure balance between anon and file pages. - * - * The amount of pressure we put on each LRU is inversely - * proportional to the cost of reclaiming each list, as - * determined by the share of pages that are refaulting, times - * the relative IO cost of bringing back a swapped out - * anonymous page vs reloading a filesystem page (swappiness). - * - * Although we limit that influence to ensure no list gets - * left behind completely: at least a third of the pressure is - * applied, before swappiness. - * - * With swappiness at 100, anon and file have equal IO cost. - */ - total_cost = sc->anon_cost + sc->file_cost; - anon_cost = total_cost + sc->anon_cost; - file_cost = total_cost + sc->file_cost; - total_cost = anon_cost + file_cost; - - ap = swappiness * (total_cost + 1); - ap /= anon_cost + 1; - - fp = (200 - swappiness) * (total_cost + 1); - fp /= file_cost + 1; - - fraction[0] = ap; - fraction[1] = fp; - denominator = ap + fp; -out: - for_each_evictable_lru(lru) { - int file = is_file_lru(lru); - unsigned long lruvec_size; - unsigned long low, min; - unsigned long scan; - - lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - mem_cgroup_protection(sc->target_mem_cgroup, memcg, - &min, &low); - - if (min || low) { - /* - * Scale a cgroup's reclaim pressure by proportioning - * its current usage to its memory.low or memory.min - * setting. - * - * This is important, as otherwise scanning aggression - * becomes extremely binary -- from nothing as we - * approach the memory protection threshold, to totally - * nominal as we exceed it. This results in requiring - * setting extremely liberal protection thresholds. It - * also means we simply get no protection at all if we - * set it too low, which is not ideal. - * - * If there is any protection in place, we reduce scan - * pressure by how much of the total memory used is - * within protection thresholds. - * - * There is one special case: in the first reclaim pass, - * we skip over all groups that are within their low - * protection. If that fails to reclaim enough pages to - * satisfy the reclaim goal, we come back and override - * the best-effort low protection. However, we still - * ideally want to honor how well-behaved groups are in - * that case instead of simply punishing them all - * equally. As such, we reclaim them based on how much - * memory they are using, reducing the scan pressure - * again by how much of the total memory used is under - * hard protection. - */ - unsigned long cgroup_size = mem_cgroup_size(memcg); - unsigned long protection; - - /* memory.low scaling, make sure we retry before OOM */ - if (!sc->memcg_low_reclaim && low > min) { - protection = low; - sc->memcg_low_skipped = 1; - } else { - protection = min; - } - - /* Avoid TOCTOU with earlier protection check */ - cgroup_size = max(cgroup_size, protection); - - scan = lruvec_size - lruvec_size * protection / - (cgroup_size + 1); - - /* - * Minimally target SWAP_CLUSTER_MAX pages to keep - * reclaim moving forwards, avoiding decrementing - * sc->priority further than desirable. - */ - scan = max(scan, SWAP_CLUSTER_MAX); - } else { - scan = lruvec_size; - } - - scan >>= sc->priority; - - /* - * If the cgroup's already been deleted, make sure to - * scrape out the remaining cache. - */ - if (!scan && !mem_cgroup_online(memcg)) - scan = min(lruvec_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. - * Make sure we don't miss the last page on - * the offlined memory cgroups because of a - * round-off error. - */ - scan = mem_cgroup_online(memcg) ? - div64_u64(scan * fraction[file], denominator) : - DIV64_U64_ROUND_UP(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; - } -} - -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; - bool proportional_reclaim; - struct blk_plug plug; - - 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. - */ - proportional_reclaim = (!cgroup_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); - } - } - - cond_resched(); - - if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) - 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; - } - - /* 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); - } - 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 (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) - shrink_active_list(SWAP_CLUSTER_MAX, lruvec, - sc, LRU_ACTIVE_ANON); -} -#endif - -/* Use reclaim/compaction for costly allocs or under memory pressure */ -static bool in_reclaim_compaction(struct scan_control *sc) -{ - if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && - (sc->order > PAGE_ALLOC_COSTLY_ORDER || - sc->priority < DEF_PRIORITY - 2)) - return true; - - return false; -} - -/* - * Reclaim/compaction is used for high-order allocation requests. It reclaims - * order-0 pages before compacting the zone. should_continue_reclaim() returns - * true if more pages should be reclaimed such that when the page allocator - * calls try_to_compact_pages() that it will have enough free pages to succeed. - * It will give up earlier than that if there is difficulty reclaiming pages. - */ -inline bool should_continue_reclaim(struct pglist_data *pgdat, - unsigned long nr_reclaimed, - struct scan_control *sc) -{ - unsigned long pages_for_compaction; - unsigned long inactive_lru_pages; - int z; - - /* If not in reclaim/compaction mode, stop */ - if (!in_reclaim_compaction(sc)) - return false; - - /* - * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX - * number of pages that were scanned. This will return to the caller - * with the risk reclaim/compaction and the resulting allocation attempt - * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL - * allocations through requiring that the full LRU list has been scanned - * first, by assuming that zero delta of sc->nr_scanned means full LRU - * scan, but that approximation was wrong, and there were corner cases - * where always a non-zero amount of pages were scanned. - */ - if (!nr_reclaimed) - return false; - - /* If compaction would go ahead or the allocation would succeed, stop */ - for (z = 0; z <= sc->reclaim_idx; z++) { - struct zone *zone = &pgdat->node_zones[z]; - if (!managed_zone(zone)) - continue; - - switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { - case COMPACT_SUCCESS: - case COMPACT_CONTINUE: - return false; - default: - /* check next zone */ - ; - } - } - - /* - * If we have not reclaimed enough pages for compaction and the - * inactive lists are large enough, continue reclaiming - */ - pages_for_compaction = compact_gap(sc->order); - inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); - if (get_nr_swap_pages() > 0) - inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); - - return inactive_lru_pages > pages_for_compaction; -} - -#ifndef CONFIG_HYPERHOLD_FILE_LRU -static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) -{ - struct mem_cgroup *target_memcg = sc->target_mem_cgroup; - struct mem_cgroup *memcg; - - memcg = mem_cgroup_iter(target_memcg, NULL, NULL); - do { - struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); - unsigned long reclaimed; - unsigned long scanned; - - /* - * This loop can become CPU-bound when target memcgs - * aren't eligible for reclaim - either because they - * don't have any reclaimable pages, or because their - * memory is explicitly protected. Avoid soft lockups. - */ - cond_resched(); - - mem_cgroup_calculate_protection(target_memcg, memcg); - - if (mem_cgroup_below_min(memcg)) { - /* - * Hard protection. - * If there is no reclaimable memory, OOM. - */ - continue; - } else if (mem_cgroup_below_low(memcg)) { - /* - * Soft protection. - * Respect the protection only as long as - * there is an unprotected supply - * of reclaimable memory from other cgroups. - */ - if (!sc->memcg_low_reclaim) { - sc->memcg_low_skipped = 1; - continue; - } - memcg_memory_event(memcg, MEMCG_LOW); - } - - reclaimed = sc->nr_reclaimed; - scanned = sc->nr_scanned; - - shrink_lruvec(lruvec, sc); - - shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, - sc->priority); - - /* Record the group's reclaim efficiency */ - vmpressure(sc->gfp_mask, memcg, false, - sc->nr_scanned - scanned, - sc->nr_reclaimed - reclaimed); - - } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); -} - -static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) -{ - struct reclaim_state *reclaim_state = current->reclaim_state; - unsigned long nr_reclaimed, nr_scanned; - struct lruvec *target_lruvec; - bool reclaimable = false; - unsigned long file; - - target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); - -again: - memset(&sc->nr, 0, sizeof(sc->nr)); - - nr_reclaimed = sc->nr_reclaimed; - nr_scanned = sc->nr_scanned; - - /* - * Determine the scan balance between anon and file LRUs. - */ - spin_lock_irq(&pgdat->lru_lock); - sc->anon_cost = target_lruvec->anon_cost; - sc->file_cost = target_lruvec->file_cost; - spin_unlock_irq(&pgdat->lru_lock); - - /* - * Target desirable inactive:active list ratios for the anon - * and file LRU lists. - */ - if (!sc->force_deactivate) { - unsigned long refaults; - - refaults = lruvec_page_state(target_lruvec, - WORKINGSET_ACTIVATE_ANON); - if (refaults != target_lruvec->refaults[0] || - inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) - sc->may_deactivate |= DEACTIVATE_ANON; - else - sc->may_deactivate &= ~DEACTIVATE_ANON; - - /* - * When refaults are being observed, it means a new - * workingset is being established. Deactivate to get - * rid of any stale active pages quickly. - */ - refaults = lruvec_page_state(target_lruvec, - WORKINGSET_ACTIVATE_FILE); - if (refaults != target_lruvec->refaults[1] || - inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) - sc->may_deactivate |= DEACTIVATE_FILE; - else - sc->may_deactivate &= ~DEACTIVATE_FILE; - } else - sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; - - /* - * If we have plenty of inactive file pages that aren't - * thrashing, try to reclaim those first before touching - * anonymous pages. - */ - file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); - if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) - sc->cache_trim_mode = 1; - else - sc->cache_trim_mode = 0; - - /* - * 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 (!cgroup_reclaim(sc)) { - unsigned long total_high_wmark = 0; - unsigned long free, anon; - int z; - - free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); - file = node_page_state(pgdat, NR_ACTIVE_FILE) + - node_page_state(pgdat, NR_INACTIVE_FILE); - - for (z = 0; z < MAX_NR_ZONES; z++) { - struct zone *zone = &pgdat->node_zones[z]; - if (!managed_zone(zone)) - continue; - - total_high_wmark += high_wmark_pages(zone); - } - - /* - * Consider anon: if that's low too, this isn't a - * runaway file reclaim problem, but rather just - * extreme pressure. Reclaim as per usual then. - */ - anon = node_page_state(pgdat, NR_INACTIVE_ANON); - - sc->file_is_tiny = - file + free <= total_high_wmark && - !(sc->may_deactivate & DEACTIVATE_ANON) && - anon >> sc->priority; - } - - shrink_node_memcgs(pgdat, sc); - - if (reclaim_state) { - sc->nr_reclaimed += reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } - - /* Record the subtree's reclaim efficiency */ - vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, - sc->nr_scanned - nr_scanned, - sc->nr_reclaimed - nr_reclaimed); - - if (sc->nr_reclaimed - nr_reclaimed) - reclaimable = true; - - if (current_is_kswapd()) { - /* - * If reclaim is isolating dirty pages under writeback, - * it implies that the long-lived page allocation rate - * is exceeding the page laundering rate. Either the - * global limits are not being effective at throttling - * processes due to the page distribution throughout - * zones or there is heavy usage of a slow backing - * device. The only option is to throttle from reclaim - * context which is not ideal as there is no guarantee - * the dirtying process is throttled in the same way - * balance_dirty_pages() manages. - * - * Once a node is flagged PGDAT_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 (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) - set_bit(PGDAT_WRITEBACK, &pgdat->flags); - - /* Allow kswapd to start writing pages during reclaim.*/ - if (sc->nr.unqueued_dirty == sc->nr.file_taken) - set_bit(PGDAT_DIRTY, &pgdat->flags); - - /* - * If kswapd scans pages 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 (sc->nr.immediate) - congestion_wait(BLK_RW_ASYNC, HZ/10); - } - - /* - * Tag a node/memcg as congested if all the dirty pages - * scanned were backed by a congested BDI and - * wait_iff_congested will stall. - * - * Legacy memcg will stall in page writeback so avoid forcibly - * stalling in wait_iff_congested(). - */ - if ((current_is_kswapd() || - (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && - sc->nr.dirty && sc->nr.dirty == sc->nr.congested) - set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); - - /* - * Stall direct reclaim for IO completions if underlying BDIs - * and node is congested. Allow kswapd to continue until it - * starts encountering unqueued dirty pages or cycling through - * the LRU too quickly. - */ - if (!current_is_kswapd() && current_may_throttle() && - !sc->hibernation_mode && - test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - wait_iff_congested(BLK_RW_ASYNC, HZ/10); - - if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, - sc)) - goto again; - - /* - * Kswapd gives up on balancing particular nodes after too - * many failures to reclaim anything from them and goes to - * sleep. On reclaim progress, reset the failure counter. A - * successful direct reclaim run will revive a dormant kswapd. - */ - if (reclaimable) - pgdat->kswapd_failures = 0; -} -#endif - -/* - * Returns true if compaction should go ahead for a costly-order request, or - * the allocation would already succeed without compaction. Return false if we - * should reclaim first. - */ -static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) -{ - unsigned long watermark; - enum compact_result suitable; - - suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); - if (suitable == COMPACT_SUCCESS) - /* Allocation should succeed already. Don't reclaim. */ - return true; - if (suitable == COMPACT_SKIPPED) - /* Compaction cannot yet proceed. Do reclaim. */ - return false; - - /* - * Compaction is already possible, but it takes time to run and there - * are potentially other callers using the pages just freed. So proceed - * with reclaim to make a buffer of free pages available to give - * compaction a reasonable chance of completing and allocating the page. - * Note that we won't actually reclaim the whole buffer in one attempt - * as the target watermark in should_continue_reclaim() is lower. But if - * we are already above the high+gap watermark, don't reclaim at all. - */ - watermark = high_wmark_pages(zone) + compact_gap(sc->order); - - return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); -} - -/* - * This is the direct reclaim path, for page-allocating processes. We only - * try to reclaim pages from zones which will satisfy the caller's allocation - * request. - * - * If a zone is deemed to be full of pinned pages then just give it a light - * scan then give up on it. - */ -static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) -{ - struct zoneref *z; - struct zone *zone; - unsigned long nr_soft_reclaimed; - unsigned long nr_soft_scanned; - gfp_t orig_mask; - pg_data_t *last_pgdat = NULL; - - /* - * 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; - sc->reclaim_idx = gfp_zone(sc->gfp_mask); - } - - for_each_zone_zonelist_nodemask(zone, z, zonelist, - sc->reclaim_idx, sc->nodemask) { - /* - * Take care memory controller reclaiming has small influence - * to global LRU. - */ - if (!cgroup_reclaim(sc)) { - if (!cpuset_zone_allowed(zone, - GFP_KERNEL | __GFP_HARDWALL)) - continue; - - /* - * If we already have plenty of memory free for - * compaction in this zone, don't free any more. - * Even though compaction is invoked for any - * non-zero order, only frequent costly order - * reclamation is disruptive enough to become a - * noticeable problem, like transparent huge - * page allocations. - */ - if (IS_ENABLED(CONFIG_COMPACTION) && - sc->order > PAGE_ALLOC_COSTLY_ORDER && - compaction_ready(zone, sc)) { - sc->compaction_ready = true; - continue; - } - - /* - * Shrink each node in the zonelist once. If the - * zonelist is ordered by zone (not the default) then a - * node may be shrunk multiple times but in that case - * the user prefers lower zones being preserved. - */ - if (zone->zone_pgdat == last_pgdat) - continue; - - /* - * This steals pages from memory cgroups over softlimit - * and returns the number of reclaimed pages and - * scanned pages. This works for global memory pressure - * and balancing, not for a memcg's limit. - */ - nr_soft_scanned = 0; - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, - sc->order, sc->gfp_mask, - &nr_soft_scanned); - sc->nr_reclaimed += nr_soft_reclaimed; - sc->nr_scanned += nr_soft_scanned; - /* need some check for avoid more shrink_zone() */ - } - - /* See comment about same check for global reclaim above */ - if (zone->zone_pgdat == last_pgdat) - continue; - last_pgdat = zone->zone_pgdat; -#ifdef CONFIG_HYPERHOLD_FILE_LRU - shrink_node_hyperhold(zone->zone_pgdat, sc); -#else - shrink_node(zone->zone_pgdat, sc); -#endif - } - - /* - * Restore to original mask to avoid the impact on the caller if we - * promoted it to __GFP_HIGHMEM. - */ - sc->gfp_mask = orig_mask; -} - -static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) -{ - struct lruvec *target_lruvec; - unsigned long refaults; - -#ifdef CONFIG_HYPERHOLD_FILE_LRU - struct lruvec *lruvec; - - lruvec = node_lruvec(pgdat); - lruvec->refaults[0] = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE_ANON); /* modified */ - lruvec->refaults[1] = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE_FILE); /* modified */ -#endif - - target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); - refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); - target_lruvec->refaults[0] = refaults; - refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); - target_lruvec->refaults[1] = refaults; -} - -/* - * This is the main entry point to direct page reclaim. - * - * If a full scan of the inactive list fails to free enough memory then we - * are "out of memory" and something needs to be killed. - * - * If the caller is !__GFP_FS then the probability of a failure is reasonably - * high - the zone may be full of dirty or under-writeback pages, which this - * caller can't do much about. We kick the writeback threads and take explicit - * naps in the hope that some of these pages can be written. But if the - * allocating task holds filesystem locks which prevent writeout this might not - * work, and the allocation attempt will fail. - * - * returns: 0, if no pages reclaimed - * else, the number of pages reclaimed - */ -static unsigned long do_try_to_free_pages(struct zonelist *zonelist, - struct scan_control *sc) -{ - int initial_priority = sc->priority; - pg_data_t *last_pgdat; - struct zoneref *z; - struct zone *zone; -retry: - delayacct_freepages_start(); - - if (!cgroup_reclaim(sc)) - __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); - - do { - vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, - sc->priority); - sc->nr_scanned = 0; - shrink_zones(zonelist, sc); - - if (sc->nr_reclaimed >= sc->nr_to_reclaim) - break; - - if (sc->compaction_ready) - break; - - /* - * If we're getting trouble reclaiming, start doing - * writepage even in laptop mode. - */ - if (sc->priority < DEF_PRIORITY - 2) - sc->may_writepage = 1; - } while (--sc->priority >= 0); - - last_pgdat = NULL; - for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, - sc->nodemask) { - if (zone->zone_pgdat == last_pgdat) - continue; - last_pgdat = zone->zone_pgdat; - - snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); - - if (cgroup_reclaim(sc)) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, - zone->zone_pgdat); - clear_bit(LRUVEC_CONGESTED, &lruvec->flags); - } - } - - delayacct_freepages_end(); - - if (sc->nr_reclaimed) - return sc->nr_reclaimed; - - /* Aborted reclaim to try compaction? don't OOM, then */ - if (sc->compaction_ready) - return 1; - - /* - * We make inactive:active ratio decisions based on the node's - * composition of memory, but a restrictive reclaim_idx or a - * memory.low cgroup setting can exempt large amounts of - * memory from reclaim. Neither of which are very common, so - * instead of doing costly eligibility calculations of the - * entire cgroup subtree up front, we assume the estimates are - * good, and retry with forcible deactivation if that fails. - */ - if (sc->skipped_deactivate) { - sc->priority = initial_priority; - sc->force_deactivate = 1; - sc->skipped_deactivate = 0; - goto retry; - } - - /* Untapped cgroup reserves? Don't OOM, retry. */ - if (sc->memcg_low_skipped) { - sc->priority = initial_priority; - sc->force_deactivate = 0; - sc->memcg_low_reclaim = 1; - sc->memcg_low_skipped = 0; - goto retry; - } - - return 0; -} - -static bool allow_direct_reclaim(pg_data_t *pgdat) -{ - struct zone *zone; - unsigned long pfmemalloc_reserve = 0; - unsigned long free_pages = 0; - int i; - bool wmark_ok; - - if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) - return true; - - for (i = 0; i <= ZONE_NORMAL; i++) { - zone = &pgdat->node_zones[i]; - if (!managed_zone(zone)) - continue; - - if (!zone_reclaimable_pages(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 */ - if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { - if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) - WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); - - wake_up_interruptible(&pgdat->kswapd_wait); - } - - return wmark_ok; -} - -/* - * Throttle direct reclaimers if backing storage is backed by the network - * and the PFMEMALLOC reserve for the preferred node is getting dangerously - * depleted. kswapd will continue to make progress and wake the processes - * when the low watermark is reached. - * - * Returns true if a fatal signal was delivered during throttling. If this - * happens, the page allocator should not consider triggering the OOM killer. - */ -static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, - nodemask_t *nodemask) -{ - struct zoneref *z; - struct zone *zone; - pg_data_t *pgdat = NULL; - - /* - * Kernel threads should not be throttled as they may be indirectly - * responsible for cleaning pages necessary for reclaim to make forward - * progress. kjournald for example may enter direct reclaim while - * committing a transaction where throttling it could forcing other - * processes to block on log_wait_commit(). - */ - if (current->flags & PF_KTHREAD) - goto out; - - /* - * If a fatal signal is pending, this process should not throttle. - * It should return quickly so it can exit and free its memory - */ - if (fatal_signal_pending(current)) - goto out; - - /* - * 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_zone(gfp_mask), nodemask) { - if (zone_idx(zone) > ZONE_NORMAL) - continue; - - /* Throttle based on the first usable node */ - pgdat = zone->zone_pgdat; - if (allow_direct_reclaim(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 */ - count_vm_event(PGSCAN_DIRECT_THROTTLE); - - /* - * If the caller cannot enter the filesystem, it's possible that it - * is due to the caller holding an FS lock or performing a journal - * transaction in the case of a filesystem like ext[3|4]. In this case, - * it is not safe to block on pfmemalloc_wait as kswapd could be - * blocked waiting on the same lock. Instead, throttle for up to a - * second before continuing. - */ - if (!(gfp_mask & __GFP_FS)) { - wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, - allow_direct_reclaim(pgdat), HZ); - - goto check_pending; - } - - /* Throttle until kswapd wakes the process */ - wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, - allow_direct_reclaim(pgdat)); - -check_pending: - if (fatal_signal_pending(current)) - return true; - -out: - return false; -} - -unsigned long try_to_free_pages(struct zonelist *zonelist, int order, - gfp_t gfp_mask, nodemask_t *nodemask) -{ - unsigned long nr_reclaimed; - struct scan_control sc = { - .nr_to_reclaim = SWAP_CLUSTER_MAX, - .gfp_mask = current_gfp_context(gfp_mask), - .reclaim_idx = gfp_zone(gfp_mask), - .order = order, - .nodemask = nodemask, - .priority = DEF_PRIORITY, - .may_writepage = !laptop_mode, - .may_unmap = 1, - .may_swap = 1, - }; - - /* - * scan_control uses s8 fields for order, priority, and reclaim_idx. - * Confirm they are large enough for max values. - */ - BUILD_BUG_ON(MAX_ORDER > S8_MAX); - BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); - BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); - - /* - * Do not enter reclaim if fatal signal was delivered while throttled. - * 1 is returned so that the page allocator does not OOM kill at this - * point. - */ - if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) - return 1; - - set_task_reclaim_state(current, &sc.reclaim_state); - trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); - - nr_reclaimed = do_try_to_free_pages(zonelist, &sc); - - trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); - set_task_reclaim_state(current, NULL); - - return nr_reclaimed; -} - -#ifdef CONFIG_MEMCG - -/* Only used by soft limit reclaim. Do not reuse for anything else. */ -unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, - gfp_t gfp_mask, bool noswap, - pg_data_t *pgdat, - unsigned long *nr_scanned) -{ - struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); - struct scan_control sc = { - .nr_to_reclaim = SWAP_CLUSTER_MAX, - .target_mem_cgroup = memcg, - .may_writepage = !laptop_mode, - .may_unmap = 1, - .reclaim_idx = MAX_NR_ZONES - 1, - .may_swap = !noswap, - }; -#ifdef CONFIG_HYPERHOLD_FILE_LRU - unsigned long nr[NR_LRU_LISTS]; -#endif - - WARN_ON_ONCE(!current->reclaim_state); - - sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | - (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); - - trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, - sc.gfp_mask); - - /* - * NOTE: Although we can get the priority field, using it - * here is not a good idea, since it limits the pages we can scan. - * if we don't reclaim here, the shrink_node from balance_pgdat - * will pick up pages from other mem cgroup's as well. We hack - * the priority and make it zero. - */ -#ifdef CONFIG_HYPERHOLD_FILE_LRU - nr[LRU_ACTIVE_ANON] = lruvec_lru_size(lruvec, - LRU_ACTIVE_ANON, MAX_NR_ZONES); - nr[LRU_INACTIVE_ANON] = lruvec_lru_size(lruvec, - LRU_INACTIVE_ANON, MAX_NR_ZONES); - nr[LRU_ACTIVE_FILE] = 0; - nr[LRU_INACTIVE_FILE] = 0; - shrink_anon_memcg(pgdat, memcg, &sc, nr); -#else - shrink_lruvec(lruvec, &sc); -#endif - - trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); - - *nr_scanned = sc.nr_scanned; - - return sc.nr_reclaimed; -} - -unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, - unsigned long nr_pages, - gfp_t gfp_mask, - bool may_swap) -{ - unsigned long nr_reclaimed; - unsigned int noreclaim_flag; - struct scan_control sc = { - .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), - .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | - (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), - .reclaim_idx = MAX_NR_ZONES - 1, - .target_mem_cgroup = memcg, - .priority = DEF_PRIORITY, - .may_writepage = !laptop_mode, - .may_unmap = 1, - .may_swap = may_swap, - }; - /* - * Traverse the ZONELIST_FALLBACK zonelist of the current node to put - * equal pressure on all the nodes. This is based on the assumption that - * the reclaim does not bail out early. - */ - struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); - - set_task_reclaim_state(current, &sc.reclaim_state); - trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); - noreclaim_flag = memalloc_noreclaim_save(); - - nr_reclaimed = do_try_to_free_pages(zonelist, &sc); - - memalloc_noreclaim_restore(noreclaim_flag); - trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); - set_task_reclaim_state(current, NULL); - - return nr_reclaimed; -} -#endif - -static void age_active_anon(struct pglist_data *pgdat, - struct scan_control *sc) -{ - struct mem_cgroup *memcg; - struct lruvec *lruvec; - - if (!total_swap_pages) - return; - - lruvec = mem_cgroup_lruvec(NULL, pgdat); - if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) - return; - - memcg = mem_cgroup_iter(NULL, NULL, NULL); - do { - lruvec = mem_cgroup_lruvec(memcg, pgdat); - shrink_active_list(SWAP_CLUSTER_MAX, lruvec, - sc, LRU_ACTIVE_ANON); - memcg = mem_cgroup_iter(NULL, memcg, NULL); - } while (memcg); -} - -static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) -{ - int i; - struct zone *zone; - - /* - * Check for watermark boosts top-down as the higher zones - * are more likely to be boosted. Both watermarks and boosts - * should not be checked at the same time as reclaim would - * start prematurely when there is no boosting and a lower - * zone is balanced. - */ - for (i = highest_zoneidx; i >= 0; i--) { - zone = pgdat->node_zones + i; - if (!managed_zone(zone)) - continue; - - if (zone->watermark_boost) - return true; - } - - return false; -} - -/* - * Returns true if there is an eligible zone balanced for the request order - * and highest_zoneidx - */ -static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) -{ - int i; - unsigned long mark = -1; - struct zone *zone; - - /* - * Check watermarks bottom-up as lower zones are more likely to - * meet watermarks. - */ - for (i = 0; i <= highest_zoneidx; i++) { - zone = pgdat->node_zones + i; - - if (!managed_zone(zone)) - continue; - - mark = high_wmark_pages(zone); - if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) - return true; - } - - /* - * If a node has no populated zone within highest_zoneidx, it does not - * need balancing by definition. This can happen if a zone-restricted - * allocation tries to wake a remote kswapd. - */ - if (mark == -1) - return true; - - return false; -} - -/* Clear pgdat state for congested, dirty or under writeback. */ -static void clear_pgdat_congested(pg_data_t *pgdat) -{ - struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); - - clear_bit(LRUVEC_CONGESTED, &lruvec->flags); - clear_bit(PGDAT_DIRTY, &pgdat->flags); - clear_bit(PGDAT_WRITEBACK, &pgdat->flags); -} - -/* - * Prepare kswapd for sleeping. This verifies that there are no processes - * waiting in throttle_direct_reclaim() and that watermarks have been met. - * - * Returns true if kswapd is ready to sleep - */ -static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, - int highest_zoneidx) -{ - /* - * The throttled processes are normally woken up in balance_pgdat() as - * soon as allow_direct_reclaim() is true. But there is a potential - * race between when kswapd checks the watermarks and a process gets - * throttled. There is also a potential race if processes get - * throttled, kswapd wakes, a large process exits thereby balancing the - * zones, which causes kswapd to exit balance_pgdat() before reaching - * the wake up checks. If kswapd is going to sleep, no process should - * be sleeping on pfmemalloc_wait, so wake them now if necessary. If - * the wake up is premature, processes will wake kswapd and get - * throttled again. The difference from wake ups in balance_pgdat() is - * that here we are under prepare_to_wait(). - */ - if (waitqueue_active(&pgdat->pfmemalloc_wait)) - wake_up_all(&pgdat->pfmemalloc_wait); - - /* Hopeless node, leave it to direct reclaim */ - if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) - return true; - - if (pgdat_balanced(pgdat, order, highest_zoneidx)) { - clear_pgdat_congested(pgdat); - return true; - } - - return false; -} - -/* - * kswapd shrinks a node of pages that are at or below the highest usable - * zone that is currently unbalanced. - * - * 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_node(pg_data_t *pgdat, - struct scan_control *sc) -{ - struct zone *zone; - int z; - - /* Reclaim a number of pages proportional to the number of zones */ - sc->nr_to_reclaim = 0; - for (z = 0; z <= sc->reclaim_idx; z++) { - zone = pgdat->node_zones + z; - if (!managed_zone(zone)) - continue; - - sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); - } - - /* - * Historically care was taken to put equal pressure on all zones but - * now pressure is applied based on node LRU order. - */ -#ifdef CONFIG_HYPERHOLD_FILE_LRU - shrink_node_hyperhold(pgdat, sc); -#else - shrink_node(pgdat, sc); -#endif - - /* - * Fragmentation may mean that the system cannot be rebalanced for - * high-order allocations. If twice the allocation size has been - * reclaimed then recheck watermarks only at order-0 to prevent - * excessive reclaim. Assume that a process requested a high-order - * can direct reclaim/compact. - */ - if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) - sc->order = 0; - - return sc->nr_scanned >= sc->nr_to_reclaim; -} - -/* - * For kswapd, balance_pgdat() will reclaim pages across a node from zones - * that are eligible for use by the caller until at least one zone is - * balanced. - * - * Returns the order kswapd finished reclaiming at. - * - * kswapd scans the zones in the highmem->normal->dma direction. It skips - * zones which have free_pages > high_wmark_pages(zone), but once a zone is - * found to have free_pages <= high_wmark_pages(zone), any page in that zone - * or lower is eligible for reclaim until at least one usable zone is - * balanced. - */ -static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) -{ - int i; - unsigned long nr_soft_reclaimed; - unsigned long nr_soft_scanned; - unsigned long pflags; - unsigned long nr_boost_reclaim; - unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; - bool boosted; - struct zone *zone; - struct scan_control sc = { - .gfp_mask = GFP_KERNEL, - .order = order, - .may_unmap = 1, - }; - - set_task_reclaim_state(current, &sc.reclaim_state); - psi_memstall_enter(&pflags); - __fs_reclaim_acquire(); - - count_vm_event(PAGEOUTRUN); - - /* - * Account for the reclaim boost. Note that the zone boost is left in - * place so that parallel allocations that are near the watermark will - * stall or direct reclaim until kswapd is finished. - */ - nr_boost_reclaim = 0; - for (i = 0; i <= highest_zoneidx; i++) { - zone = pgdat->node_zones + i; - if (!managed_zone(zone)) - continue; - - nr_boost_reclaim += zone->watermark_boost; - zone_boosts[i] = zone->watermark_boost; - } - boosted = nr_boost_reclaim; - -restart: - sc.priority = DEF_PRIORITY; - do { - unsigned long nr_reclaimed = sc.nr_reclaimed; - bool raise_priority = true; - bool balanced; - bool ret; - - sc.reclaim_idx = highest_zoneidx; - - /* - * If the number of buffer_heads exceeds the maximum allowed - * then consider reclaiming from all zones. This has a dual - * purpose -- on 64-bit systems it is expected that - * buffer_heads are stripped during active rotation. On 32-bit - * systems, highmem pages can pin lowmem memory and shrinking - * buffers can relieve lowmem pressure. Reclaim may still not - * go ahead if all eligible zones for the original allocation - * request are balanced to avoid excessive reclaim from kswapd. - */ - if (buffer_heads_over_limit) { - for (i = MAX_NR_ZONES - 1; i >= 0; i--) { - zone = pgdat->node_zones + i; - if (!managed_zone(zone)) - continue; - - sc.reclaim_idx = i; - break; - } - } - - /* - * If the pgdat is imbalanced then ignore boosting and preserve - * the watermarks for a later time and restart. Note that the - * zone watermarks will be still reset at the end of balancing - * on the grounds that the normal reclaim should be enough to - * re-evaluate if boosting is required when kswapd next wakes. - */ - balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); - if (!balanced && nr_boost_reclaim) { - nr_boost_reclaim = 0; - goto restart; - } - - /* - * If boosting is not active then only reclaim if there are no - * eligible zones. Note that sc.reclaim_idx is not used as - * buffer_heads_over_limit may have adjusted it. - */ - if (!nr_boost_reclaim && balanced) - goto out; - - /* Limit the priority of boosting to avoid reclaim writeback */ - if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) - raise_priority = false; - - /* - * Do not writeback or swap pages for boosted reclaim. The - * intent is to relieve pressure not issue sub-optimal IO - * from reclaim context. If no pages are reclaimed, the - * reclaim will be aborted. - */ - sc.may_writepage = !laptop_mode && !nr_boost_reclaim; - sc.may_swap = !nr_boost_reclaim; - - /* - * Do some background aging of the anon list, to give - * pages a chance to be referenced before reclaiming. All - * pages are rotated regardless of classzone as this is - * about consistent aging. - */ - age_active_anon(pgdat, &sc); - - /* - * If we're getting trouble reclaiming, start doing writepage - * even in laptop mode. - */ - if (sc.priority < DEF_PRIORITY - 2) - sc.may_writepage = 1; - - /* Call soft limit reclaim before calling shrink_node. */ - sc.nr_scanned = 0; - nr_soft_scanned = 0; - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, - sc.gfp_mask, &nr_soft_scanned); - sc.nr_reclaimed += nr_soft_reclaimed; - - /* - * 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 (kswapd_shrink_node(pgdat, &sc)) - raise_priority = false; - - /* - * If the low watermark is met there is no need for processes - * to be throttled on pfmemalloc_wait as they should not be - * able to safely make forward progress. Wake them - */ - if (waitqueue_active(&pgdat->pfmemalloc_wait) && - allow_direct_reclaim(pgdat)) - wake_up_all(&pgdat->pfmemalloc_wait); - - /* Check if kswapd should be suspending */ - __fs_reclaim_release(); - ret = try_to_freeze(); - __fs_reclaim_acquire(); - if (ret || kthread_should_stop()) - break; - - /* - * Raise priority if scanning rate is too low or there was no - * progress in reclaiming pages - */ - nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; - nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); - - /* - * If reclaim made no progress for a boost, stop reclaim as - * IO cannot be queued and it could be an infinite loop in - * extreme circumstances. - */ - if (nr_boost_reclaim && !nr_reclaimed) - break; - - if (raise_priority || !nr_reclaimed) - sc.priority--; - } while (sc.priority >= 1); - - if (!sc.nr_reclaimed) - pgdat->kswapd_failures++; - -out: - /* If reclaim was boosted, account for the reclaim done in this pass */ - if (boosted) { - unsigned long flags; - - for (i = 0; i <= highest_zoneidx; i++) { - if (!zone_boosts[i]) - continue; - - /* Increments are under the zone lock */ - zone = pgdat->node_zones + i; - spin_lock_irqsave(&zone->lock, flags); - zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); - spin_unlock_irqrestore(&zone->lock, flags); - } - - /* - * As there is now likely space, wakeup kcompact to defragment - * pageblocks. - */ - wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); - } - - snapshot_refaults(NULL, pgdat); - __fs_reclaim_release(); - psi_memstall_leave(&pflags); - set_task_reclaim_state(current, NULL); - - /* - * Return the order kswapd stopped reclaiming at as - * prepare_kswapd_sleep() takes it into account. If another caller - * entered the allocator slow path while kswapd was awake, order will - * remain at the higher level. - */ - return sc.order; -} - -/* - * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to - * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is - * not a valid index then either kswapd runs for first time or kswapd couldn't - * sleep after previous reclaim attempt (node is still unbalanced). In that - * case return the zone index of the previous kswapd reclaim cycle. - */ -static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, - enum zone_type prev_highest_zoneidx) -{ - enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); - - return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; -} - -static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, - unsigned int highest_zoneidx) -{ - long remaining = 0; - DEFINE_WAIT(wait); - - if (freezing(current) || kthread_should_stop()) - return; - - prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); - - /* - * Try to sleep for a short interval. Note that kcompactd will only be - * woken if it is possible to sleep for a short interval. This is - * deliberate on the assumption that if reclaim cannot keep an - * eligible zone balanced that it's also unlikely that compaction will - * succeed. - */ - if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { - /* - * Compaction records what page blocks it recently failed to - * isolate pages from and skips them in the future scanning. - * When kswapd is going to sleep, it is reasonable to assume - * that pages and compaction may succeed so reset the cache. - */ - reset_isolation_suitable(pgdat); - - /* - * We have freed the memory, now we should compact it to make - * allocation of the requested order possible. - */ - wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); - - remaining = schedule_timeout(HZ/10); - - /* - * If woken prematurely then reset kswapd_highest_zoneidx and - * order. The values will either be from a wakeup request or - * the previous request that slept prematurely. - */ - if (remaining) { - WRITE_ONCE(pgdat->kswapd_highest_zoneidx, - kswapd_highest_zoneidx(pgdat, - highest_zoneidx)); - - if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) - WRITE_ONCE(pgdat->kswapd_order, reclaim_order); - } - - finish_wait(&pgdat->kswapd_wait, &wait); - prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); - } - - /* - * After a short sleep, check if it was a premature sleep. If not, then - * go fully to sleep until explicitly woken up. - */ - if (!remaining && - prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { - trace_mm_vmscan_kswapd_sleep(pgdat->node_id); - - /* - * vmstat counters are not perfectly accurate and the estimated - * value for counters such as NR_FREE_PAGES can deviate from the - * true value by nr_online_cpus * threshold. To avoid the zone - * watermarks being breached while under pressure, we reduce the - * per-cpu vmstat threshold while kswapd is awake and restore - * them before going back to sleep. - */ - set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - - if (!kthread_should_stop()) - schedule(); - - set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); - } else { - if (remaining) - count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); - else - count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); - } - finish_wait(&pgdat->kswapd_wait, &wait); -} - -/* - * The background pageout daemon, started as a kernel thread - * from the init process. - * - * This basically trickles out pages so that we have _some_ - * free memory available even if there is no other activity - * that frees anything up. This is needed for things like routing - * etc, where we otherwise might have all activity going on in - * asynchronous contexts that cannot page things out. - * - * If there are applications that are active memory-allocators - * (most normal use), this basically shouldn't matter. - */ -static int kswapd(void *p) -{ - unsigned int alloc_order, reclaim_order; - unsigned int highest_zoneidx = MAX_NR_ZONES - 1; - pg_data_t *pgdat = (pg_data_t*)p; - struct task_struct *tsk = current; - const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); -#ifdef CONFIG_RECLAIM_ACCT - struct reclaim_acct ra = {0}; -#endif - - if (!cpumask_empty(cpumask)) - set_cpus_allowed_ptr(tsk, cpumask); - - /* - * Tell the memory management that we're a "memory allocator", - * and that if we need more memory we should get access to it - * regardless (see "__alloc_pages()"). "kswapd" should - * never get caught in the normal page freeing logic. - * - * (Kswapd normally doesn't need memory anyway, but sometimes - * you need a small amount of memory in order to be able to - * page out something else, and this flag essentially protects - * us from recursively trying to free more memory as we're - * trying to free the first piece of memory in the first place). - */ - tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; - set_freezable(); - - WRITE_ONCE(pgdat->kswapd_order, 0); - WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); - for ( ; ; ) { - bool ret; - - alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); - highest_zoneidx = kswapd_highest_zoneidx(pgdat, - highest_zoneidx); - -kswapd_try_sleep: - kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, - highest_zoneidx); - - /* Read the new order and highest_zoneidx */ - alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); - highest_zoneidx = kswapd_highest_zoneidx(pgdat, - highest_zoneidx); - WRITE_ONCE(pgdat->kswapd_order, 0); - WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); - - ret = try_to_freeze(); - if (kthread_should_stop()) - break; - - /* - * We can speed up thawing tasks if we don't call balance_pgdat - * after returning from the refrigerator - */ - if (ret) - continue; - - /* - * Reclaim begins at the requested order but if a high-order - * reclaim fails then kswapd falls back to reclaiming for - * order-0. If that happens, kswapd will consider sleeping - * for the order it finished reclaiming at (reclaim_order) - * but kcompactd is woken to compact for the original - * request (alloc_order). - */ - trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, - alloc_order); -#ifdef CONFIG_MEMORY_MONITOR - kswapd_monitor_wake_up_queue(); -#endif -#ifdef CONFIG_RECLAIM_ACCT - reclaimacct_start(KSWAPD_RECLAIM, &ra); -#endif - reclaim_order = balance_pgdat(pgdat, alloc_order, - highest_zoneidx); -#ifdef CONFIG_RECLAIM_ACCT - reclaimacct_end(KSWAPD_RECLAIM); -#endif - if (reclaim_order < alloc_order) - goto kswapd_try_sleep; - } - - tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); - - return 0; -} - -/* - * A zone is low on free memory or too fragmented for high-order memory. If - * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's - * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim - * has failed or is not needed, still wake up kcompactd if only compaction is - * needed. - */ -void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, - enum zone_type highest_zoneidx) -{ - pg_data_t *pgdat; - enum zone_type curr_idx; - - if (!managed_zone(zone)) - return; - - if (!cpuset_zone_allowed(zone, gfp_flags)) - return; - - pgdat = zone->zone_pgdat; - curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); - - if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) - WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); - - if (READ_ONCE(pgdat->kswapd_order) < order) - WRITE_ONCE(pgdat->kswapd_order, order); - - if (!waitqueue_active(&pgdat->kswapd_wait)) - return; - - /* Hopeless node, leave it to direct reclaim if possible */ - if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || - (pgdat_balanced(pgdat, order, highest_zoneidx) && - !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { - /* - * There may be plenty of free memory available, but it's too - * fragmented for high-order allocations. Wake up kcompactd - * and rely on compaction_suitable() to determine if it's - * needed. If it fails, it will defer subsequent attempts to - * ratelimit its work. - */ - if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) - wakeup_kcompactd(pgdat, order, highest_zoneidx); - return; - } - - trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, - gfp_flags); - wake_up_interruptible(&pgdat->kswapd_wait); -} - -#ifdef CONFIG_HIBERNATION -/* - * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of - * freed pages. - * - * Rather than trying to age LRUs the aim is to preserve the overall - * LRU order by reclaiming preferentially - * inactive > active > active referenced > active mapped - */ -unsigned long shrink_all_memory(unsigned long nr_to_reclaim) -{ - struct scan_control sc = { - .nr_to_reclaim = nr_to_reclaim, - .gfp_mask = GFP_HIGHUSER_MOVABLE, - .reclaim_idx = MAX_NR_ZONES - 1, - .priority = DEF_PRIORITY, - .may_writepage = 1, - .may_unmap = 1, - .may_swap = 1, - .hibernation_mode = 1, - }; - struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); - unsigned long nr_reclaimed; - unsigned int noreclaim_flag; - - fs_reclaim_acquire(sc.gfp_mask); - noreclaim_flag = memalloc_noreclaim_save(); - set_task_reclaim_state(current, &sc.reclaim_state); - - nr_reclaimed = do_try_to_free_pages(zonelist, &sc); - - set_task_reclaim_state(current, NULL); - memalloc_noreclaim_restore(noreclaim_flag); - fs_reclaim_release(sc.gfp_mask); - - return nr_reclaimed; -} -#endif /* CONFIG_HIBERNATION */ - -/* - * This kswapd start function will be called by init and node-hot-add. - * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. - */ -int kswapd_run(int nid) -{ - pg_data_t *pgdat = NODE_DATA(nid); - int ret = 0; - - if (pgdat->kswapd) - return 0; - - pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); - if (IS_ERR(pgdat->kswapd)) { - /* failure at boot is fatal */ - BUG_ON(system_state < SYSTEM_RUNNING); - 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 mem_hotplug_begin/end(). - */ -void kswapd_stop(int nid) -{ - struct task_struct *kswapd = NODE_DATA(nid)->kswapd; - - if (kswapd) { - kthread_stop(kswapd); - NODE_DATA(nid)->kswapd = NULL; - } -} - -#ifdef CONFIG_MEM_PURGEABLE_DEBUG -static void __init purgeable_debugfs_init(void); -#endif - -static int __init kswapd_init(void) -{ - int nid; - - swap_setup(); - for_each_node_state(nid, N_MEMORY) - kswapd_run(nid); -#ifdef CONFIG_MEM_PURGEABLE_DEBUG - purgeable_debugfs_init(); -#endif - return 0; -} - -module_init(kswapd_init) - -#ifdef CONFIG_NUMA -/* - * Node reclaim mode - * - * If non-zero call node_reclaim when the number of free pages falls below - * the watermarks. - */ -int node_reclaim_mode __read_mostly; - -/* - * These bit locations are exposed in the vm.zone_reclaim_mode sysctl - * ABI. New bits are OK, but existing bits can never change. - */ -#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ -#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ -#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ - -/* - * Priority for NODE_RECLAIM. This determines the fraction of pages - * of a node considered for each zone_reclaim. 4 scans 1/16th of - * a zone. - */ -#define NODE_RECLAIM_PRIORITY 4 - -/* - * Percentage of pages in a zone that must be unmapped for node_reclaim to - * occur. - */ -int sysctl_min_unmapped_ratio = 1; - -/* - * If the number of slab pages in a zone grows beyond this percentage then - * slab reclaim needs to occur. - */ -int sysctl_min_slab_ratio = 5; - -static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) -{ - unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); - unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + - node_page_state(pgdat, NR_ACTIVE_FILE); - - /* - * It's possible for there to be more file mapped pages than - * accounted for by the pages on the file LRU lists because - * tmpfs pages accounted for as ANON can also be FILE_MAPPED - */ - return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; -} - -/* Work out how many page cache pages we can reclaim in this reclaim_mode */ -static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) -{ - unsigned long nr_pagecache_reclaimable; - unsigned long delta = 0; - - /* - * If RECLAIM_UNMAP is set, then all file pages are considered - * potentially reclaimable. Otherwise, we have to worry about - * pages like swapcache and node_unmapped_file_pages() provides - * a better estimate - */ - if (node_reclaim_mode & RECLAIM_UNMAP) - nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); - else - nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); - - /* If we can't clean pages, remove dirty pages from consideration */ - if (!(node_reclaim_mode & RECLAIM_WRITE)) - delta += node_page_state(pgdat, NR_FILE_DIRTY); - - /* Watch for any possible underflows due to delta */ - if (unlikely(delta > nr_pagecache_reclaimable)) - delta = nr_pagecache_reclaimable; - - return nr_pagecache_reclaimable - delta; -} - -/* - * Try to free up some pages from this node through reclaim. - */ -static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) -{ - /* Minimum pages needed in order to stay on node */ - const unsigned long nr_pages = 1 << order; - struct task_struct *p = current; - unsigned int noreclaim_flag; - struct scan_control sc = { - .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), - .gfp_mask = current_gfp_context(gfp_mask), - .order = order, - .priority = NODE_RECLAIM_PRIORITY, - .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), - .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), - .may_swap = 1, - .reclaim_idx = gfp_zone(gfp_mask), - }; - unsigned long pflags; - - trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, - sc.gfp_mask); - - cond_resched(); - psi_memstall_enter(&pflags); - fs_reclaim_acquire(sc.gfp_mask); - /* - * We need to be able to allocate from the reserves for RECLAIM_UNMAP - * and we also need to be able to write out pages for RECLAIM_WRITE - * and RECLAIM_UNMAP. - */ - noreclaim_flag = memalloc_noreclaim_save(); - p->flags |= PF_SWAPWRITE; - set_task_reclaim_state(p, &sc.reclaim_state); - - if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) { - /* - * Free memory by calling shrink node with increasing - * priorities until we have enough memory freed. - */ - do { -#ifdef CONFIG_HYPERHOLD_FILE_LRU - shrink_node_hyperhold(pgdat, &sc); -#else - shrink_node(pgdat, &sc); -#endif - } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); - } - - set_task_reclaim_state(p, NULL); - current->flags &= ~PF_SWAPWRITE; - memalloc_noreclaim_restore(noreclaim_flag); - fs_reclaim_release(sc.gfp_mask); - psi_memstall_leave(&pflags); - - trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); - - return sc.nr_reclaimed >= nr_pages; -} - -int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) -{ - int ret; - - /* - * Node reclaim reclaims unmapped file backed pages and - * slab pages if we are over the defined limits. - * - * A small portion of unmapped file backed pages is needed for - * file I/O otherwise pages read by file I/O will be immediately - * thrown out if the node is overallocated. So we do not reclaim - * if less than a specified percentage of the node is used by - * unmapped file backed pages. - */ - if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && - node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= - pgdat->min_slab_pages) - return NODE_RECLAIM_FULL; - - /* - * Do not scan if the allocation should not be delayed. - */ - if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) - return NODE_RECLAIM_NOSCAN; - - /* - * Only run node reclaim on the local node or on nodes that do not - * have associated processors. This will favor the local processor - * over remote processors and spread off node memory allocations - * as wide as possible. - */ - if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) - return NODE_RECLAIM_NOSCAN; - - if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) - return NODE_RECLAIM_NOSCAN; - - ret = __node_reclaim(pgdat, gfp_mask, order); - clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); - - if (!ret) - count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); - - return ret; -} -#endif - -/** - * check_move_unevictable_pages - check pages for evictability and move to - * appropriate zone lru list - * @pvec: pagevec with lru pages to check - * - * Checks pages for evictability, if an evictable page is in the unevictable - * lru list, moves it to the appropriate evictable lru list. This function - * should be only used for lru pages. - */ -void check_move_unevictable_pages(struct pagevec *pvec) -{ - struct lruvec *lruvec; - struct pglist_data *pgdat = NULL; - int pgscanned = 0; - int pgrescued = 0; - int i; - - for (i = 0; i < pvec->nr; i++) { - struct page *page = pvec->pages[i]; - struct pglist_data *pagepgdat = page_pgdat(page); - int nr_pages; - - if (PageTransTail(page)) - continue; - - nr_pages = thp_nr_pages(page); - pgscanned += nr_pages; - - if (pagepgdat != pgdat) { - if (pgdat) - spin_unlock_irq(&pgdat->lru_lock); - pgdat = pagepgdat; - spin_lock_irq(&pgdat->lru_lock); - } - lruvec = mem_cgroup_page_lruvec(page, pgdat); - - if (!PageLRU(page) || !PageUnevictable(page)) - continue; - - if (page_evictable(page)) { - enum lru_list lru = page_lru_base_type(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); - pgrescued += nr_pages; - } - } - - if (pgdat) { - __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); - __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); - spin_unlock_irq(&pgdat->lru_lock); - } -} -EXPORT_SYMBOL_GPL(check_move_unevictable_pages); - -#ifdef CONFIG_MEM_PURGEABLE_DEBUG -static unsigned long purgeable_node(pg_data_t *pgdata, struct scan_control *sc) -{ - struct mem_cgroup *memcg = NULL; - unsigned long nr = 0; -#ifdef CONFIG_MEMCG - while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))) -#endif - { - struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdata); - - shrink_list(LRU_ACTIVE_PURGEABLE, -1, lruvec, sc); - nr += shrink_list(LRU_INACTIVE_PURGEABLE, -1, lruvec, sc); - } - - pr_info("reclaim %lu purgeable pages.\n", nr); - - return nr; -} - -static int purgeable(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) -{ - struct scan_control sc = { - .gfp_mask = GFP_KERNEL, - .order = 0, - .priority = DEF_PRIORITY, - .may_deactivate = DEACTIVATE_ANON, - .may_writepage = 1, - .may_unmap = 1, - .may_swap = 1, - .reclaim_idx = MAX_NR_ZONES - 1, - }; - int nid = 0; - - for_each_node_state(nid, N_MEMORY) - purgeable_node(NODE_DATA(nid), &sc); - return 0; -} - -static struct ctl_table ker_tab[] = { - { - .procname = "purgeable", - .mode = 0200, - .proc_handler = purgeable, - }, - {}, -}; - -static struct ctl_table sys_tab[] = { - { - .procname = "kernel", - .mode = 0555, - .child = ker_tab, - }, - {}, -}; - -static struct ctl_table_header *purgeable_header; - -static void __init purgeable_debugfs_init(void) -{ - purgeable_header = register_sysctl_table(sys_tab); - if (!purgeable_header) - pr_err("register purgeable sysctl table failed.\n"); -} - -static void __exit purgeable_debugfs_exit(void) -{ - unregister_sysctl_table(purgeable_header); -} -#endif /* CONFIG_MEM_PURGEABLE_DEBUG */ -- Gitee