diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.txt new file mode 100644 index 000000000000..7e492d8aaeaf --- /dev/null +++ b/Documentation/vm/zswap.txt @@ -0,0 +1,68 @@ +Overview: + +Zswap is 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. zswap basically trades CPU cycles +for potentially reduced swap I/O.  This trade-off can also result in a +significant performance improvement if reads from the compressed cache are +faster than reads from a swap device. + +NOTE: Zswap is a new feature as of v3.11 and interacts heavily with memory +reclaim. This interaction has not be fully explored on the large set of +potential configurations and workloads that exist. For this reason, zswap +is a work in progress and should be considered experimental. + +Some potential benefits: +* Desktop/laptop users with limited RAM capacities can mitigate the +    performance impact of swapping. +* Overcommitted guests that share a common I/O resource can +    dramatically reduce their swap I/O pressure, avoiding heavy handed I/O + throttling by the hypervisor. This allows more work to get done with less + impact to the guest workload and guests sharing the I/O subsystem +* Users with SSDs as swap devices can extend the life of the device by +    drastically reducing life-shortening writes. + +Zswap evicts pages from compressed cache on an LRU basis to the backing swap +device when the compressed pool reaches it size limit. This requirement had +been identified in prior community discussions. + +To enabled zswap, the "enabled" attribute must be set to 1 at boot time. e.g. +zswap.enabled=1 + +Design: + +Zswap receives pages for compression through the Frontswap API and is able to +evict pages from its own compressed pool on an LRU basis and write them back to +the backing swap device in the case that the compressed pool is full. + +Zswap makes use of zbud for the managing the compressed memory pool. Each +allocation in zbud is not directly accessible by address. Rather, a handle is +return by the allocation routine and that handle must be mapped before being +accessed. The compressed memory pool grows on demand and shrinks as compressed +pages are freed. The pool is not preallocated. + +When a swap page is passed from frontswap to zswap, zswap maintains a mapping +of the swap entry, a combination of the swap type and swap offset, to the zbud +handle that references that compressed swap page. This mapping is achieved +with a red-black tree per swap type. The swap offset is the search key for the +tree nodes. + +During a page fault on a PTE that is a swap entry, frontswap calls the zswap +load function to decompress the page into the page allocated by the page fault +handler. + +Once there are no PTEs referencing a swap page stored in zswap (i.e. the count +in the swap_map goes to 0) the swap code calls the zswap invalidate function, +via frontswap, to free the compressed entry. + +Zswap seeks to be simple in its policies. Sysfs attributes allow for one user +controlled policies: +* max_pool_percent - The maximum percentage of memory that the compressed + pool can occupy. + +Zswap allows the compressor to be selected at kernel boot time by setting the +“compressor” attribute. The default compressor is lzo. e.g. +zswap.compressor=deflate + +A debugfs interface is provided for various statistic about pool size, number +of pages stored, and various counters for the reasons pages are rejected. diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 10062ceadd1c..0c6356255fe3 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -181,11 +181,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 7c7be7855638..8ed6cb1a900f 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -90,11 +90,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } EXPORT_SYMBOL_GPL(arch_pick_mmap_layout); diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 7e5fe2790d8a..f1baadd56e82 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -158,11 +158,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 67a42ed0d2fc..cb8bdbe4972f 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -92,10 +92,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 06bafec00278..40023290ee5b 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -91,11 +91,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } @@ -176,11 +174,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = s390_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = s390_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 2daaaa6eda23..51561b8b15ba 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -290,7 +290,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) sysctl_legacy_va_layout) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { /* We know it's 32-bit */ unsigned long task_size = STACK_TOP32; @@ -302,7 +301,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->mmap_base = PAGE_ALIGN(task_size - gap - random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/tile/mm/mmap.c b/arch/tile/mm/mmap.c index f96f4cec602a..d67d91ebf63e 100644 --- a/arch/tile/mm/mmap.c +++ b/arch/tile/mm/mmap.c @@ -66,10 +66,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (!is_32bit || rlimit(RLIMIT_STACK) == RLIM_INFINITY) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(mm); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 52ff81cce008..bae3aba95b15 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -308,8 +308,6 @@ static int load_aout_binary(struct linux_binprm *bprm) (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = TASK_UNMAPPED_BASE; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); if (retval < 0) { diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 845df6835f9f..62c29a5bfe26 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -115,10 +115,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = mmap_legacy_base(); mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index bce87694f7b0..89dec7f789a4 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -255,8 +255,6 @@ static int load_aout_binary(struct linux_binprm * bprm) (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = current->mm->mmap_base; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT); if (retval < 0) { diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index f8a0b0efda44..100edcc5e312 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -738,8 +738,6 @@ static int load_elf_binary(struct linux_binprm *bprm) /* Do this so that we can load the interpreter, if need be. We will change some of these later */ - current->mm->free_area_cache = current->mm->mmap_base; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP), executable_stack); if (retval < 0) { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ace9a5f01c64..fb425aa16c01 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -330,12 +330,9 @@ struct mm_struct { unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); - void (*unmap_area) (struct mm_struct *mm, unsigned long addr); #endif unsigned long mmap_base; /* base of mmap area */ unsigned long task_size; /* size of task vm space */ - unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ - unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f99d57e0ae47..50d04b92ceda 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -322,8 +322,6 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); -extern void arch_unmap_area(struct mm_struct *, unsigned long); -extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} #endif diff --git a/include/linux/zbud.h b/include/linux/zbud.h new file mode 100644 index 000000000000..2571a5cfa5fc --- /dev/null +++ b/include/linux/zbud.h @@ -0,0 +1,22 @@ +#ifndef _ZBUD_H_ +#define _ZBUD_H_ + +#include + +struct zbud_pool; + +struct zbud_ops { + int (*evict)(struct zbud_pool *pool, unsigned long handle); +}; + +struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops); +void zbud_destroy_pool(struct zbud_pool *pool); +int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp, + unsigned long *handle); +void zbud_free(struct zbud_pool *pool, unsigned long handle); +int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries); +void *zbud_map(struct zbud_pool *pool, unsigned long handle); +void zbud_unmap(struct zbud_pool *pool, unsigned long handle); +u64 zbud_get_pool_size(struct zbud_pool *pool); + +#endif /* _ZBUD_H_ */ diff --git a/kernel/fork.c b/kernel/fork.c index 6e6a1c11b3e5..66635c80a813 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -365,8 +365,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; mm->mmap_cache = NULL; - mm->free_area_cache = oldmm->mmap_base; - mm->cached_hole_size = ~0UL; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -540,8 +538,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm->nr_ptes = 0; memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); - mm->free_area_cache = TASK_UNMAPPED_BASE; - mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); diff --git a/mm/Kconfig b/mm/Kconfig index 7e28ecfa8aa4..8028dcc6615c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -478,6 +478,36 @@ config FRONTSWAP If unsure, say Y to enable frontswap. +config ZBUD + tristate + default n + help + A special purpose allocator for storing compressed pages. + It is designed to store up to two compressed pages per physical + page. While this design limits storage density, it has simple and + deterministic reclaim properties that make it preferable to a higher + density approach when reclaim will be used. + +config ZSWAP + bool "Compressed cache for swap pages (EXPERIMENTAL)" + depends on FRONTSWAP && CRYPTO=y + select CRYPTO_LZO + select ZBUD + default n + help + A lightweight compressed cache for swap pages. It takes + pages that are in the process of being swapped out and attempts to + compress them into a dynamically allocated RAM-based memory pool. + This can result in a significant I/O reduction on swap device and, + in the case where decompressing from RAM is faster that swap device + reads, can also improve workload performance. + + This is marked experimental because it is a new feature (as of + v3.11) that interacts heavily with memory reclaim. While these + interactions don't cause any known issues on simple memory setups, + they have not be fully explored on the large set of potential + configurations and workloads that exist. + config MEM_SOFT_DIRTY bool "Track memory changes" depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY diff --git a/mm/Makefile b/mm/Makefile index 72c5acb9345f..f00803386a67 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o obj-$(CONFIG_FRONTSWAP) += frontswap.o +obj-$(CONFIG_ZSWAP) += zswap.o obj-$(CONFIG_HAS_DMA) += dmapool.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o obj-$(CONFIG_NUMA) += mempolicy.o @@ -58,3 +59,4 @@ obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o +obj-$(CONFIG_ZBUD) += zbud.o diff --git a/mm/mmap.c b/mm/mmap.c index f81311173b4d..fbad7b091090 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1878,15 +1878,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, } #endif -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the lowest possible address? - */ - if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) - mm->free_area_cache = addr; -} - /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): @@ -1943,19 +1934,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, } #endif -void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the highest possible address? - */ - if (addr > mm->free_area_cache) - mm->free_area_cache = addr; - - /* dont allow allocations above current base */ - if (mm->free_area_cache > mm->mmap_base) - mm->free_area_cache = mm->mmap_base; -} - unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -2376,7 +2354,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, { struct vm_area_struct **insertion_point; struct vm_area_struct *tail_vma = NULL; - unsigned long addr; insertion_point = (prev ? &prev->vm_next : &mm->mmap); vma->vm_prev = NULL; @@ -2393,11 +2370,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - if (mm->unmap_area == arch_unmap_area) - addr = prev ? prev->vm_end : mm->mmap_base; - else - addr = vma ? vma->vm_start : mm->mmap_base; - mm->unmap_area(mm, addr); mm->mmap_cache = NULL; /* Kill the cache. */ } diff --git a/mm/nommu.c b/mm/nommu.c index e44e6e0a125c..ecd1f158548e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1871,10 +1871,6 @@ unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; } -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ -} - void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) diff --git a/mm/util.c b/mm/util.c index ab1424dbe2e6..7441c41d00f6 100644 --- a/mm/util.c +++ b/mm/util.c @@ -295,7 +295,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } #endif diff --git a/mm/zbud.c b/mm/zbud.c new file mode 100644 index 000000000000..9bb4710e3589 --- /dev/null +++ b/mm/zbud.c @@ -0,0 +1,527 @@ +/* + * zbud.c + * + * Copyright (C) 2013, Seth Jennings, IBM + * + * Concepts based on zcache internal zbud allocator by Dan Magenheimer. + * + * zbud is an special purpose allocator for storing compressed pages. Contrary + * to what its name may suggest, zbud is not a buddy allocator, but rather an + * allocator that "buddies" two compressed pages together in a single memory + * page. + * + * While this design limits storage density, it has simple and deterministic + * reclaim properties that make it preferable to a higher density approach when + * reclaim will be used. + * + * zbud works by storing compressed pages, or "zpages", together in pairs in a + * single memory page called a "zbud page". The first buddy is "left + * justifed" at the beginning of the zbud page, and the last buddy is "right + * justified" at the end of the zbud page. The benefit is that if either + * buddy is freed, the freed buddy space, coalesced with whatever slack space + * that existed between the buddies, results in the largest possible free region + * within the zbud page. + * + * zbud also provides an attractive lower bound on density. The ratio of zpages + * to zbud pages can not be less than 1. This ensures that zbud can never "do + * harm" by using more pages to store zpages than the uncompressed zpages would + * have used on their own. + * + * zbud pages are divided into "chunks". The size of the chunks is fixed at + * compile time and determined by NCHUNKS_ORDER below. Dividing zbud pages + * into chunks allows organizing unbuddied zbud pages into a manageable number + * of unbuddied lists according to the number of free chunks available in the + * zbud page. + * + * The zbud API differs from that of conventional allocators in that the + * allocation function, zbud_alloc(), returns an opaque handle to the user, + * not a dereferenceable pointer. The user must map the handle using + * zbud_map() in order to get a usable pointer by which to access the + * allocation data and unmap the handle with zbud_unmap() when operations + * on the allocation data are complete. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +/***************** + * Structures +*****************/ +/* + * NCHUNKS_ORDER determines the internal allocation granularity, effectively + * adjusting internal fragmentation. It also determines the number of + * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the + * allocation granularity will be in chunks of size PAGE_SIZE/64, and there + * will be 64 freelists per pool. + */ +#define NCHUNKS_ORDER 6 + +#define CHUNK_SHIFT (PAGE_SHIFT - NCHUNKS_ORDER) +#define CHUNK_SIZE (1 << CHUNK_SHIFT) +#define NCHUNKS (PAGE_SIZE >> CHUNK_SHIFT) +#define ZHDR_SIZE_ALIGNED CHUNK_SIZE + +/** + * struct zbud_pool - stores metadata for each zbud pool + * @lock: protects all pool fields and first|last_chunk fields of any + * zbud page in the pool + * @unbuddied: array of lists tracking zbud pages that only contain one buddy; + * the lists each zbud page is added to depends on the size of + * its free region. + * @buddied: list tracking the zbud pages that contain two buddies; + * these zbud pages are full + * @lru: list tracking the zbud pages in LRU order by most recently + * added buddy. + * @pages_nr: number of zbud pages in the pool. + * @ops: pointer to a structure of user defined operations specified at + * pool creation time. + * + * This structure is allocated at pool creation time and maintains metadata + * pertaining to a particular zbud pool. + */ +struct zbud_pool { + spinlock_t lock; + struct list_head unbuddied[NCHUNKS]; + struct list_head buddied; + struct list_head lru; + u64 pages_nr; + struct zbud_ops *ops; +}; + +/* + * struct zbud_header - zbud page metadata occupying the first chunk of each + * zbud page. + * @buddy: links the zbud page into the unbuddied/buddied lists in the pool + * @lru: links the zbud page into the lru list in the pool + * @first_chunks: the size of the first buddy in chunks, 0 if free + * @last_chunks: the size of the last buddy in chunks, 0 if free + */ +struct zbud_header { + struct list_head buddy; + struct list_head lru; + unsigned int first_chunks; + unsigned int last_chunks; + bool under_reclaim; +}; + +/***************** + * Helpers +*****************/ +/* Just to make the code easier to read */ +enum buddy { + FIRST, + LAST +}; + +/* Converts an allocation size in bytes to size in zbud chunks */ +static int size_to_chunks(int size) +{ + return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; +} + +#define for_each_unbuddied_list(_iter, _begin) \ + for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) + +/* Initializes the zbud header of a newly allocated zbud page */ +static struct zbud_header *init_zbud_page(struct page *page) +{ + struct zbud_header *zhdr = page_address(page); + zhdr->first_chunks = 0; + zhdr->last_chunks = 0; + INIT_LIST_HEAD(&zhdr->buddy); + INIT_LIST_HEAD(&zhdr->lru); + zhdr->under_reclaim = 0; + return zhdr; +} + +/* Resets the struct page fields and frees the page */ +static void free_zbud_page(struct zbud_header *zhdr) +{ + __free_page(virt_to_page(zhdr)); +} + +/* + * Encodes the handle of a particular buddy within a zbud page + * Pool lock should be held as this function accesses first|last_chunks + */ +static unsigned long encode_handle(struct zbud_header *zhdr, enum buddy bud) +{ + unsigned long handle; + + /* + * For now, the encoded handle is actually just the pointer to the data + * but this might not always be the case. A little information hiding. + * Add CHUNK_SIZE to the handle if it is the first allocation to jump + * over the zbud header in the first chunk. + */ + handle = (unsigned long)zhdr; + if (bud == FIRST) + /* skip over zbud header */ + handle += ZHDR_SIZE_ALIGNED; + else /* bud == LAST */ + handle += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + return handle; +} + +/* Returns the zbud page where a given handle is stored */ +static struct zbud_header *handle_to_zbud_header(unsigned long handle) +{ + return (struct zbud_header *)(handle & PAGE_MASK); +} + +/* Returns the number of free chunks in a zbud page */ +static int num_free_chunks(struct zbud_header *zhdr) +{ + /* + * Rather than branch for different situations, just use the fact that + * free buddies have a length of zero to simplify everything. -1 at the + * end for the zbud header. + */ + return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks - 1; +} + +/***************** + * API Functions +*****************/ +/** + * zbud_create_pool() - create a new zbud pool + * @gfp: gfp flags when allocating the zbud pool structure + * @ops: user-defined operations for the zbud pool + * + * Return: pointer to the new zbud pool or NULL if the metadata allocation + * failed. + */ +struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops) +{ + struct zbud_pool *pool; + int i; + + pool = kmalloc(sizeof(struct zbud_pool), gfp); + if (!pool) + return NULL; + spin_lock_init(&pool->lock); + for_each_unbuddied_list(i, 0) + INIT_LIST_HEAD(&pool->unbuddied[i]); + INIT_LIST_HEAD(&pool->buddied); + INIT_LIST_HEAD(&pool->lru); + pool->pages_nr = 0; + pool->ops = ops; + return pool; +} + +/** + * zbud_destroy_pool() - destroys an existing zbud pool + * @pool: the zbud pool to be destroyed + * + * The pool should be emptied before this function is called. + */ +void zbud_destroy_pool(struct zbud_pool *pool) +{ + kfree(pool); +} + +/** + * zbud_alloc() - allocates a region of a given size + * @pool: zbud pool from which to allocate + * @size: size in bytes of the desired allocation + * @gfp: gfp flags used if the pool needs to grow + * @handle: handle of the new allocation + * + * This function will attempt to find a free region in the pool large enough to + * satisfy the allocation request. A search of the unbuddied lists is + * performed first. If no suitable free region is found, then a new page is + * allocated and added to the pool to satisfy the request. + * + * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used + * as zbud pool pages. + * + * Return: 0 if success and handle is set, otherwise -EINVAL is the size or + * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate + * a new page. + */ +int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp, + unsigned long *handle) +{ + int chunks, i, freechunks; + struct zbud_header *zhdr = NULL; + enum buddy bud; + struct page *page; + + if (size <= 0 || gfp & __GFP_HIGHMEM) + return -EINVAL; + if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED) + return -ENOSPC; + chunks = size_to_chunks(size); + spin_lock(&pool->lock); + + /* First, try to find an unbuddied zbud page. */ + zhdr = NULL; + for_each_unbuddied_list(i, chunks) { + if (!list_empty(&pool->unbuddied[i])) { + zhdr = list_first_entry(&pool->unbuddied[i], + struct zbud_header, buddy); + list_del(&zhdr->buddy); + if (zhdr->first_chunks == 0) + bud = FIRST; + else + bud = LAST; + goto found; + } + } + + /* Couldn't find unbuddied zbud page, create new one */ + spin_unlock(&pool->lock); + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + spin_lock(&pool->lock); + pool->pages_nr++; + zhdr = init_zbud_page(page); + bud = FIRST; + +found: + if (bud == FIRST) + zhdr->first_chunks = chunks; + else + zhdr->last_chunks = chunks; + + if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0) { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* Add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + + /* Add/move zbud page to beginning of LRU */ + if (!list_empty(&zhdr->lru)) + list_del(&zhdr->lru); + list_add(&zhdr->lru, &pool->lru); + + *handle = encode_handle(zhdr, bud); + spin_unlock(&pool->lock); + + return 0; +} + +/** + * zbud_free() - frees the allocation associated with the given handle + * @pool: pool in which the allocation resided + * @handle: handle associated with the allocation returned by zbud_alloc() + * + * In the case that the zbud page in which the allocation resides is under + * reclaim, as indicated by the PG_reclaim flag being set, this function + * only sets the first|last_chunks to 0. The page is actually freed + * once both buddies are evicted (see zbud_reclaim_page() below). + */ +void zbud_free(struct zbud_pool *pool, unsigned long handle) +{ + struct zbud_header *zhdr; + int freechunks; + + spin_lock(&pool->lock); + zhdr = handle_to_zbud_header(handle); + + /* If first buddy, handle will be page aligned */ + if ((handle - ZHDR_SIZE_ALIGNED) & ~PAGE_MASK) + zhdr->last_chunks = 0; + else + zhdr->first_chunks = 0; + + if (zhdr->under_reclaim) { + /* zbud page is under reclaim, reclaim will free */ + spin_unlock(&pool->lock); + return; + } + + /* Remove from existing buddy list */ + list_del(&zhdr->buddy); + + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* zbud page is empty, free */ + list_del(&zhdr->lru); + free_zbud_page(zhdr); + pool->pages_nr--; + } else { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } + + spin_unlock(&pool->lock); +} + +#define list_tail_entry(ptr, type, member) \ + list_entry((ptr)->prev, type, member) + +/** + * zbud_reclaim_page() - evicts allocations from a pool page and frees it + * @pool: pool from which a page will attempt to be evicted + * @retires: number of pages on the LRU list for which eviction will + * be attempted before failing + * + * zbud reclaim is different from normal system reclaim in that the reclaim is + * done from the bottom, up. This is because only the bottom layer, zbud, has + * information on how the allocations are organized within each zbud page. This + * has the potential to create interesting locking situations between zbud and + * the user, however. + * + * To avoid these, this is how zbud_reclaim_page() should be called: + + * The user detects a page should be reclaimed and calls zbud_reclaim_page(). + * zbud_reclaim_page() will remove a zbud page from the pool LRU list and call + * the user-defined eviction handler with the pool and handle as arguments. + * + * If the handle can not be evicted, the eviction handler should return + * non-zero. zbud_reclaim_page() will add the zbud page back to the + * appropriate list and try the next zbud page on the LRU up to + * a user defined number of retries. + * + * If the handle is successfully evicted, the eviction handler should + * return 0 _and_ should have called zbud_free() on the handle. zbud_free() + * contains logic to delay freeing the page if the page is under reclaim, + * as indicated by the setting of the PG_reclaim flag on the underlying page. + * + * If all buddies in the zbud page are successfully evicted, then the + * zbud page can be freed. + * + * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are + * no pages to evict or an eviction handler is not registered, -EAGAIN if + * the retry limit was hit. + */ +int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) +{ + int i, ret, freechunks; + struct zbud_header *zhdr; + unsigned long first_handle = 0, last_handle = 0; + + spin_lock(&pool->lock); + if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || + retries == 0) { + spin_unlock(&pool->lock); + return -EINVAL; + } + for (i = 0; i < retries; i++) { + zhdr = list_tail_entry(&pool->lru, struct zbud_header, lru); + list_del(&zhdr->lru); + list_del(&zhdr->buddy); + /* Protect zbud page against free */ + zhdr->under_reclaim = true; + /* + * We need encode the handles before unlocking, since we can + * race with free that will set (first|last)_chunks to 0 + */ + first_handle = 0; + last_handle = 0; + if (zhdr->first_chunks) + first_handle = encode_handle(zhdr, FIRST); + if (zhdr->last_chunks) + last_handle = encode_handle(zhdr, LAST); + spin_unlock(&pool->lock); + + /* Issue the eviction callback(s) */ + if (first_handle) { + ret = pool->ops->evict(pool, first_handle); + if (ret) + goto next; + } + if (last_handle) { + ret = pool->ops->evict(pool, last_handle); + if (ret) + goto next; + } +next: + spin_lock(&pool->lock); + zhdr->under_reclaim = false; + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* + * Both buddies are now free, free the zbud page and + * return success. + */ + free_zbud_page(zhdr); + pool->pages_nr--; + spin_unlock(&pool->lock); + return 0; + } else if (zhdr->first_chunks == 0 || + zhdr->last_chunks == 0) { + /* add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + + /* add to beginning of LRU */ + list_add(&zhdr->lru, &pool->lru); + } + spin_unlock(&pool->lock); + return -EAGAIN; +} + +/** + * zbud_map() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be mapped + * + * While trivial for zbud, the mapping functions for others allocators + * implementing this allocation API could have more complex information encoded + * in the handle and could create temporary mappings to make the data + * accessible to the user. + * + * Returns: a pointer to the mapped allocation + */ +void *zbud_map(struct zbud_pool *pool, unsigned long handle) +{ + return (void *)(handle); +} + +/** + * zbud_unmap() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be unmapped + */ +void zbud_unmap(struct zbud_pool *pool, unsigned long handle) +{ +} + +/** + * zbud_get_pool_size() - gets the zbud pool size in pages + * @pool: pool whose size is being queried + * + * Returns: size in pages of the given pool. The pool lock need not be + * taken to access pages_nr. + */ +u64 zbud_get_pool_size(struct zbud_pool *pool) +{ + return pool->pages_nr; +} + +static int __init init_zbud(void) +{ + /* Make sure the zbud header will fit in one chunk */ + BUILD_BUG_ON(sizeof(struct zbud_header) > ZHDR_SIZE_ALIGNED); + pr_info("loaded\n"); + return 0; +} + +static void __exit exit_zbud(void) +{ + pr_info("unloaded\n"); +} + +module_init(init_zbud); +module_exit(exit_zbud); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Seth Jennings "); +MODULE_DESCRIPTION("Buddy Allocator for Compressed Pages"); diff --git a/mm/zswap.c b/mm/zswap.c new file mode 100644 index 000000000000..deda2b671e12 --- /dev/null +++ b/mm/zswap.c @@ -0,0 +1,943 @@ +/* + * zswap.c - zswap driver file + * + * zswap is a backend for frontswap that takes pages that are in the process + * of being swapped out and attempts to compress and store them in a + * RAM-based memory pool. This can result in a significant I/O reduction on + * the swap device and, in the case where decompressing from RAM is faster + * than reading from the swap device, can also improve workload performance. + * + * Copyright (C) 2012 Seth Jennings + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. +*/ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +/********************************* +* statistics +**********************************/ +/* Number of memory pages used by the compressed pool */ +static u64 zswap_pool_pages; +/* The number of compressed pages currently stored in zswap */ +static atomic_t zswap_stored_pages = ATOMIC_INIT(0); + +/* + * The statistics below are not protected from concurrent access for + * performance reasons so they may not be a 100% accurate. However, + * they do provide useful information on roughly how many times a + * certain event is occurring. +*/ + +/* Pool limit was hit (see zswap_max_pool_percent) */ +static u64 zswap_pool_limit_hit; +/* Pages written back when pool limit was reached */ +static u64 zswap_written_back_pages; +/* Store failed due to a reclaim failure after pool limit was reached */ +static u64 zswap_reject_reclaim_fail; +/* Compressed page was too big for the allocator to (optimally) store */ +static u64 zswap_reject_compress_poor; +/* Store failed because underlying allocator could not get memory */ +static u64 zswap_reject_alloc_fail; +/* Store failed because the entry metadata could not be allocated (rare) */ +static u64 zswap_reject_kmemcache_fail; +/* Duplicate store was encountered (rare) */ +static u64 zswap_duplicate_entry; + +/********************************* +* tunables +**********************************/ +/* Enable/disable zswap (disabled by default, fixed at boot for now) */ +static bool zswap_enabled __read_mostly; +module_param_named(enabled, zswap_enabled, bool, 0); + +/* Compressor to be used by zswap (fixed at boot for now) */ +#define ZSWAP_COMPRESSOR_DEFAULT "lzo" +static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT; +module_param_named(compressor, zswap_compressor, charp, 0); + +/* The maximum percentage of memory that the compressed pool can occupy */ +static unsigned int zswap_max_pool_percent = 20; +module_param_named(max_pool_percent, + zswap_max_pool_percent, uint, 0644); + +/********************************* +* compression functions +**********************************/ +/* per-cpu compression transforms */ +static struct crypto_comp * __percpu *zswap_comp_pcpu_tfms; + +enum comp_op { + ZSWAP_COMPOP_COMPRESS, + ZSWAP_COMPOP_DECOMPRESS +}; + +static int zswap_comp_op(enum comp_op op, const u8 *src, unsigned int slen, + u8 *dst, unsigned int *dlen) +{ + struct crypto_comp *tfm; + int ret; + + tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, get_cpu()); + switch (op) { + case ZSWAP_COMPOP_COMPRESS: + ret = crypto_comp_compress(tfm, src, slen, dst, dlen); + break; + case ZSWAP_COMPOP_DECOMPRESS: + ret = crypto_comp_decompress(tfm, src, slen, dst, dlen); + break; + default: + ret = -EINVAL; + } + + put_cpu(); + return ret; +} + +static int __init zswap_comp_init(void) +{ + if (!crypto_has_comp(zswap_compressor, 0, 0)) { + pr_info("%s compressor not available\n", zswap_compressor); + /* fall back to default compressor */ + zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT; + if (!crypto_has_comp(zswap_compressor, 0, 0)) + /* can't even load the default compressor */ + return -ENODEV; + } + pr_info("using %s compressor\n", zswap_compressor); + + /* alloc percpu transforms */ + zswap_comp_pcpu_tfms = alloc_percpu(struct crypto_comp *); + if (!zswap_comp_pcpu_tfms) + return -ENOMEM; + return 0; +} + +static void zswap_comp_exit(void) +{ + /* free percpu transforms */ + if (zswap_comp_pcpu_tfms) + free_percpu(zswap_comp_pcpu_tfms); +} + +/********************************* +* data structures +**********************************/ +/* + * struct zswap_entry + * + * This structure contains the metadata for tracking a single compressed + * page within zswap. + * + * rbnode - links the entry into red-black tree for the appropriate swap type + * refcount - the number of outstanding reference to the entry. This is needed + * to protect against premature freeing of the entry by code + * concurent calls to load, invalidate, and writeback. The lock + * for the zswap_tree structure that contains the entry must + * be held while changing the refcount. Since the lock must + * be held, there is no reason to also make refcount atomic. + * offset - the swap offset for the entry. Index into the red-black tree. + * handle - zsmalloc allocation handle that stores the compressed page data + * length - the length in bytes of the compressed page data. Needed during + * decompression + */ +struct zswap_entry { + struct rb_node rbnode; + pgoff_t offset; + int refcount; + unsigned int length; + unsigned long handle; +}; + +struct zswap_header { + swp_entry_t swpentry; +}; + +/* + * The tree lock in the zswap_tree struct protects a few things: + * - the rbtree + * - the refcount field of each entry in the tree + */ +struct zswap_tree { + struct rb_root rbroot; + spinlock_t lock; + struct zbud_pool *pool; +}; + +static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; + +/********************************* +* zswap entry functions +**********************************/ +static struct kmem_cache *zswap_entry_cache; + +static int zswap_entry_cache_create(void) +{ + zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); + return (zswap_entry_cache == NULL); +} + +static void zswap_entry_cache_destory(void) +{ + kmem_cache_destroy(zswap_entry_cache); +} + +static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp) +{ + struct zswap_entry *entry; + entry = kmem_cache_alloc(zswap_entry_cache, gfp); + if (!entry) + return NULL; + entry->refcount = 1; + return entry; +} + +static void zswap_entry_cache_free(struct zswap_entry *entry) +{ + kmem_cache_free(zswap_entry_cache, entry); +} + +/* caller must hold the tree lock */ +static void zswap_entry_get(struct zswap_entry *entry) +{ + entry->refcount++; +} + +/* caller must hold the tree lock */ +static int zswap_entry_put(struct zswap_entry *entry) +{ + entry->refcount--; + return entry->refcount; +} + +/********************************* +* rbtree functions +**********************************/ +static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset) +{ + struct rb_node *node = root->rb_node; + struct zswap_entry *entry; + + while (node) { + entry = rb_entry(node, struct zswap_entry, rbnode); + if (entry->offset > offset) + node = node->rb_left; + else if (entry->offset < offset) + node = node->rb_right; + else + return entry; + } + return NULL; +} + +/* + * In the case that a entry with the same offset is found, a pointer to + * the existing entry is stored in dupentry and the function returns -EEXIST + */ +static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry, + struct zswap_entry **dupentry) +{ + struct rb_node **link = &root->rb_node, *parent = NULL; + struct zswap_entry *myentry; + + while (*link) { + parent = *link; + myentry = rb_entry(parent, struct zswap_entry, rbnode); + if (myentry->offset > entry->offset) + link = &(*link)->rb_left; + else if (myentry->offset < entry->offset) + link = &(*link)->rb_right; + else { + *dupentry = myentry; + return -EEXIST; + } + } + rb_link_node(&entry->rbnode, parent, link); + rb_insert_color(&entry->rbnode, root); + return 0; +} + +/********************************* +* per-cpu code +**********************************/ +static DEFINE_PER_CPU(u8 *, zswap_dstmem); + +static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu) +{ + struct crypto_comp *tfm; + u8 *dst; + + switch (action) { + case CPU_UP_PREPARE: + tfm = crypto_alloc_comp(zswap_compressor, 0, 0); + if (IS_ERR(tfm)) { + pr_err("can't allocate compressor transform\n"); + return NOTIFY_BAD; + } + *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = tfm; + dst = kmalloc(PAGE_SIZE * 2, GFP_KERNEL); + if (!dst) { + pr_err("can't allocate compressor buffer\n"); + crypto_free_comp(tfm); + *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL; + return NOTIFY_BAD; + } + per_cpu(zswap_dstmem, cpu) = dst; + break; + case CPU_DEAD: + case CPU_UP_CANCELED: + tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu); + if (tfm) { + crypto_free_comp(tfm); + *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL; + } + dst = per_cpu(zswap_dstmem, cpu); + kfree(dst); + per_cpu(zswap_dstmem, cpu) = NULL; + break; + default: + break; + } + return NOTIFY_OK; +} + +static int zswap_cpu_notifier(struct notifier_block *nb, + unsigned long action, void *pcpu) +{ + unsigned long cpu = (unsigned long)pcpu; + return __zswap_cpu_notifier(action, cpu); +} + +static struct notifier_block zswap_cpu_notifier_block = { + .notifier_call = zswap_cpu_notifier +}; + +static int zswap_cpu_init(void) +{ + unsigned long cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) + if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK) + goto cleanup; + register_cpu_notifier(&zswap_cpu_notifier_block); + put_online_cpus(); + return 0; + +cleanup: + for_each_online_cpu(cpu) + __zswap_cpu_notifier(CPU_UP_CANCELED, cpu); + put_online_cpus(); + return -ENOMEM; +} + +/********************************* +* helpers +**********************************/ +static bool zswap_is_full(void) +{ + return (totalram_pages * zswap_max_pool_percent / 100 < + zswap_pool_pages); +} + +/* + * Carries out the common pattern of freeing and entry's zsmalloc allocation, + * freeing the entry itself, and decrementing the number of stored pages. + */ +static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry) +{ + zbud_free(tree->pool, entry->handle); + zswap_entry_cache_free(entry); + atomic_dec(&zswap_stored_pages); + zswap_pool_pages = zbud_get_pool_size(tree->pool); +} + +/********************************* +* writeback code +**********************************/ +/* return enum for zswap_get_swap_cache_page */ +enum zswap_get_swap_ret { + ZSWAP_SWAPCACHE_NEW, + ZSWAP_SWAPCACHE_EXIST, + ZSWAP_SWAPCACHE_NOMEM +}; + +/* + * zswap_get_swap_cache_page + * + * This is an adaption of read_swap_cache_async() + * + * This function tries to find a page with the given swap entry + * in the swapper_space address space (the swap cache). If the page + * is found, it is returned in retpage. Otherwise, a page is allocated, + * added to the swap cache, and returned in retpage. + * + * If success, the swap cache page is returned in retpage + * Returns 0 if page was already in the swap cache, page is not locked + * Returns 1 if the new page needs to be populated, page is locked + * Returns <0 on error + */ +static int zswap_get_swap_cache_page(swp_entry_t entry, + struct page **retpage) +{ + struct page *found_page, *new_page = NULL; + struct address_space *swapper_space = &swapper_spaces[swp_type(entry)]; + int err; + + *retpage = NULL; + do { + /* + * First check the swap cache. Since this is normally + * called after lookup_swap_cache() failed, re-calling + * that would confuse statistics. + */ + found_page = find_get_page(swapper_space, entry.val); + if (found_page) + break; + + /* + * Get a new page to read into from swap. + */ + if (!new_page) { + new_page = alloc_page(GFP_KERNEL); + if (!new_page) + break; /* Out of memory */ + } + + /* + * call radix_tree_preload() while we can wait. + */ + err = radix_tree_preload(GFP_KERNEL); + if (err) + break; + + /* + * Swap entry may have been freed since our caller observed it. + */ + err = swapcache_prepare(entry); + if (err == -EEXIST) { /* seems racy */ + radix_tree_preload_end(); + continue; + } + if (err) { /* swp entry is obsolete ? */ + radix_tree_preload_end(); + break; + } + + /* May fail (-ENOMEM) if radix-tree node allocation failed. */ + __set_page_locked(new_page); + SetPageSwapBacked(new_page); + err = __add_to_swap_cache(new_page, entry); + if (likely(!err)) { + radix_tree_preload_end(); + lru_cache_add_anon(new_page); + *retpage = new_page; + return ZSWAP_SWAPCACHE_NEW; + } + radix_tree_preload_end(); + ClearPageSwapBacked(new_page); + __clear_page_locked(new_page); + /* + * add_to_swap_cache() doesn't return -EEXIST, so we can safely + * clear SWAP_HAS_CACHE flag. + */ + swapcache_free(entry, NULL); + } while (err != -ENOMEM); + + if (new_page) + page_cache_release(new_page); + if (!found_page) + return ZSWAP_SWAPCACHE_NOMEM; + *retpage = found_page; + return ZSWAP_SWAPCACHE_EXIST; +} + +/* + * Attempts to free an entry by adding a page to the swap cache, + * decompressing the entry data into the page, and issuing a + * bio write to write the page back to the swap device. + * + * This can be thought of as a "resumed writeback" of the page + * to the swap device. We are basically resuming the same swap + * writeback path that was intercepted with the frontswap_store() + * in the first place. After the page has been decompressed into + * the swap cache, the compressed version stored by zswap can be + * freed. + */ +static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle) +{ + struct zswap_header *zhdr; + swp_entry_t swpentry; + struct zswap_tree *tree; + pgoff_t offset; + struct zswap_entry *entry; + struct page *page; + u8 *src, *dst; + unsigned int dlen; + int ret, refcount; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + }; + + /* extract swpentry from data */ + zhdr = zbud_map(pool, handle); + swpentry = zhdr->swpentry; /* here */ + zbud_unmap(pool, handle); + tree = zswap_trees[swp_type(swpentry)]; + offset = swp_offset(swpentry); + BUG_ON(pool != tree->pool); + + /* find and ref zswap entry */ + spin_lock(&tree->lock); + entry = zswap_rb_search(&tree->rbroot, offset); + if (!entry) { + /* entry was invalidated */ + spin_unlock(&tree->lock); + return 0; + } + zswap_entry_get(entry); + spin_unlock(&tree->lock); + BUG_ON(offset != entry->offset); + + /* try to allocate swap cache page */ + switch (zswap_get_swap_cache_page(swpentry, &page)) { + case ZSWAP_SWAPCACHE_NOMEM: /* no memory */ + ret = -ENOMEM; + goto fail; + + case ZSWAP_SWAPCACHE_EXIST: /* page is unlocked */ + /* page is already in the swap cache, ignore for now */ + page_cache_release(page); + ret = -EEXIST; + goto fail; + + case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* decompress */ + dlen = PAGE_SIZE; + src = (u8 *)zbud_map(tree->pool, entry->handle) + + sizeof(struct zswap_header); + dst = kmap_atomic(page); + ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, + entry->length, dst, &dlen); + kunmap_atomic(dst); + zbud_unmap(tree->pool, entry->handle); + BUG_ON(ret); + BUG_ON(dlen != PAGE_SIZE); + + /* page is up to date */ + SetPageUptodate(page); + } + + /* start writeback */ + __swap_writepage(page, &wbc, end_swap_bio_write); + page_cache_release(page); + zswap_written_back_pages++; + + spin_lock(&tree->lock); + + /* drop local reference */ + zswap_entry_put(entry); + /* drop the initial reference from entry creation */ + refcount = zswap_entry_put(entry); + + /* + * There are three possible values for refcount here: + * (1) refcount is 1, load is in progress, unlink from rbtree, + * load will free + * (2) refcount is 0, (normal case) entry is valid, + * remove from rbtree and free entry + * (3) refcount is -1, invalidate happened during writeback, + * free entry + */ + if (refcount >= 0) { + /* no invalidate yet, remove from rbtree */ + rb_erase(&entry->rbnode, &tree->rbroot); + } + spin_unlock(&tree->lock); + if (refcount <= 0) { + /* free the entry */ + zswap_free_entry(tree, entry); + return 0; + } + return -EAGAIN; + +fail: + spin_lock(&tree->lock); + zswap_entry_put(entry); + spin_unlock(&tree->lock); + return ret; +} + +/********************************* +* frontswap hooks +**********************************/ +/* attempts to compress and store an single page */ +static int zswap_frontswap_store(unsigned type, pgoff_t offset, + struct page *page) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry, *dupentry; + int ret; + unsigned int dlen = PAGE_SIZE, len; + unsigned long handle; + char *buf; + u8 *src, *dst; + struct zswap_header *zhdr; + + if (!tree) { + ret = -ENODEV; + goto reject; + } + + /* reclaim space if needed */ + if (zswap_is_full()) { + zswap_pool_limit_hit++; + if (zbud_reclaim_page(tree->pool, 8)) { + zswap_reject_reclaim_fail++; + ret = -ENOMEM; + goto reject; + } + } + + /* allocate entry */ + entry = zswap_entry_cache_alloc(GFP_KERNEL); + if (!entry) { + zswap_reject_kmemcache_fail++; + ret = -ENOMEM; + goto reject; + } + + /* compress */ + dst = get_cpu_var(zswap_dstmem); + src = kmap_atomic(page); + ret = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen); + kunmap_atomic(src); + if (ret) { + ret = -EINVAL; + goto freepage; + } + + /* store */ + len = dlen + sizeof(struct zswap_header); + ret = zbud_alloc(tree->pool, len, __GFP_NORETRY | __GFP_NOWARN, + &handle); + if (ret == -ENOSPC) { + zswap_reject_compress_poor++; + goto freepage; + } + if (ret) { + zswap_reject_alloc_fail++; + goto freepage; + } + zhdr = zbud_map(tree->pool, handle); + zhdr->swpentry = swp_entry(type, offset); + buf = (u8 *)(zhdr + 1); + memcpy(buf, dst, dlen); + zbud_unmap(tree->pool, handle); + put_cpu_var(zswap_dstmem); + + /* populate entry */ + entry->offset = offset; + entry->handle = handle; + entry->length = dlen; + + /* map */ + spin_lock(&tree->lock); + do { + ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry); + if (ret == -EEXIST) { + zswap_duplicate_entry++; + /* remove from rbtree */ + rb_erase(&dupentry->rbnode, &tree->rbroot); + if (!zswap_entry_put(dupentry)) { + /* free */ + zswap_free_entry(tree, dupentry); + } + } + } while (ret == -EEXIST); + spin_unlock(&tree->lock); + + /* update stats */ + atomic_inc(&zswap_stored_pages); + zswap_pool_pages = zbud_get_pool_size(tree->pool); + + return 0; + +freepage: + put_cpu_var(zswap_dstmem); + zswap_entry_cache_free(entry); +reject: + return ret; +} + +/* + * returns 0 if the page was successfully decompressed + * return -1 on entry not found or error +*/ +static int zswap_frontswap_load(unsigned type, pgoff_t offset, + struct page *page) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry; + u8 *src, *dst; + unsigned int dlen; + int refcount, ret; + + /* find */ + spin_lock(&tree->lock); + entry = zswap_rb_search(&tree->rbroot, offset); + if (!entry) { + /* entry was written back */ + spin_unlock(&tree->lock); + return -1; + } + zswap_entry_get(entry); + spin_unlock(&tree->lock); + + /* decompress */ + dlen = PAGE_SIZE; + src = (u8 *)zbud_map(tree->pool, entry->handle) + + sizeof(struct zswap_header); + dst = kmap_atomic(page); + ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length, + dst, &dlen); + kunmap_atomic(dst); + zbud_unmap(tree->pool, entry->handle); + BUG_ON(ret); + + spin_lock(&tree->lock); + refcount = zswap_entry_put(entry); + if (likely(refcount)) { + spin_unlock(&tree->lock); + return 0; + } + spin_unlock(&tree->lock); + + /* + * We don't have to unlink from the rbtree because + * zswap_writeback_entry() or zswap_frontswap_invalidate page() + * has already done this for us if we are the last reference. + */ + /* free */ + + zswap_free_entry(tree, entry); + + return 0; +} + +/* frees an entry in zswap */ +static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry; + int refcount; + + /* find */ + spin_lock(&tree->lock); + entry = zswap_rb_search(&tree->rbroot, offset); + if (!entry) { + /* entry was written back */ + spin_unlock(&tree->lock); + return; + } + + /* remove from rbtree */ + rb_erase(&entry->rbnode, &tree->rbroot); + + /* drop the initial reference from entry creation */ + refcount = zswap_entry_put(entry); + + spin_unlock(&tree->lock); + + if (refcount) { + /* writeback in progress, writeback will free */ + return; + } + + /* free */ + zswap_free_entry(tree, entry); +} + +/* frees all zswap entries for the given swap type */ +static void zswap_frontswap_invalidate_area(unsigned type) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct rb_node *node; + struct zswap_entry *entry; + + if (!tree) + return; + + /* walk the tree and free everything */ + spin_lock(&tree->lock); + /* + * TODO: Even though this code should not be executed because + * the try_to_unuse() in swapoff should have emptied the tree, + * it is very wasteful to rebalance the tree after every + * removal when we are freeing the whole tree. + * + * If post-order traversal code is ever added to the rbtree + * implementation, it should be used here. + */ + while ((node = rb_first(&tree->rbroot))) { + entry = rb_entry(node, struct zswap_entry, rbnode); + rb_erase(&entry->rbnode, &tree->rbroot); + zbud_free(tree->pool, entry->handle); + zswap_entry_cache_free(entry); + atomic_dec(&zswap_stored_pages); + } + tree->rbroot = RB_ROOT; + spin_unlock(&tree->lock); +} + +static struct zbud_ops zswap_zbud_ops = { + .evict = zswap_writeback_entry +}; + +static void zswap_frontswap_init(unsigned type) +{ + struct zswap_tree *tree; + + tree = kzalloc(sizeof(struct zswap_tree), GFP_KERNEL); + if (!tree) + goto err; + tree->pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops); + if (!tree->pool) + goto freetree; + tree->rbroot = RB_ROOT; + spin_lock_init(&tree->lock); + zswap_trees[type] = tree; + return; + +freetree: + kfree(tree); +err: + pr_err("alloc failed, zswap disabled for swap type %d\n", type); +} + +static struct frontswap_ops zswap_frontswap_ops = { + .store = zswap_frontswap_store, + .load = zswap_frontswap_load, + .invalidate_page = zswap_frontswap_invalidate_page, + .invalidate_area = zswap_frontswap_invalidate_area, + .init = zswap_frontswap_init +}; + +/********************************* +* debugfs functions +**********************************/ +#ifdef CONFIG_DEBUG_FS +#include + +static struct dentry *zswap_debugfs_root; + +static int __init zswap_debugfs_init(void) +{ + if (!debugfs_initialized()) + return -ENODEV; + + zswap_debugfs_root = debugfs_create_dir("zswap", NULL); + if (!zswap_debugfs_root) + return -ENOMEM; + + debugfs_create_u64("pool_limit_hit", S_IRUGO, + zswap_debugfs_root, &zswap_pool_limit_hit); + debugfs_create_u64("reject_reclaim_fail", S_IRUGO, + zswap_debugfs_root, &zswap_reject_reclaim_fail); + debugfs_create_u64("reject_alloc_fail", S_IRUGO, + zswap_debugfs_root, &zswap_reject_alloc_fail); + debugfs_create_u64("reject_kmemcache_fail", S_IRUGO, + zswap_debugfs_root, &zswap_reject_kmemcache_fail); + debugfs_create_u64("reject_compress_poor", S_IRUGO, + zswap_debugfs_root, &zswap_reject_compress_poor); + debugfs_create_u64("written_back_pages", S_IRUGO, + zswap_debugfs_root, &zswap_written_back_pages); + debugfs_create_u64("duplicate_entry", S_IRUGO, + zswap_debugfs_root, &zswap_duplicate_entry); + debugfs_create_u64("pool_pages", S_IRUGO, + zswap_debugfs_root, &zswap_pool_pages); + debugfs_create_atomic_t("stored_pages", S_IRUGO, + zswap_debugfs_root, &zswap_stored_pages); + + return 0; +} + +static void __exit zswap_debugfs_exit(void) +{ + debugfs_remove_recursive(zswap_debugfs_root); +} +#else +static int __init zswap_debugfs_init(void) +{ + return 0; +} + +static void __exit zswap_debugfs_exit(void) { } +#endif + +/********************************* +* module init and exit +**********************************/ +static int __init init_zswap(void) +{ + if (!zswap_enabled) + return 0; + + pr_info("loading zswap\n"); + if (zswap_entry_cache_create()) { + pr_err("entry cache creation failed\n"); + goto error; + } + if (zswap_comp_init()) { + pr_err("compressor initialization failed\n"); + goto compfail; + } + if (zswap_cpu_init()) { + pr_err("per-cpu initialization failed\n"); + goto pcpufail; + } + frontswap_register_ops(&zswap_frontswap_ops); + if (zswap_debugfs_init()) + pr_warn("debugfs initialization failed\n"); + return 0; +pcpufail: + zswap_comp_exit(); +compfail: + zswap_entry_cache_destory(); +error: + return -ENOMEM; +} +/* must be late so crypto has time to come up */ +late_initcall(init_zswap); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Seth Jennings "); +MODULE_DESCRIPTION("Compressed cache for swap pages");