diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 25 | ||||
-rw-r--r-- | mm/Makefile | 2 | ||||
-rw-r--r-- | mm/cleancache.c | 7 | ||||
-rw-r--r-- | mm/madvise.c | 3 | ||||
-rw-r--r-- | mm/memory.c | 17 | ||||
-rw-r--r-- | mm/mempolicy.c | 5 | ||||
-rw-r--r-- | mm/mlock.c | 3 | ||||
-rw-r--r-- | mm/mmap.c | 44 | ||||
-rw-r--r-- | mm/mprotect.c | 3 | ||||
-rw-r--r-- | mm/oom_kill.c | 22 | ||||
-rw-r--r-- | mm/page_io.c | 46 | ||||
-rw-r--r-- | mm/shmem.c | 9 | ||||
-rw-r--r-- | mm/swapfile.c | 193 | ||||
-rw-r--r-- | mm/vmscan.c | 90 | ||||
-rw-r--r-- | mm/zsmalloc.c | 1148 |
15 files changed, 1341 insertions, 276 deletions
@@ -371,6 +371,31 @@ config CLEANCACHE If unsure, say Y to enable cleancache +config ZSMALLOC + bool "Memory allocator for compressed pages" + depends on MMU + default n + help + zsmalloc is a slab-based memory allocator designed to store + compressed RAM pages. zsmalloc uses virtual memory mapping + in order to reduce fragmentation. However, this results in a + non-standard allocator interface where a handle, not a pointer, is + returned by an alloc(). This handle must be mapped in order to + access the allocated space. + +config PGTABLE_MAPPING + bool "Use page table mapping to access object in zsmalloc" + depends on ZSMALLOC + help + By default, zsmalloc uses a copy-based object mapping method to + access allocations that span two pages. However, if a particular + architecture (ex, ARM) performs VM mapping faster than copying, + then you should select this. This causes zsmalloc to use page table + mapping rather than copying for object mapping. + + You can check speed with zsmalloc benchmark[1]. + [1] https://github.com/spartacus06/zsmalloc + config CMA bool "Contiguous Memory Allocator framework" # Currently there is only one allocator so force it on diff --git a/mm/Makefile b/mm/Makefile index 9b994ce..47ebf93 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -78,5 +78,7 @@ obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o obj-$(CONFIG_CLEANCACHE) += cleancache.o +obj-$(CONFIG_ZSMALLOC) += zsmalloc.o + obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_CMA_BEST_FIT) += cma-best-fit.o diff --git a/mm/cleancache.c b/mm/cleancache.c index bcaae4c..83a8241 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -160,7 +160,8 @@ void __cleancache_flush_page(struct address_space *mapping, struct page *page) if (pool_id >= 0) { VM_BUG_ON(!PageLocked(page)); if (cleancache_get_key(mapping->host, &key) >= 0) { - (*cleancache_ops.flush_page)(pool_id, key, page->index); + (*cleancache_ops.invalidate_page)(pool_id, + key, page->index); cleancache_flushes++; } } @@ -178,7 +179,7 @@ void __cleancache_flush_inode(struct address_space *mapping) struct cleancache_filekey key = { .u.key = { 0 } }; if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0) - (*cleancache_ops.flush_inode)(pool_id, key); + (*cleancache_ops.invalidate_inode)(pool_id, key); } EXPORT_SYMBOL(__cleancache_flush_inode); @@ -192,7 +193,7 @@ void __cleancache_flush_fs(struct super_block *sb) if (sb->cleancache_poolid >= 0) { int old_poolid = sb->cleancache_poolid; sb->cleancache_poolid = -1; - (*cleancache_ops.flush_fs)(old_poolid); + (*cleancache_ops.invalidate_fs)(old_poolid); } } EXPORT_SYMBOL(__cleancache_flush_fs); diff --git a/mm/madvise.c b/mm/madvise.c index deabe5f6..5a273af 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -87,7 +87,8 @@ static long madvise_behavior(struct vm_area_struct * vma, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, - vma->vm_file, pgoff, vma_policy(vma)); + vma->vm_file, pgoff, vma_policy(vma), + vma_get_anon_name(vma)); if (*prev) { vma = *prev; goto success; diff --git a/mm/memory.c b/mm/memory.c index 5331e67..29c8112 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1436,6 +1436,16 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(zap_vma_ptes); +/* + * FOLL_FORCE can write to even unwritable pte's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +{ + return pte_write(pte) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); +} + /** * follow_page - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address @@ -1518,7 +1528,7 @@ split_fallthrough: pte = *ptep; if (!pte_present(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !pte_write(pte)) + if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) goto unlock; page = vm_normal_page(vma, address, pte); @@ -1832,7 +1842,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, */ if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) - foll_flags &= ~FOLL_WRITE; + foll_flags |= FOLL_COW; cond_resched(); } @@ -3140,7 +3150,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, mem_cgroup_commit_charge_swapin(page, ptr); swap_free(entry); - if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) + if ((PageSwapCache(page) && vm_swap_full(page_swap_info(page))) || + (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (swapcache) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 7065fb3..7c8caa9 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -664,8 +664,9 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, vmend = min(end, vma->vm_end); pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, new_pol); + prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, + new_pol, vma_get_anon_name(name)); if (prev) { vma = prev; next = vma->vm_next; @@ -321,7 +321,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, - vma->vm_file, pgoff, vma_policy(vma)); + vma->vm_file, pgoff, vma_policy(vma), + vma_get_anon_name(vma)); if (*prev) { vma = *prev; goto success; @@ -656,7 +656,8 @@ again: remove_next = 1 + (end > next->vm_end); * per-vma resources, so we don't attempt to merge those. */ static inline int is_mergeable_vma(struct vm_area_struct *vma, - struct file *file, unsigned long vm_flags) + struct file *file, unsigned long vm_flags, + const char __user *anon_name) { /* VM_CAN_NONLINEAR may get set later by f_op->mmap() */ if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR) @@ -665,6 +666,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, return 0; if (vma->vm_ops && vma->vm_ops->close) return 0; + if (vma_get_anon_name(vma) != anon_name) + return 0; return 1; } @@ -695,9 +698,10 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, */ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, - struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff) + struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, + const char __user *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags) && + if (is_mergeable_vma(vma, file, vm_flags, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; @@ -714,9 +718,10 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, */ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, - struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff) + struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, + const char __user *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags) && + if (is_mergeable_vma(vma, file, vm_flags, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; @@ -727,9 +732,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, } /* - * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out - * whether that can be merged with its predecessor or its successor. - * Or both (it neatly fills a hole). + * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), + * figure out whether that can be merged with its predecessor or its + * successor. Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when @@ -759,7 +764,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, - pgoff_t pgoff, struct mempolicy *policy) + pgoff_t pgoff, struct mempolicy *policy, + const char __user *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -785,15 +791,15 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, */ if (prev && prev->vm_end == addr && mpol_equal(vma_policy(prev), policy) && - can_vma_merge_after(prev, vm_flags, - anon_vma, file, pgoff)) { + can_vma_merge_after(prev, vm_flags, anon_vma, + file, pgoff, anon_name)) { /* * OK, it can. Can we now merge in the successor as well? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && - can_vma_merge_before(next, vm_flags, - anon_vma, file, pgoff+pglen) && + can_vma_merge_before(next, vm_flags, anon_vma, + file, pgoff+pglen, anon_name) && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ @@ -813,8 +819,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && - can_vma_merge_before(next, vm_flags, - anon_vma, file, pgoff+pglen)) { + can_vma_merge_before(next, vm_flags, anon_vma, + file, pgoff+pglen, anon_name)) { if (prev && addr < prev->vm_end) /* case 4 */ err = vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL); @@ -1251,7 +1257,8 @@ munmap_back: /* * Can we just expand an old mapping? */ - vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL); + vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, + NULL, NULL); if (vma) goto out; @@ -2202,7 +2209,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, - NULL, NULL, pgoff, NULL); + NULL, NULL, pgoff, NULL, NULL); if (vma) goto out; @@ -2340,7 +2347,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent); new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma)); + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), + vma_get_anon_name(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mprotect.c b/mm/mprotect.c index 5a688a2..5f168eb 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -179,7 +179,8 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, */ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *pprev = vma_merge(mm, *pprev, start, end, newflags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma)); + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), + vma_get_anon_name(vma)); if (*pprev) { vma = *pprev; goto success; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 7c72487..678cf2b 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -38,6 +38,28 @@ int sysctl_oom_kill_allocating_task; int sysctl_oom_dump_tasks = 1; static DEFINE_SPINLOCK(zone_scan_lock); +/* + * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj + * @old_val: old oom_score_adj for compare + * @new_val: new oom_score_adj for swap + * + * Sets the oom_score_adj value for current to @new_val iff its present value is + * @old_val. Usually used to reinstate a previous value to prevent racing with + * userspacing tuning the value in the interim. + */ +void compare_swap_oom_score_adj(int old_val, int new_val) +{ + struct sighand_struct *sighand = current->sighand; + + spin_lock_irq(&sighand->siglock); + if (current->signal->oom_score_adj == old_val) { + current->signal->oom_score_adj = new_val; + delete_from_adj_tree(current); + add_2_adj_tree(current); + } + spin_unlock_irq(&sighand->siglock); +} + /** * test_set_oom_score_adj() - set current's oom_score_adj and return old value * @new_val: new oom_score_adj value diff --git a/mm/page_io.c b/mm/page_io.c index dc76b4d..f57da45 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -18,6 +18,8 @@ #include <linux/bio.h> #include <linux/swapops.h> #include <linux/writeback.h> +#include <linux/aio.h> +#include <linux/blkdev.h> #include <asm/pgtable.h> static struct bio *get_swap_bio(gfp_t gfp_flags, @@ -78,9 +80,49 @@ void end_swap_bio_read(struct bio *bio, int err) imajor(bio->bi_bdev->bd_inode), iminor(bio->bi_bdev->bd_inode), (unsigned long long)bio->bi_sector); - } else { - SetPageUptodate(page); + goto out; + } + + SetPageUptodate(page); + + /* + * There is no guarantee that the page is in swap cache - the software + * suspend code (at least) uses end_swap_bio_read() against a non- + * swapcache page. So we must check PG_swapcache before proceeding with + * this optimization. + */ + if (likely(PageSwapCache(page))) { + /* + * The swap subsystem performs lazy swap slot freeing, + * expecting that the page will be swapped out again. + * So we can avoid an unnecessary write if the page + * isn't redirtied. + * This is good for real swap storage because we can + * reduce unnecessary I/O and enhance wear-leveling + * if an SSD is used as the as swap device. + * But if in-memory swap device (eg zram) is used, + * this causes a duplicated copy between uncompressed + * data in VM-owned memory and compressed data in + * zram-owned memory. So let's free zram-owned memory + * and make the VM-owned decompressed page *dirty*, + * so the page should be swapped out somewhere again if + * we again wish to reclaim it. + */ + struct gendisk *disk = bio->bi_bdev->bd_disk; + if (disk->fops->swap_slot_free_notify) { + swp_entry_t entry; + unsigned long offset; + + entry.val = page_private(page); + offset = swp_offset(entry); + + SetPageDirty(page); + disk->fops->swap_slot_free_notify(bio->bi_bdev, + offset); + } } + +out: unlock_page(page); bio_put(bio); } @@ -1060,17 +1060,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; -#ifdef CONFIG_ZRAM_FOR_ANDROID - /* - * Modification for compcache - * shmem_writepage can be reason of kernel panic when using swap. - * This modification prevent using swap by shmem. - */ - goto redirty; -#else if (!total_swap_pages) goto redirty; -#endif /* * shmem_backing_dev_info's capabilities prevent regular writeback or diff --git a/mm/swapfile.c b/mm/swapfile.c index 3e5a3a7..4add436 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -69,6 +69,26 @@ static inline unsigned char swap_count(unsigned char ent) return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */ } +bool is_swap_fast(swp_entry_t entry) +{ + struct swap_info_struct *p; + unsigned long type; + + if (non_swap_entry(entry)) + return false; + + type = swp_type(entry); + if (type >= nr_swapfiles) + return false; + + p = swap_info[type]; + + if (p->flags & SWP_FAST) + return true; + + return false; +} + /* returns 1 if swap entry is freed */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) @@ -289,7 +309,7 @@ checks: scan_base = offset = si->lowest_bit; /* reuse swap entry of cache-only swap if not busy. */ - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + if (vm_swap_full(si) && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; spin_unlock(&swap_lock); swap_was_freed = __try_to_reclaim_swap(si, offset); @@ -378,7 +398,8 @@ scan: spin_lock(&swap_lock); goto checks; } - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + if (vm_swap_full(si) && + si->swap_map[offset] == SWAP_HAS_CACHE) { spin_lock(&swap_lock); goto checks; } @@ -393,7 +414,8 @@ scan: spin_lock(&swap_lock); goto checks; } - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + if (vm_swap_full(si) && + si->swap_map[offset] == SWAP_HAS_CACHE) { spin_lock(&swap_lock); goto checks; } @@ -708,7 +730,8 @@ int free_swap_and_cache(swp_entry_t entry) * Also recheck PageSwapCache now page is locked (above). */ if (PageSwapCache(page) && !PageWriteback(page) && - (!page_mapped(page) || vm_swap_full())) { + (!page_mapped(page) || + vm_swap_full(page_swap_info(page)))) { delete_from_swap_cache(page); SetPageDirty(page); } @@ -2012,159 +2035,6 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, return nr_extents; } -#ifdef CONFIG_ZRAM_FOR_ANDROID -int swapon(char *name, int swap_flags) -{ - struct swap_info_struct *p; - - struct file *swap_file = NULL; - struct address_space *mapping; - int i; - int prio; - int error; - union swap_header *swap_header; - int nr_extents; - sector_t span; - unsigned long maxpages; - unsigned char *swap_map = NULL; - struct page *page = NULL; - struct inode *inode = NULL; - - p = alloc_swap_info(); - if (IS_ERR(p)) - return PTR_ERR(p); - - swap_file = filp_open(name, O_RDWR | O_LARGEFILE, 0); - if (IS_ERR(swap_file)) { - error = PTR_ERR(swap_file); - swap_file = NULL; - printk("zfqin, filp_open failed\n"); - goto bad_swap; - } - - printk("zfqin, filp_open succeeded\n"); - p->swap_file = swap_file; - mapping = swap_file->f_mapping; - - for (i = 0; i < nr_swapfiles; i++) { - struct swap_info_struct *q = swap_info[i]; - - if (q == p || !q->swap_file) - continue; - if (mapping == q->swap_file->f_mapping) { - error = -EBUSY; - goto bad_swap; - } - } - - inode = mapping->host; - /* If S_ISREG(inode->i_mode) will do mutex_lock(&inode->i_mutex); */ - error = claim_swapfile(p, inode); - if (unlikely(error)) - goto bad_swap; - - /* - * Read the swap header. - */ - if (!mapping->a_ops->readpage) { - error = -EINVAL; - goto bad_swap; - } - page = read_mapping_page(mapping, 0, swap_file); - if (IS_ERR(page)) { - error = PTR_ERR(page); - goto bad_swap; - } - swap_header = kmap(page); - - maxpages = read_swap_header(p, swap_header, inode); - if (unlikely(!maxpages)) { - error = -EINVAL; - goto bad_swap; - } - - /* OK, set up the swap map and apply the bad block list */ - swap_map = vzalloc(maxpages); - if (!swap_map) { - error = -ENOMEM; - goto bad_swap; - } - - error = swap_cgroup_swapon(p->type, maxpages); - if (error) - goto bad_swap; - - nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, - maxpages, &span); - if (unlikely(nr_extents < 0)) { - error = nr_extents; - goto bad_swap; - } - - if (p->bdev) { - if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { - p->flags |= SWP_SOLIDSTATE; - p->cluster_next = 1 + (random32() % p->highest_bit); - } - if (discard_swap(p) == 0 && (swap_flags & SWAP_FLAG_DISCARD)) - p->flags |= SWP_DISCARDABLE; - } - - mutex_lock(&swapon_mutex); - prio = -1; - if (swap_flags & SWAP_FLAG_PREFER) - prio = - (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; - enable_swap_info(p, prio, swap_map); - - printk(KERN_INFO "Adding %uk swap on %s. " - "Priority:%d extents:%d across:%lluk %s%s\n", - p->pages << (PAGE_SHIFT - 10), name, p->prio, - nr_extents, (unsigned long long)span << (PAGE_SHIFT - 10), - (p->flags & SWP_SOLIDSTATE) ? "SS" : "", - (p->flags & SWP_DISCARDABLE) ? "D" : ""); - - mutex_unlock(&swapon_mutex); - atomic_inc(&proc_poll_event); - wake_up_interruptible(&proc_poll_wait); - - if (S_ISREG(inode->i_mode)) - inode->i_flags |= S_SWAPFILE; - error = 0; - goto out; - bad_swap: - if (inode && S_ISBLK(inode->i_mode) && p->bdev) { - set_blocksize(p->bdev, p->old_block_size); - blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); - } - destroy_swap_extents(p); - swap_cgroup_swapoff(p->type); - spin_lock(&swap_lock); - p->swap_file = NULL; - p->flags = 0; - spin_unlock(&swap_lock); - vfree(swap_map); - if (swap_file) { - if (inode && S_ISREG(inode->i_mode)) { - mutex_unlock(&inode->i_mutex); - inode = NULL; - } - filp_close(swap_file, NULL); - } - out: - if (page && !IS_ERR(page)) { - kunmap(page); - page_cache_release(page); - } - - if (inode && S_ISREG(inode->i_mode)) - mutex_unlock(&inode->i_mutex); - return error; -} - -EXPORT_SYMBOL(swapon); -#endif /* CONFIG_ZRAM_FOR_ANDROID */ - SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; @@ -2267,6 +2137,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } if (discard_swap(p) == 0 && (swap_flags & SWAP_FLAG_DISCARD)) p->flags |= SWP_DISCARDABLE; + if (blk_queue_fast(bdev_get_queue(p->bdev))) + p->flags |= SWP_FAST; } mutex_lock(&swapon_mutex); @@ -2449,6 +2321,13 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +struct swap_info_struct *page_swap_info(struct page *page) +{ + swp_entry_t swap = { .val = page_private(page) }; + BUG_ON(!PageSwapCache(page)); + return swap_info[swp_type(swap)]; +} + /* * swap_lock prevents swap_map being freed. Don't grab an extra * reference on the swaphandle, it doesn't matter if it becomes unused. diff --git a/mm/vmscan.c b/mm/vmscan.c index b0d3366..ce6e2e5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -624,6 +624,10 @@ void putback_lru_page(struct page *page) int was_unevictable = PageUnevictable(page); VM_BUG_ON(PageLRU(page)); +#ifdef CONFIG_CLEANCACHE + if (active) + SetPageWasActive(page); +#endif redo: ClearPageUnevictable(page); @@ -771,9 +775,6 @@ static noinline_for_stack void free_page_list(struct list_head *free_pages) /* * shrink_page_list() returns the number of reclaimed pages */ -#ifndef CONFIG_ZRAM_FOR_ANDROID -static -#endif /* CONFIG_ZRAM_FOR_ANDROID */ unsigned long shrink_page_list(struct list_head *page_list, struct zone *zone, struct scan_control *sc) @@ -989,7 +990,7 @@ cull_mlocked: activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ - if (PageSwapCache(page) && vm_swap_full()) + if (PageSwapCache(page) && vm_swap_full(page_swap_info(page))) try_to_free_swap(page); VM_BUG_ON(PageActive(page)); SetPageActive(page); @@ -1281,9 +1282,6 @@ static unsigned long isolate_pages_global(unsigned long nr, * clear_active_flags() is a helper for shrink_active_list(), clearing * any active bits from the pages in the list. */ -#ifndef CONFIG_ZRAM_FOR_ANDROID -static -#endif /* CONFIG_ZRAM_FOR_ANDROID */ unsigned long clear_active_flags(struct list_head *page_list, unsigned int *count) { @@ -1297,6 +1295,9 @@ unsigned long clear_active_flags(struct list_head *page_list, if (PageActive(page)) { lru += LRU_ACTIVE; ClearPageActive(page); +#ifdef CONFIG_CLEANCACHE + SetPageWasActive(page); +#endif nr_active += numpages; } if (count) @@ -1354,40 +1355,6 @@ int isolate_lru_page(struct page *page) return ret; } -#ifdef CONFIG_ZRAM_FOR_ANDROID -/** - * isolate_lru_page_compcache - tries to isolate a page for compcache - * @page: page to isolate from its LRU list - * - * Isolates a @page from an LRU list, clears PageLRU,but - * does not adjusts the vmstat statistic - * Returns 0 if the page was removed from an LRU list. - * Returns -EBUSY if the page was not on an LRU list. - */ -int isolate_lru_page_compcache(struct page *page) -{ - int ret = -EBUSY; - - VM_BUG_ON(!page_count(page)); - - if (PageLRU(page)) { - struct zone *zone = page_zone(page); - - spin_lock_irq(&zone->lru_lock); - if (PageLRU(page)) { - int lru = page_lru(page); - ret = 0; - get_page(page); - ClearPageLRU(page); - list_del(&page->lru); - mem_cgroup_del_lru_list(page, lru); - } - spin_unlock_irq(&zone->lru_lock); - } - return ret; -} -#endif - /* * Are there way too many processes in the direct reclaim path already? */ @@ -1624,44 +1591,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, return nr_reclaimed; } -#ifdef CONFIG_ZRAM_FOR_ANDROID -unsigned long -zone_id_shrink_pagelist(struct zone *zone, struct list_head *page_list) -{ - unsigned long nr_reclaimed = 0; - unsigned long nr_anon; - unsigned long nr_file; - - struct scan_control sc = { - .gfp_mask = GFP_USER, - .may_writepage = 1, - .nr_to_reclaim = SWAP_CLUSTER_MAX, - .may_unmap = 1, - .may_swap = 1, - .swappiness = vm_swappiness, - .order = 0, - .mem_cgroup = NULL, - .nodemask = NULL, - }; - - spin_lock_irq(&zone->lru_lock); - - update_isolated_counts(zone, &sc, &nr_anon, &nr_file, page_list); - - spin_unlock_irq(&zone->lru_lock); - - nr_reclaimed = shrink_page_list(page_list, zone, &sc); - - __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed); - - putback_lru_pages(zone, &sc, nr_anon, nr_file, page_list); - - return nr_reclaimed; -} - -EXPORT_SYMBOL(zone_id_shrink_pagelist); -#endif /* CONFIG_ZRAM_FOR_ANDROID */ - /* * This moves pages from the active list to the inactive list. * @@ -1790,6 +1719,9 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, } ClearPageActive(page); /* we are de-activating */ +#ifdef CONFIG_CLEANCACHE + SetPageWasActive(page); +#endif list_add(&page->lru, &l_inactive); } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c new file mode 100644 index 0000000..5e17643 --- /dev/null +++ b/mm/zsmalloc.c @@ -0,0 +1,1148 @@ +/* + * zsmalloc memory allocator + * + * Copyright (C) 2011 Nitin Gupta + * Copyright (C) 2012, 2013 Minchan Kim + * + * This code is released using a dual license strategy: BSD/GPL + * You can choose the license that better fits your requirements. + * + * Released under the terms of 3-clause BSD License + * Released under the terms of GNU General Public License Version 2.0 + */ + +/* + * This allocator is designed for use with zram. Thus, the allocator is + * supposed to work well under low memory conditions. In particular, it + * never attempts higher order page allocation which is very likely to + * fail under memory pressure. On the other hand, if we just use single + * (0-order) pages, it would suffer from very high fragmentation -- + * any object of size PAGE_SIZE/2 or larger would occupy an entire page. + * This was one of the major issues with its predecessor (xvmalloc). + * + * To overcome these issues, zsmalloc allocates a bunch of 0-order pages + * and links them together using various 'struct page' fields. These linked + * pages act as a single higher-order page i.e. an object can span 0-order + * page boundaries. The code refers to these linked pages as a single entity + * called zspage. + * + * For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE + * since this satisfies the requirements of all its current users (in the + * worst case, page is incompressible and is thus stored "as-is" i.e. in + * uncompressed form). For allocation requests larger than this size, failure + * is returned (see zs_malloc). + * + * Additionally, zs_malloc() does not return a dereferenceable pointer. + * Instead, it returns an opaque handle (unsigned long) which encodes actual + * location of the allocated object. The reason for this indirection is that + * zsmalloc does not keep zspages permanently mapped since that would cause + * issues on 32-bit systems where the VA region for kernel space mappings + * is very small. So, before using the allocating memory, the object has to + * be mapped using zs_map_object() to get a usable pointer and subsequently + * unmapped using zs_unmap_object(). + * + * Following is how we use various fields and flags of underlying + * struct page(s) to form a zspage. + * + * Usage of struct page fields: + * page->first_page: points to the first component (0-order) page + * page->index (union with page->freelist): offset of the first object + * starting in this page. For the first page, this is + * always 0, so we use this field (aka freelist) to point + * to the first free object in zspage. + * page->lru: links together all component pages (except the first page) + * of a zspage + * + * For _first_ page only: + * + * page->private (union with page->first_page): refers to the + * component page after the first page + * page->freelist: points to the first free object in zspage. + * Free objects are linked together using in-place + * metadata. + * page->objects: maximum number of objects we can store in this + * zspage (class->zspage_order * PAGE_SIZE / class->size) + * page->lru: links together first pages of various zspages. + * Basically forming list of zspages in a fullness group. + * page->mapping: class index and fullness group of the zspage + * + * Usage of struct page flags: + * PG_private: identifies the first component page + * PG_private2: identifies the last component page + * + */ + +#ifdef CONFIG_ZSMALLOC_DEBUG +#define DEBUG +#endif + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/errno.h> +#include <linux/highmem.h> +#include <linux/init.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <asm/tlbflush.h> +#include <asm/pgtable.h> +#include <linux/cpumask.h> +#include <linux/cpu.h> +#include <linux/vmalloc.h> +#include <linux/hardirq.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/zsmalloc.h> + +/* + * This must be power of 2 and greater than of equal to sizeof(link_free). + * These two conditions ensure that any 'struct link_free' itself doesn't + * span more than 1 page which avoids complex case of mapping 2 pages simply + * to restore link_free pointer values. + */ +#define ZS_ALIGN 8 + +/* + * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single) + * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N. + */ +#define ZS_MAX_ZSPAGE_ORDER 2 +#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) + +/* + * Object location (<PFN>, <obj_idx>) is encoded as + * as single (unsigned long) handle value. + * + * Note that object index <obj_idx> is relative to system + * page <PFN> it is stored in, so for each sub-page belonging + * to a zspage, obj_idx starts with 0. + * + * This is made more complicated by various memory models and PAE. + */ + +#ifndef MAX_PHYSMEM_BITS +#ifdef CONFIG_HIGHMEM64G +#define MAX_PHYSMEM_BITS 36 +#else /* !CONFIG_HIGHMEM64G */ +/* + * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just + * be PAGE_SHIFT + */ +#define MAX_PHYSMEM_BITS BITS_PER_LONG +#endif +#endif +#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS) +#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) + +#define MAX(a, b) ((a) >= (b) ? (a) : (b)) +/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ +#define ZS_MIN_ALLOC_SIZE \ + MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) +#define ZS_MAX_ALLOC_SIZE PAGE_SIZE + +/* + * On systems with 4K page size, this gives 254 size classes! There is a + * trader-off here: + * - Large number of size classes is potentially wasteful as free page are + * spread across these classes + * - Small number of size classes causes large internal fragmentation + * - Probably its better to use specific size classes (empirically + * determined). NOTE: all those class sizes must be set as multiple of + * ZS_ALIGN to make sure link_free itself never has to span 2 pages. + * + * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN + * (reason above) + */ +#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8) +#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \ + ZS_SIZE_CLASS_DELTA + 1) + +/* + * We do not maintain any list for completely empty or full pages + */ +enum fullness_group { + ZS_ALMOST_FULL, + ZS_ALMOST_EMPTY, + _ZS_NR_FULLNESS_GROUPS, + + ZS_EMPTY, + ZS_FULL +}; + +/* + * We assign a page to ZS_ALMOST_EMPTY fullness group when: + * n <= N / f, where + * n = number of allocated objects + * N = total number of objects zspage can store + * f = 1/fullness_threshold_frac + * + * Similarly, we assign zspage to: + * ZS_ALMOST_FULL when n > N / f + * ZS_EMPTY when n == 0 + * ZS_FULL when n == N + * + * (see: fix_fullness_group()) + */ +static const int fullness_threshold_frac = 4; + +struct size_class { + /* + * Size of objects stored in this class. Must be multiple + * of ZS_ALIGN. + */ + int size; + unsigned int index; + + /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ + int pages_per_zspage; + + spinlock_t lock; + + struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS]; +}; + +/* + * Placed within free objects to form a singly linked list. + * For every zspage, first_page->freelist gives head of this list. + * + * This must be power of 2 and less than or equal to ZS_ALIGN + */ +struct link_free { + /* Handle of next free chunk (encodes <PFN, obj_idx>) */ + void *next; +}; + +struct zs_pool { + struct size_class *size_class[ZS_SIZE_CLASSES]; + + gfp_t flags; /* allocation flags used when growing pool */ + atomic_long_t pages_allocated; +}; + +/* + * A zspage's class index and fullness group + * are encoded in its (first)page->mapping + */ +#define CLASS_IDX_BITS 28 +#define FULLNESS_BITS 4 +#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1) +#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1) + +struct mapping_area { +#ifdef CONFIG_PGTABLE_MAPPING + struct vm_struct *vm; /* vm area for mapping object that span pages */ +#else + char *vm_buf; /* copy buffer for objects that span pages */ +#endif + char *vm_addr; /* address of kmap_atomic()'ed pages */ + enum zs_mapmode vm_mm; /* mapping mode */ +}; + +/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ +static DEFINE_PER_CPU(struct mapping_area, zs_map_area); + +static int is_first_page(struct page *page) +{ + return PagePrivate(page); +} + +static int is_last_page(struct page *page) +{ + return PagePrivate2(page); +} + +static void get_zspage_mapping(struct page *page, unsigned int *class_idx, + enum fullness_group *fullness) +{ + unsigned long m; + BUG_ON(!is_first_page(page)); + + m = (unsigned long)page->mapping; + *fullness = m & FULLNESS_MASK; + *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK; +} + +static void set_zspage_mapping(struct page *page, unsigned int class_idx, + enum fullness_group fullness) +{ + unsigned long m; + BUG_ON(!is_first_page(page)); + + m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) | + (fullness & FULLNESS_MASK); + page->mapping = (struct address_space *)m; +} + +/* + * zsmalloc divides the pool into various size classes where each + * class maintains a list of zspages where each zspage is divided + * into equal sized chunks. Each allocation falls into one of these + * classes depending on its size. This function returns index of the + * size class which has chunk size big enough to hold the give size. + */ +static int get_size_class_index(int size) +{ + int idx = 0; + + if (likely(size > ZS_MIN_ALLOC_SIZE)) + idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE, + ZS_SIZE_CLASS_DELTA); + + return idx; +} + +/* + * For each size class, zspages are divided into different groups + * depending on how "full" they are. This was done so that we could + * easily find empty or nearly empty zspages when we try to shrink + * the pool (not yet implemented). This function returns fullness + * status of the given page. + */ +static enum fullness_group get_fullness_group(struct page *page) +{ + int inuse, max_objects; + enum fullness_group fg; + BUG_ON(!is_first_page(page)); + + inuse = page->inuse; + max_objects = page->objects; + + if (inuse == 0) + fg = ZS_EMPTY; + else if (inuse == max_objects) + fg = ZS_FULL; + else if (inuse <= max_objects / fullness_threshold_frac) + fg = ZS_ALMOST_EMPTY; + else + fg = ZS_ALMOST_FULL; + + return fg; +} + +/* + * Each size class maintains various freelists and zspages are assigned + * to one of these freelists based on the number of live objects they + * have. This functions inserts the given zspage into the freelist + * identified by <class, fullness_group>. + */ +static void insert_zspage(struct page *page, struct size_class *class, + enum fullness_group fullness) +{ + struct page **head; + + BUG_ON(!is_first_page(page)); + + if (fullness >= _ZS_NR_FULLNESS_GROUPS) + return; + + head = &class->fullness_list[fullness]; + if (*head) + list_add_tail(&page->lru, &(*head)->lru); + + *head = page; +} + +/* + * This function removes the given zspage from the freelist identified + * by <class, fullness_group>. + */ +static void remove_zspage(struct page *page, struct size_class *class, + enum fullness_group fullness) +{ + struct page **head; + + BUG_ON(!is_first_page(page)); + + if (fullness >= _ZS_NR_FULLNESS_GROUPS) + return; + + head = &class->fullness_list[fullness]; + BUG_ON(!*head); + if (list_empty(&(*head)->lru)) + *head = NULL; + else if (*head == page) + *head = (struct page *)list_entry((*head)->lru.next, + struct page, lru); + + list_del_init(&page->lru); +} + +/* + * Each size class maintains zspages in different fullness groups depending + * on the number of live objects they contain. When allocating or freeing + * objects, the fullness status of the page can change, say, from ALMOST_FULL + * to ALMOST_EMPTY when freeing an object. This function checks if such + * a status change has occurred for the given page and accordingly moves the + * page from the freelist of the old fullness group to that of the new + * fullness group. + */ +static enum fullness_group fix_fullness_group(struct zs_pool *pool, + struct page *page) +{ + int class_idx; + struct size_class *class; + enum fullness_group currfg, newfg; + + BUG_ON(!is_first_page(page)); + + get_zspage_mapping(page, &class_idx, &currfg); + newfg = get_fullness_group(page); + if (newfg == currfg) + goto out; + + class = pool->size_class[class_idx]; + remove_zspage(page, class, currfg); + insert_zspage(page, class, newfg); + set_zspage_mapping(page, class_idx, newfg); + +out: + return newfg; +} + +/* + * We have to decide on how many pages to link together + * to form a zspage for each size class. This is important + * to reduce wastage due to unusable space left at end of + * each zspage which is given as: + * wastage = Zp - Zp % size_class + * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ... + * + * For example, for size class of 3/8 * PAGE_SIZE, we should + * link together 3 PAGE_SIZE sized pages to form a zspage + * since then we can perfectly fit in 8 such objects. + */ +static int get_pages_per_zspage(int class_size) +{ + int i, max_usedpc = 0; + /* zspage order which gives maximum used size per KB */ + int max_usedpc_order = 1; + + for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) { + int zspage_size; + int waste, usedpc; + + zspage_size = i * PAGE_SIZE; + waste = zspage_size % class_size; + usedpc = (zspage_size - waste) * 100 / zspage_size; + + if (usedpc > max_usedpc) { + max_usedpc = usedpc; + max_usedpc_order = i; + } + } + + return max_usedpc_order; +} + +/* + * A single 'zspage' is composed of many system pages which are + * linked together using fields in struct page. This function finds + * the first/head page, given any component page of a zspage. + */ +static struct page *get_first_page(struct page *page) +{ + if (is_first_page(page)) + return page; + else + return page->first_page; +} + +static struct page *get_next_page(struct page *page) +{ + struct page *next; + + if (is_last_page(page)) + next = NULL; + else if (is_first_page(page)) + next = (struct page *)page_private(page); + else + next = list_entry(page->lru.next, struct page, lru); + + return next; +} + +/* + * Encode <page, obj_idx> as a single handle value. + * On hardware platforms with physical memory starting at 0x0 the pfn + * could be 0 so we ensure that the handle will never be 0 by adjusting the + * encoded obj_idx value before encoding. + */ +static void *obj_location_to_handle(struct page *page, unsigned long obj_idx) +{ + unsigned long handle; + + if (!page) { + BUG_ON(obj_idx); + return NULL; + } + + handle = page_to_pfn(page) << OBJ_INDEX_BITS; + handle |= ((obj_idx + 1) & OBJ_INDEX_MASK); + + return (void *)handle; +} + +/* + * Decode <page, obj_idx> pair from the given object handle. We adjust the + * decoded obj_idx back to its original value since it was adjusted in + * obj_location_to_handle(). + */ +static void obj_handle_to_location(unsigned long handle, struct page **page, + unsigned long *obj_idx) +{ + *page = pfn_to_page(handle >> OBJ_INDEX_BITS); + *obj_idx = (handle & OBJ_INDEX_MASK) - 1; +} + +static unsigned long obj_idx_to_offset(struct page *page, + unsigned long obj_idx, int class_size) +{ + unsigned long off = 0; + + if (!is_first_page(page)) + off = page->index; + + return off + obj_idx * class_size; +} + +static void reset_page(struct page *page) +{ + clear_bit(PG_private, &page->flags); + clear_bit(PG_private_2, &page->flags); + set_page_private(page, 0); + page->mapping = NULL; + page->freelist = NULL; + reset_page_mapcount(page); +} + +static void free_zspage(struct page *first_page) +{ + struct page *nextp, *tmp, *head_extra; + + BUG_ON(!is_first_page(first_page)); + BUG_ON(first_page->inuse); + + head_extra = (struct page *)page_private(first_page); + + reset_page(first_page); + __free_page(first_page); + + /* zspage with only 1 system page */ + if (!head_extra) + return; + + list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) { + list_del(&nextp->lru); + reset_page(nextp); + __free_page(nextp); + } + reset_page(head_extra); + __free_page(head_extra); +} + +/* Initialize a newly allocated zspage */ +static void init_zspage(struct page *first_page, struct size_class *class) +{ + unsigned long off = 0; + struct page *page = first_page; + + BUG_ON(!is_first_page(first_page)); + while (page) { + struct page *next_page; + struct link_free *link; + unsigned int i = 1; + void *vaddr; + + /* + * page->index stores offset of first object starting + * in the page. For the first page, this is always 0, + * so we use first_page->index (aka ->freelist) to store + * head of corresponding zspage's freelist. + */ + if (page != first_page) + page->index = off; + + vaddr = kmap_atomic(page); + link = (struct link_free *)vaddr + off / sizeof(*link); + + while ((off += class->size) < PAGE_SIZE) { + link->next = obj_location_to_handle(page, i++); + link += class->size / sizeof(*link); + } + + /* + * We now come to the last (full or partial) object on this + * page, which must point to the first object on the next + * page (if present) + */ + next_page = get_next_page(page); + link->next = obj_location_to_handle(next_page, 0); + kunmap_atomic(vaddr); + page = next_page; + off %= PAGE_SIZE; + } +} + +/* + * Allocate a zspage for the given size class + */ +static struct page *alloc_zspage(struct size_class *class, gfp_t flags) +{ + int i, error; + struct page *first_page = NULL, *uninitialized_var(prev_page); + + /* + * Allocate individual pages and link them together as: + * 1. first page->private = first sub-page + * 2. all sub-pages are linked together using page->lru + * 3. each sub-page is linked to the first page using page->first_page + * + * For each size class, First/Head pages are linked together using + * page->lru. Also, we set PG_private to identify the first page + * (i.e. no other sub-page has this flag set) and PG_private_2 to + * identify the last page. + */ + error = -ENOMEM; + for (i = 0; i < class->pages_per_zspage; i++) { + struct page *page; + + page = alloc_page(flags); + if (!page) + goto cleanup; + + INIT_LIST_HEAD(&page->lru); + if (i == 0) { /* first page */ + SetPagePrivate(page); + set_page_private(page, 0); + first_page = page; + first_page->inuse = 0; + } + if (i == 1) + set_page_private(first_page, (unsigned long)page); + if (i >= 1) + page->first_page = first_page; + if (i >= 2) + list_add(&page->lru, &prev_page->lru); + if (i == class->pages_per_zspage - 1) /* last page */ + SetPagePrivate2(page); + prev_page = page; + } + + init_zspage(first_page, class); + + first_page->freelist = obj_location_to_handle(first_page, 0); + /* Maximum number of objects we can store in this zspage */ + first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size; + + error = 0; /* Success */ + +cleanup: + if (unlikely(error) && first_page) { + free_zspage(first_page); + first_page = NULL; + } + + return first_page; +} + +static struct page *find_get_zspage(struct size_class *class) +{ + int i; + struct page *page; + + for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) { + page = class->fullness_list[i]; + if (page) + break; + } + + return page; +} + +#ifdef CONFIG_PGTABLE_MAPPING +static inline int __zs_cpu_up(struct mapping_area *area) +{ + /* + * Make sure we don't leak memory if a cpu UP notification + * and zs_init() race and both call zs_cpu_up() on the same cpu + */ + if (area->vm) + return 0; + area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL); + if (!area->vm) + return -ENOMEM; + return 0; +} + +static inline void __zs_cpu_down(struct mapping_area *area) +{ + if (area->vm) + free_vm_area(area->vm); + area->vm = NULL; +} + +static inline void *__zs_map_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages)); + area->vm_addr = area->vm->addr; + return area->vm_addr + off; +} + +static inline void __zs_unmap_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + unsigned long addr = (unsigned long)area->vm_addr; + + unmap_kernel_range(addr, PAGE_SIZE * 2); +} + +#else /* CONFIG_PGTABLE_MAPPING */ + +static inline int __zs_cpu_up(struct mapping_area *area) +{ + /* + * Make sure we don't leak memory if a cpu UP notification + * and zs_init() race and both call zs_cpu_up() on the same cpu + */ + if (area->vm_buf) + return 0; + area->vm_buf = (char *)__get_free_page(GFP_KERNEL); + if (!area->vm_buf) + return -ENOMEM; + return 0; +} + +static inline void __zs_cpu_down(struct mapping_area *area) +{ + if (area->vm_buf) + free_page((unsigned long)area->vm_buf); + area->vm_buf = NULL; +} + +static void *__zs_map_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + int sizes[2]; + void *addr; + char *buf = area->vm_buf; + + /* disable page faults to match kmap_atomic() return conditions */ + pagefault_disable(); + + /* no read fastpath */ + if (area->vm_mm == ZS_MM_WO) + goto out; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = size - sizes[0]; + + /* copy object to per-cpu buffer */ + addr = kmap_atomic(pages[0]); + memcpy(buf, addr + off, sizes[0]); + kunmap_atomic(addr); + addr = kmap_atomic(pages[1]); + memcpy(buf + sizes[0], addr, sizes[1]); + kunmap_atomic(addr); +out: + return area->vm_buf; +} + +static void __zs_unmap_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + int sizes[2]; + void *addr; + char *buf = area->vm_buf; + + /* no write fastpath */ + if (area->vm_mm == ZS_MM_RO) + goto out; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = size - sizes[0]; + + /* copy per-cpu buffer to object */ + addr = kmap_atomic(pages[0]); + memcpy(addr + off, buf, sizes[0]); + kunmap_atomic(addr); + addr = kmap_atomic(pages[1]); + memcpy(addr, buf + sizes[0], sizes[1]); + kunmap_atomic(addr); + +out: + /* enable page faults to match kunmap_atomic() return conditions */ + pagefault_enable(); +} + +#endif /* CONFIG_PGTABLE_MAPPING */ + +static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action, + void *pcpu) +{ + int ret, cpu = (long)pcpu; + struct mapping_area *area; + + switch (action) { + case CPU_UP_PREPARE: + area = &per_cpu(zs_map_area, cpu); + ret = __zs_cpu_up(area); + if (ret) + return notifier_from_errno(ret); + break; + case CPU_DEAD: + case CPU_UP_CANCELED: + area = &per_cpu(zs_map_area, cpu); + __zs_cpu_down(area); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block zs_cpu_nb = { + .notifier_call = zs_cpu_notifier +}; + +static void zs_exit(void) +{ + int cpu; + + for_each_online_cpu(cpu) + zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu); + unregister_cpu_notifier(&zs_cpu_nb); +} + +static int zs_init(void) +{ + int cpu, ret; + + register_cpu_notifier(&zs_cpu_nb); + for_each_online_cpu(cpu) { + ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu); + if (notifier_to_errno(ret)) + goto fail; + } + return 0; +fail: + zs_exit(); + return notifier_to_errno(ret); +} + +static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage) +{ + return pages_per_zspage * PAGE_SIZE / size; +} + +static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) +{ + if (prev->pages_per_zspage != pages_per_zspage) + return false; + + if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage) + != get_maxobj_per_zspage(size, pages_per_zspage)) + return false; + + return true; +} + +/** + * zs_create_pool - Creates an allocation pool to work from. + * @flags: allocation flags used to allocate pool metadata + * + * This function must be called before anything when using + * the zsmalloc allocator. + * + * On success, a pointer to the newly created pool is returned, + * otherwise NULL. + */ +struct zs_pool *zs_create_pool(gfp_t flags) +{ + int i; + struct zs_pool *pool; + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return NULL; + + /* + * Iterate reversly, because, size of size_class that we want to use + * for merging should be larger or equal to current size. + */ + for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { + int size; + int pages_per_zspage; + struct size_class *class; + struct size_class *prev_class; + + size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA; + if (size > ZS_MAX_ALLOC_SIZE) + size = ZS_MAX_ALLOC_SIZE; + pages_per_zspage = get_pages_per_zspage(size); + + /* + * size_class is used for normal zsmalloc operation such + * as alloc/free for that size. Although it is natural that we + * have one size_class for each size, there is a chance that we + * can get more memory utilization if we use one size_class for + * many different sizes whose size_class have same + * characteristics. So, we makes size_class point to + * previous size_class if possible. + */ + if (i < ZS_SIZE_CLASSES - 1) { + prev_class = pool->size_class[i + 1]; + if (can_merge(prev_class, size, pages_per_zspage)) { + pool->size_class[i] = prev_class; + continue; + } + } + + class = kzalloc(sizeof(struct size_class), GFP_KERNEL); + if (!class) + goto err; + + class->size = size; + class->index = i; + class->pages_per_zspage = pages_per_zspage; + spin_lock_init(&class->lock); + pool->size_class[i] = class; + } + + pool->flags = flags; + + return pool; + +err: + zs_destroy_pool(pool); + return NULL; +} +EXPORT_SYMBOL_GPL(zs_create_pool); + +void zs_destroy_pool(struct zs_pool *pool) +{ + int i; + + for (i = 0; i < ZS_SIZE_CLASSES; i++) { + int fg; + struct size_class *class = pool->size_class[i]; + + if (!class) + continue; + + if (class->index != i) + continue; + + for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) { + if (class->fullness_list[fg]) { + pr_info("Freeing non-empty class with size %db, fullness group %d\n", + class->size, fg); + } + } + kfree(class); + } + kfree(pool); +} +EXPORT_SYMBOL_GPL(zs_destroy_pool); + +/** + * zs_malloc - Allocate block of given size from pool. + * @pool: pool to allocate from + * @size: size of block to allocate + * + * On success, handle to the allocated object is returned, + * otherwise 0. + * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. + */ +unsigned long zs_malloc(struct zs_pool *pool, size_t size) +{ + unsigned long obj; + struct link_free *link; + struct size_class *class; + void *vaddr; + + struct page *first_page, *m_page; + unsigned long m_objidx, m_offset; + + if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) + return 0; + + class = pool->size_class[get_size_class_index(size)]; + + spin_lock(&class->lock); + first_page = find_get_zspage(class); + + if (!first_page) { + spin_unlock(&class->lock); + first_page = alloc_zspage(class, pool->flags); + if (unlikely(!first_page)) + return 0; + + set_zspage_mapping(first_page, class->index, ZS_EMPTY); + atomic_long_add(class->pages_per_zspage, + &pool->pages_allocated); + spin_lock(&class->lock); + } + + obj = (unsigned long)first_page->freelist; + obj_handle_to_location(obj, &m_page, &m_objidx); + m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); + + vaddr = kmap_atomic(m_page); + link = (struct link_free *)vaddr + m_offset / sizeof(*link); + first_page->freelist = link->next; + memset(link, POISON_INUSE, sizeof(*link)); + kunmap_atomic(vaddr); + + first_page->inuse++; + /* Now move the zspage to another fullness group, if required */ + fix_fullness_group(pool, first_page); + spin_unlock(&class->lock); + + return obj; +} +EXPORT_SYMBOL_GPL(zs_malloc); + +void zs_free(struct zs_pool *pool, unsigned long obj) +{ + struct link_free *link; + struct page *first_page, *f_page; + unsigned long f_objidx, f_offset; + void *vaddr; + + int class_idx; + struct size_class *class; + enum fullness_group fullness; + + if (unlikely(!obj)) + return; + + obj_handle_to_location(obj, &f_page, &f_objidx); + first_page = get_first_page(f_page); + + get_zspage_mapping(first_page, &class_idx, &fullness); + class = pool->size_class[class_idx]; + f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); + + spin_lock(&class->lock); + + /* Insert this object in containing zspage's freelist */ + vaddr = kmap_atomic(f_page); + link = (struct link_free *)(vaddr + f_offset); + link->next = first_page->freelist; + kunmap_atomic(vaddr); + first_page->freelist = (void *)obj; + + first_page->inuse--; + fullness = fix_fullness_group(pool, first_page); + spin_unlock(&class->lock); + + if (fullness == ZS_EMPTY) { + atomic_long_sub(class->pages_per_zspage, + &pool->pages_allocated); + free_zspage(first_page); + } +} +EXPORT_SYMBOL_GPL(zs_free); + +/** + * zs_map_object - get address of allocated object from handle. + * @pool: pool from which the object was allocated + * @handle: handle returned from zs_malloc + * + * Before using an object allocated from zs_malloc, it must be mapped using + * this function. When done with the object, it must be unmapped using + * zs_unmap_object. + * + * Only one object can be mapped per cpu at a time. There is no protection + * against nested mappings. + * + * This function returns with preemption and page faults disabled. + */ +void *zs_map_object(struct zs_pool *pool, unsigned long handle, + enum zs_mapmode mm) +{ + struct page *page; + unsigned long obj_idx, off; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + struct page *pages[2]; + + BUG_ON(!handle); + + /* + * Because we use per-cpu mapping areas shared among the + * pools/users, we can't allow mapping in interrupt context + * because it can corrupt another users mappings. + */ + BUG_ON(in_interrupt()); + + obj_handle_to_location(handle, &page, &obj_idx); + get_zspage_mapping(get_first_page(page), &class_idx, &fg); + class = pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + + area = &get_cpu_var(zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ + area->vm_addr = kmap_atomic(page); + return area->vm_addr + off; + } + + /* this object spans two pages */ + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + return __zs_map_object(area, pages, off, class->size); +} +EXPORT_SYMBOL_GPL(zs_map_object); + +void zs_unmap_object(struct zs_pool *pool, unsigned long handle) +{ + struct page *page; + unsigned long obj_idx, off; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + + BUG_ON(!handle); + + obj_handle_to_location(handle, &page, &obj_idx); + get_zspage_mapping(get_first_page(page), &class_idx, &fg); + class = pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + + area = &__get_cpu_var(zs_map_area); + if (off + class->size <= PAGE_SIZE) + kunmap_atomic(area->vm_addr); + else { + struct page *pages[2]; + + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + __zs_unmap_object(area, pages, off, class->size); + } + put_cpu_var(zs_map_area); +} +EXPORT_SYMBOL_GPL(zs_unmap_object); + +unsigned long zs_get_total_pages(struct zs_pool *pool) +{ + return atomic_long_read(&pool->pages_allocated); +} +EXPORT_SYMBOL_GPL(zs_get_total_pages); + +module_init(zs_init); +module_exit(zs_exit); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>"); |