diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Makefile | 4 | ||||
| -rw-r--r-- | mm/allocpercpu.c | 32 | ||||
| -rw-r--r-- | mm/backing-dev.c | 26 | ||||
| -rw-r--r-- | mm/bootmem.c | 35 | ||||
| -rw-r--r-- | mm/filemap.c | 7 | ||||
| -rw-r--r-- | mm/fremap.c | 2 | ||||
| -rw-r--r-- | mm/highmem.c | 65 | ||||
| -rw-r--r-- | mm/hugetlb.c | 28 | ||||
| -rw-r--r-- | mm/memory.c | 6 | ||||
| -rw-r--r-- | mm/migrate.c | 2 | ||||
| -rw-r--r-- | mm/mlock.c | 12 | ||||
| -rw-r--r-- | mm/mmap.c | 52 | ||||
| -rw-r--r-- | mm/mprotect.c | 5 | ||||
| -rw-r--r-- | mm/page-writeback.c | 50 | ||||
| -rw-r--r-- | mm/page_alloc.c | 27 | ||||
| -rw-r--r-- | mm/page_cgroup.c | 3 | ||||
| -rw-r--r-- | mm/page_io.c | 2 | ||||
| -rw-r--r-- | mm/percpu.c | 1326 | ||||
| -rw-r--r-- | mm/readahead.c | 25 | ||||
| -rw-r--r-- | mm/rmap.c | 3 | ||||
| -rw-r--r-- | mm/shmem.c | 45 | ||||
| -rw-r--r-- | mm/slab.c | 1 | ||||
| -rw-r--r-- | mm/slob.c | 44 | ||||
| -rw-r--r-- | mm/slub.c | 83 | ||||
| -rw-r--r-- | mm/swapfile.c | 4 | ||||
| -rw-r--r-- | mm/util.c | 20 | ||||
| -rw-r--r-- | mm/vmalloc.c | 117 | ||||
| -rw-r--r-- | mm/vmscan.c | 32 |
28 files changed, 1847 insertions, 211 deletions
diff --git a/mm/Makefile b/mm/Makefile index 72255be57f89..818569b68f46 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -30,6 +30,10 @@ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o +ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA +obj-$(CONFIG_SMP) += percpu.o +else obj-$(CONFIG_SMP) += allocpercpu.o +endif obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index 4297bc41bfd2..1882923bc706 100644 --- a/mm/allocpercpu.c +++ b/mm/allocpercpu.c @@ -99,45 +99,51 @@ static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, __percpu_populate_mask((__pdata), (size), (gfp), &(mask)) /** - * percpu_alloc_mask - initial setup of per-cpu data + * alloc_percpu - initial setup of per-cpu data * @size: size of per-cpu object - * @gfp: may sleep or not etc. - * @mask: populate per-data for cpu's selected through mask bits + * @align: alignment * - * Populating per-cpu data for all online cpu's would be a typical use case, - * which is simplified by the percpu_alloc() wrapper. - * Per-cpu objects are populated with zeroed buffers. + * Allocate dynamic percpu area. Percpu objects are populated with + * zeroed buffers. */ -void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) +void *__alloc_percpu(size_t size, size_t align) { /* * We allocate whole cache lines to avoid false sharing */ size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size()); - void *pdata = kzalloc(sz, gfp); + void *pdata = kzalloc(sz, GFP_KERNEL); void *__pdata = __percpu_disguise(pdata); + /* + * Can't easily make larger alignment work with kmalloc. WARN + * on it. Larger alignment should only be used for module + * percpu sections on SMP for which this path isn't used. + */ + WARN_ON_ONCE(align > SMP_CACHE_BYTES); + if (unlikely(!pdata)) return NULL; - if (likely(!__percpu_populate_mask(__pdata, size, gfp, mask))) + if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL, + &cpu_possible_map))) return __pdata; kfree(pdata); return NULL; } -EXPORT_SYMBOL_GPL(__percpu_alloc_mask); +EXPORT_SYMBOL_GPL(__alloc_percpu); /** - * percpu_free - final cleanup of per-cpu data + * free_percpu - final cleanup of per-cpu data * @__pdata: object to clean up * * We simply clean up any per-cpu object left. No need for the client to * track and specify through a bis mask which per-cpu objects are to free. */ -void percpu_free(void *__pdata) +void free_percpu(void *__pdata) { if (unlikely(!__pdata)) return; __percpu_depopulate_mask(__pdata, &cpu_possible_map); kfree(__percpu_disguise(__pdata)); } -EXPORT_SYMBOL_GPL(percpu_free); +EXPORT_SYMBOL_GPL(free_percpu); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8e8587444132..be68c956a660 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -2,11 +2,24 @@ #include <linux/wait.h> #include <linux/backing-dev.h> #include <linux/fs.h> +#include <linux/pagemap.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> +void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) +{ +} +EXPORT_SYMBOL(default_unplug_io_fn); + +struct backing_dev_info default_backing_dev_info = { + .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, + .state = 0, + .capabilities = BDI_CAP_MAP_COPY, + .unplug_io_fn = default_unplug_io_fn, +}; +EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; @@ -166,9 +179,20 @@ static __init int bdi_class_init(void) bdi_debug_init(); return 0; } - postcore_initcall(bdi_class_init); +static int __init default_bdi_init(void) +{ + int err; + + err = bdi_init(&default_backing_dev_info); + if (!err) + bdi_register(&default_backing_dev_info, NULL, "default"); + + return err; +} +subsys_initcall(default_bdi_init); + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { diff --git a/mm/bootmem.c b/mm/bootmem.c index 51a0ccf61e0e..daf92713f7de 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -382,7 +382,6 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, return mark_bootmem_node(pgdat->bdata, start, end, 1, flags); } -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE /** * reserve_bootmem - mark a page range as usable * @addr: starting address of the range @@ -403,7 +402,6 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size, return mark_bootmem(start, end, 1, flags); } -#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ static unsigned long align_idx(struct bootmem_data *bdata, unsigned long idx, unsigned long step) @@ -429,8 +427,8 @@ static unsigned long align_off(struct bootmem_data *bdata, unsigned long off, } static void * __init alloc_bootmem_core(struct bootmem_data *bdata, - unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) + unsigned long size, unsigned long align, + unsigned long goal, unsigned long limit) { unsigned long fallback = 0; unsigned long min, max, start, sidx, midx, step; @@ -530,17 +528,34 @@ find_block: return NULL; } +static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata, + unsigned long size, unsigned long align, + unsigned long goal, unsigned long limit) +{ +#ifdef CONFIG_HAVE_ARCH_BOOTMEM + bootmem_data_t *p_bdata; + + p_bdata = bootmem_arch_preferred_node(bdata, size, align, goal, limit); + if (p_bdata) + return alloc_bootmem_core(p_bdata, size, align, goal, limit); +#endif + return NULL; +} + static void * __init ___alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { bootmem_data_t *bdata; + void *region; restart: - list_for_each_entry(bdata, &bdata_list, list) { - void *region; + region = alloc_arch_preferred_bootmem(NULL, size, align, goal, limit); + if (region) + return region; + list_for_each_entry(bdata, &bdata_list, list) { if (goal && bdata->node_low_pfn <= PFN_DOWN(goal)) continue; if (limit && bdata->node_min_pfn >= PFN_DOWN(limit)) @@ -618,6 +633,10 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata, { void *ptr; + ptr = alloc_arch_preferred_bootmem(bdata, size, align, goal, limit); + if (ptr) + return ptr; + ptr = alloc_bootmem_core(bdata, size, align, goal, limit); if (ptr) return ptr; @@ -674,6 +693,10 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, { void *ptr; + ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0); + if (ptr) + return ptr; + ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0); if (ptr) return ptr; diff --git a/mm/filemap.c b/mm/filemap.c index 23acefe51808..126d3973b3d1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1823,7 +1823,7 @@ static size_t __iovec_copy_from_user_inatomic(char *vaddr, int copy = min(bytes, iov->iov_len - base); base = 0; - left = __copy_from_user_inatomic_nocache(vaddr, buf, copy); + left = __copy_from_user_inatomic(vaddr, buf, copy); copied += copy; bytes -= copy; vaddr += copy; @@ -1851,8 +1851,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_inatomic_nocache(kaddr + offset, - buf, bytes); + left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); copied = bytes - left; } else { copied = __iovec_copy_from_user_inatomic(kaddr + offset, @@ -1880,7 +1879,7 @@ size_t iov_iter_copy_from_user(struct page *page, if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_nocache(kaddr + offset, buf, bytes); + left = __copy_from_user(kaddr + offset, buf, bytes); copied = bytes - left; } else { copied = __iovec_copy_from_user_inatomic(kaddr + offset, diff --git a/mm/fremap.c b/mm/fremap.c index 736ba7f3306a..b6ec85abbb39 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -198,7 +198,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; get_file(file); addr = mmap_region(file, start, size, - flags, vma->vm_flags, pgoff, 1); + flags, vma->vm_flags, pgoff); fput(file); if (IS_ERR_VALUE(addr)) { err = addr; diff --git a/mm/highmem.c b/mm/highmem.c index b36b83b920ff..910198037bf5 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -67,6 +67,25 @@ pte_t * pkmap_page_table; static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait); +/* + * Most architectures have no use for kmap_high_get(), so let's abstract + * the disabling of IRQ out of the locking in that case to save on a + * potential useless overhead. + */ +#ifdef ARCH_NEEDS_KMAP_HIGH_GET +#define lock_kmap() spin_lock_irq(&kmap_lock) +#define unlock_kmap() spin_unlock_irq(&kmap_lock) +#define lock_kmap_any(flags) spin_lock_irqsave(&kmap_lock, flags) +#define unlock_kmap_any(flags) spin_unlock_irqrestore(&kmap_lock, flags) +#else +#define lock_kmap() spin_lock(&kmap_lock) +#define unlock_kmap() spin_unlock(&kmap_lock) +#define lock_kmap_any(flags) \ + do { spin_lock(&kmap_lock); (void)(flags); } while (0) +#define unlock_kmap_any(flags) \ + do { spin_unlock(&kmap_lock); (void)(flags); } while (0) +#endif + static void flush_all_zero_pkmaps(void) { int i; @@ -113,9 +132,9 @@ static void flush_all_zero_pkmaps(void) */ void kmap_flush_unused(void) { - spin_lock(&kmap_lock); + lock_kmap(); flush_all_zero_pkmaps(); - spin_unlock(&kmap_lock); + unlock_kmap(); } static inline unsigned long map_new_virtual(struct page *page) @@ -145,10 +164,10 @@ start: __set_current_state(TASK_UNINTERRUPTIBLE); add_wait_queue(&pkmap_map_wait, &wait); - spin_unlock(&kmap_lock); + unlock_kmap(); schedule(); remove_wait_queue(&pkmap_map_wait, &wait); - spin_lock(&kmap_lock); + lock_kmap(); /* Somebody else might have mapped it while we slept */ if (page_address(page)) @@ -184,29 +203,59 @@ void *kmap_high(struct page *page) * For highmem pages, we can't trust "virtual" until * after we have the lock. */ - spin_lock(&kmap_lock); + lock_kmap(); vaddr = (unsigned long)page_address(page); if (!vaddr) vaddr = map_new_virtual(page); pkmap_count[PKMAP_NR(vaddr)]++; BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2); - spin_unlock(&kmap_lock); + unlock_kmap(); return (void*) vaddr; } EXPORT_SYMBOL(kmap_high); +#ifdef ARCH_NEEDS_KMAP_HIGH_GET +/** + * kmap_high_get - pin a highmem page into memory + * @page: &struct page to pin + * + * Returns the page's current virtual memory address, or NULL if no mapping + * exists. When and only when a non null address is returned then a + * matching call to kunmap_high() is necessary. + * + * This can be called from any context. + */ +void *kmap_high_get(struct page *page) +{ + unsigned long vaddr, flags; + + lock_kmap_any(flags); + vaddr = (unsigned long)page_address(page); + if (vaddr) { + BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1); + pkmap_count[PKMAP_NR(vaddr)]++; + } + unlock_kmap_any(flags); + return (void*) vaddr; +} +#endif + /** * kunmap_high - map a highmem page into memory * @page: &struct page to unmap + * + * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called + * only from user context. */ void kunmap_high(struct page *page) { unsigned long vaddr; unsigned long nr; + unsigned long flags; int need_wakeup; - spin_lock(&kmap_lock); + lock_kmap_any(flags); vaddr = (unsigned long)page_address(page); BUG_ON(!vaddr); nr = PKMAP_NR(vaddr); @@ -232,7 +281,7 @@ void kunmap_high(struct page *page) */ need_wakeup = waitqueue_active(&pkmap_map_wait); } - spin_unlock(&kmap_lock); + unlock_kmap_any(flags); /* do wake-up, if needed, race-free outside of the spin lock */ if (need_wakeup) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 618e98304080..107da3d809a8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2269,12 +2269,18 @@ void hugetlb_change_protection(struct vm_area_struct *vma, int hugetlb_reserve_pages(struct inode *inode, long from, long to, - struct vm_area_struct *vma) + struct vm_area_struct *vma, + int acctflag) { long ret, chg; struct hstate *h = hstate_inode(inode); - if (vma && vma->vm_flags & VM_NORESERVE) + /* + * Only apply hugepage reservation if asked. At fault time, an + * attempt will be made for VM_NORESERVE to allocate a page + * and filesystem quota without using reserves + */ + if (acctflag & VM_NORESERVE) return 0; /* @@ -2299,13 +2305,31 @@ int hugetlb_reserve_pages(struct inode *inode, if (chg < 0) return chg; + /* There must be enough filesystem quota for the mapping */ if (hugetlb_get_quota(inode->i_mapping, chg)) return -ENOSPC; + + /* + * Check enough hugepages are available for the reservation. + * Hand back the quota if there are not + */ ret = hugetlb_acct_memory(h, chg); if (ret < 0) { hugetlb_put_quota(inode->i_mapping, chg); return ret; } + + /* + * Account for the reservations made. Shared mappings record regions + * that have reservations as they are shared by multiple VMAs. + * When the last VMA disappears, the region map says how much + * the reservation was and the page cache tells how much of + * the reservation was consumed. Private mappings are per-VMA and + * only the consumed reservations are tracked. When the VMA + * disappears, the original reservation is the VMA size and the + * consumed reservations are stored in the map. Hence, nothing + * else has to be done for private mappings here + */ if (!vma || vma->vm_flags & VM_SHARED) region_add(&inode->i_mapping->private_list, from, to); return 0; diff --git a/mm/memory.c b/mm/memory.c index baa999e87cd2..2032ad2fc34b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1665,9 +1665,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". */ - if (addr == vma->vm_start && end == vma->vm_end) + if (addr == vma->vm_start && end == vma->vm_end) { vma->vm_pgoff = pfn; - else if (is_cow_mapping(vma->vm_flags)) + vma->vm_flags |= VM_PFN_AT_MMAP; + } else if (is_cow_mapping(vma->vm_flags)) return -EINVAL; vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; @@ -1679,6 +1680,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * needed from higher level routine calling unmap_vmas */ vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP); + vma->vm_flags &= ~VM_PFN_AT_MMAP; return -EINVAL; } diff --git a/mm/migrate.c b/mm/migrate.c index 2bb4e1d63520..a9eff3f092f6 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1129,7 +1129,7 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, struct vm_area_struct *vma; int err = 0; - for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) { + for (vma = mm->mmap; vma && !err; vma = vma->vm_next) { if (vma->vm_ops && vma->vm_ops->migrate) { err = vma->vm_ops->migrate(vma, to, from, flags); if (err) diff --git a/mm/mlock.c b/mm/mlock.c index 028ec482fdd4..cbe9e0581b75 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -311,7 +311,10 @@ long mlock_vma_pages_range(struct vm_area_struct *vma, is_vm_hugetlb_page(vma) || vma == get_gate_vma(current))) { - return __mlock_vma_pages_range(vma, start, end, 1); + __mlock_vma_pages_range(vma, start, end, 1); + + /* Hide errors from mmap() and other callers */ + return 0; } /* @@ -657,7 +660,7 @@ void *alloc_locked_buffer(size_t size) return buffer; } -void free_locked_buffer(void *buffer, size_t size) +void release_locked_buffer(void *buffer, size_t size) { unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; @@ -667,6 +670,11 @@ void free_locked_buffer(void *buffer, size_t size) current->mm->locked_vm -= pgsz; up_write(¤t->mm->mmap_sem); +} + +void free_locked_buffer(void *buffer, size_t size) +{ + release_locked_buffer(buffer, size); kfree(buffer); } diff --git a/mm/mmap.c b/mm/mmap.c index 214b6a258eeb..1abb9185a686 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -20,6 +20,7 @@ #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> +#include <linux/ima.h> #include <linux/hugetlb.h> #include <linux/profile.h> #include <linux/module.h> @@ -918,7 +919,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, struct inode *inode; unsigned int vm_flags; int error; - int accountable = 1; unsigned long reqprot = prot; /* @@ -1019,8 +1019,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, return -EPERM; vm_flags &= ~VM_MAYEXEC; } - if (is_file_hugepages(file)) - accountable = 0; if (!file->f_op || !file->f_op->mmap) return -ENODEV; @@ -1052,9 +1050,11 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, error = security_file_mmap(file, reqprot, prot, flags, addr, 0); if (error) return error; + error = ima_file_mmap(file, prot); + if (error) + return error; - return mmap_region(file, addr, len, flags, vm_flags, pgoff, - accountable); + return mmap_region(file, addr, len, flags, vm_flags, pgoff); } EXPORT_SYMBOL(do_mmap_pgoff); @@ -1092,17 +1092,23 @@ int vma_wants_writenotify(struct vm_area_struct *vma) /* * We account for memory if it's a private writeable mapping, - * and VM_NORESERVE wasn't set. + * not hugepages and VM_NORESERVE wasn't set. */ -static inline int accountable_mapping(unsigned int vm_flags) +static inline int accountable_mapping(struct file *file, unsigned int vm_flags) { + /* + * hugetlb has its own accounting separate from the core VM + * VM_HUGETLB may not be set yet so we cannot check for that flag. + */ + if (file && is_file_hugepages(file)) + return 0; + return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, - unsigned int vm_flags, unsigned long pgoff, - int accountable) + unsigned int vm_flags, unsigned long pgoff) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; @@ -1128,18 +1134,22 @@ munmap_back: /* * Set 'VM_NORESERVE' if we should not account for the - * memory use of this mapping. We only honor MAP_NORESERVE - * if we're allowed to overcommit memory. + * memory use of this mapping. */ - if ((flags & MAP_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) - vm_flags |= VM_NORESERVE; - if (!accountable) - vm_flags |= VM_NORESERVE; + if ((flags & MAP_NORESERVE)) { + /* We honor MAP_NORESERVE if allowed to overcommit */ + if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) + vm_flags |= VM_NORESERVE; + + /* hugetlb applies strict overcommit unless MAP_NORESERVE */ + if (file && is_file_hugepages(file)) + vm_flags |= VM_NORESERVE; + } /* * Private writable mapping: check memory availability */ - if (accountable_mapping(vm_flags)) { + if (accountable_mapping(file, vm_flags)) { charged = len >> PAGE_SHIFT; if (security_vm_enough_memory(charged)) return -ENOMEM; @@ -2078,12 +2088,8 @@ void exit_mmap(struct mm_struct *mm) unsigned long end; /* mm's last user has gone, and its about to be pulled down */ - arch_exit_mmap(mm); mmu_notifier_release(mm); - if (!mm->mmap) /* Can happen if dup_mmap() received an OOM */ - return; - if (mm->locked_vm) { vma = mm->mmap; while (vma) { @@ -2092,7 +2098,13 @@ void exit_mmap(struct mm_struct *mm) vma = vma->vm_next; } } + + arch_exit_mmap(mm); + vma = mm->mmap; + if (!vma) /* Can happen if dup_mmap() received an OOM */ + return; + lru_add_drain(); flush_cache_mm(mm); tlb = tlb_gather_mmu(mm, 1); diff --git a/mm/mprotect.c b/mm/mprotect.c index abe2694e13f4..258197b76fb4 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -151,10 +151,11 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, /* * If we make a private mapping writable we increase our commit; * but (without finer accounting) cannot reduce our commit if we - * make it unwritable again. + * make it unwritable again. hugetlb mapping were accounted for + * even if read-only so there is no need to account for them here */ if (newflags & VM_WRITE) { - if (!(oldflags & (VM_ACCOUNT|VM_WRITE| + if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB| VM_SHARED|VM_NORESERVE))) { charged = nrpages; if (security_vm_enough_memory(charged)) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index dc32dae01e5f..40ca7cdb653e 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -66,7 +66,7 @@ static inline long sync_writeback_pages(void) /* * Start background writeback (via pdflush) at this percentage */ -int dirty_background_ratio = 5; +int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of @@ -83,7 +83,7 @@ int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ -int vm_dirty_ratio = 10; +int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of @@ -209,7 +209,7 @@ int dirty_bytes_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { - int old_bytes = vm_dirty_bytes; + unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); @@ -240,7 +240,7 @@ void bdi_writeout_inc(struct backing_dev_info *bdi) } EXPORT_SYMBOL_GPL(bdi_writeout_inc); -static inline void task_dirty_inc(struct task_struct *tsk) +void task_dirty_inc(struct task_struct *tsk) { prop_inc_single(&vm_dirties, &tsk->dirties); } @@ -1051,20 +1051,23 @@ continue_unlock: } } - if (nr_to_write > 0) + if (nr_to_write > 0) { nr_to_write--; - else if (wbc->sync_mode == WB_SYNC_NONE) { - /* - * We stop writing back only if we are not - * doing integrity sync. In case of integrity - * sync we have to keep going because someone - * may be concurrently dirtying pages, and we - * might have synced a lot of newly appeared - * dirty pages, but have not synced all of the - * old dirty pages. - */ - done = 1; - break; + if (nr_to_write == 0 && + wbc->sync_mode == WB_SYNC_NONE) { + /* + * We stop writing back only if we are + * not doing integrity sync. In case of + * integrity sync we have to keep going + * because someone may be concurrently + * dirtying pages, and we might have + * synced a lot of newly appeared dirty + * pages, but have not synced all of the + * old dirty pages. + */ + done = 1; + break; + } } if (wbc->nonblocking && bdi_write_congested(bdi)) { @@ -1076,7 +1079,7 @@ continue_unlock: pagevec_release(&pvec); cond_resched(); } - if (!cycled) { + if (!cycled && !done) { /* * range_cyclic: * We hit the last page and there is more work to be done: wrap @@ -1227,6 +1230,7 @@ int __set_page_dirty_nobuffers(struct page *page) __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); + task_dirty_inc(current); task_io_account_write(PAGE_CACHE_SIZE); } radix_tree_tag_set(&mapping->page_tree, @@ -1259,7 +1263,7 @@ EXPORT_SYMBOL(redirty_page_for_writepage); * If the mapping doesn't provide a set_page_dirty a_op, then * just fall through and assume that it wants buffer_heads. */ -static int __set_page_dirty(struct page *page) +int set_page_dirty(struct page *page) { struct address_space *mapping = page_mapping(page); @@ -1277,14 +1281,6 @@ static int __set_page_dirty(struct page *page) } return 0; } - -int set_page_dirty(struct page *page) -{ - int ret = __set_page_dirty(page); - if (ret) - task_dirty_inc(current); - return ret; -} EXPORT_SYMBOL(set_page_dirty); /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 22b15a4cde8a..a3803ea8c27d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2994,7 +2994,7 @@ static int __meminit next_active_region_index_in_nid(int index, int nid) * was used and there are no special requirements, this is a convenient * alternative */ -int __meminit early_pfn_to_nid(unsigned long pfn) +int __meminit __early_pfn_to_nid(unsigned long pfn) { int i; @@ -3005,10 +3005,33 @@ int __meminit early_pfn_to_nid(unsigned long pfn) if (start_pfn <= pfn && pfn < end_pfn) return early_node_map[i].nid; } + /* This is a memory hole */ + return -1; +} +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + +int __meminit early_pfn_to_nid(unsigned long pfn) +{ + int nid; + nid = __early_pfn_to_nid(pfn); + if (nid >= 0) + return nid; + /* just returns 0 */ return 0; } -#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + +#ifdef CONFIG_NODES_SPAN_OTHER_NODES +bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + int nid; + + nid = __early_pfn_to_nid(pfn); + if (nid >= 0 && nid != node) + return false; + return true; +} +#endif /* Basic iterator support to walk early_node_map[] */ #define for_each_active_range_index_in_nid(i, nid) \ diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 7006a11350c8..ceecfbb143fa 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -114,7 +114,8 @@ static int __init_refok init_section_page_cgroup(unsigned long pfn) nid = page_to_nid(pfn_to_page(pfn)); table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION; if (slab_is_available()) { - base = kmalloc_node(table_size, GFP_KERNEL, nid); + base = kmalloc_node(table_size, + GFP_KERNEL | __GFP_NOWARN, nid); if (!base) base = vmalloc_node(table_size, nid); } else { diff --git a/mm/page_io.c b/mm/page_io.c index dc6ce0afbded..3023c475e041 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -111,7 +111,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) goto out; } if (wbc->sync_mode == WB_SYNC_ALL) - rw |= (1 << BIO_RW_SYNC); + rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); count_vm_event(PSWPOUT); set_page_writeback(page); unlock_page(page); diff --git a/mm/percpu.c b/mm/percpu.c new file mode 100644 index 000000000000..1aa5d8fbca12 --- /dev/null +++ b/mm/percpu.c @@ -0,0 +1,1326 @@ +/* + * linux/mm/percpu.c - percpu memory allocator + * + * Copyright (C) 2009 SUSE Linux Products GmbH + * Copyright (C) 2009 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + * + * This is percpu allocator which can handle both static and dynamic + * areas. Percpu areas are allocated in chunks in vmalloc area. Each + * chunk is consisted of num_possible_cpus() units and the first chunk + * is used for static percpu variables in the kernel image (special + * boot time alloc/init handling necessary as these areas need to be + * brought up before allocation services are running). Unit grows as + * necessary and all units grow or shrink in unison. When a chunk is + * filled up, another chunk is allocated. ie. in vmalloc area + * + * c0 c1 c2 + * ------------------- ------------------- ------------ + * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u + * ------------------- ...... ------------------- .... ------------ + * + * Allocation is done in offset-size areas of single unit space. Ie, + * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0, + * c1:u1, c1:u2 and c1:u3. Percpu access can be done by configuring + * percpu base registers UNIT_SIZE apart. + * + * There are usually many small percpu allocations many of them as + * small as 4 bytes. The allocator organizes chunks into lists + * according to free size and tries to allocate from the fullest one. + * Each chunk keeps the maximum contiguous area size hint which is + * guaranteed to be eqaul to or larger than the maximum contiguous + * area in the chunk. This helps the allocator not to iterate the + * chunk maps unnecessarily. + * + * Allocation state in each chunk is kept using an array of integers + * on chunk->map. A positive value in the map represents a free + * region and negative allocated. Allocation inside a chunk is done + * by scanning this map sequentially and serving the first matching + * entry. This is mostly copied from the percpu_modalloc() allocator. + * Chunks are also linked into a rb tree to ease address to chunk + * mapping during free. + * + * To use this allocator, arch code should do the followings. + * + * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA + * + * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate + * regular address to percpu pointer and back if they need to be + * different from the default + * + * - use pcpu_setup_first_chunk() during percpu area initialization to + * setup the first chunk containing the kernel static percpu area + */ + +#include <linux/bitmap.h> +#include <linux/bootmem.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/pfn.h> +#include <linux/rbtree.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/vmalloc.h> +#include <linux/workqueue.h> + +#include <asm/cacheflush.h> +#include <asm/sections.h> +#include <asm/tlbflush.h> + +#define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */ +#define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */ + +/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ +#ifndef __addr_to_pcpu_ptr +#define __addr_to_pcpu_ptr(addr) \ + (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \ + + (unsigned long)__per_cpu_start) +#endif +#ifndef __pcpu_ptr_to_addr +#define __pcpu_ptr_to_addr(ptr) \ + (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \ + - (unsigned long)__per_cpu_start) +#endif + +struct pcpu_chunk { + struct list_head list; /* linked to pcpu_slot lists */ + struct rb_node rb_node; /* key is chunk->vm->addr */ + int free_size; /* free bytes in the chunk */ + int contig_hint; /* max contiguous size hint */ + struct vm_struct *vm; /* mapped vmalloc region */ + int map_used; /* # of map entries used */ + int map_alloc; /* # of map entries allocated */ + int *map; /* allocation map */ + bool immutable; /* no [de]population allowed */ + struct page **page; /* points to page array */ + struct page *page_ar[]; /* #cpus * UNIT_PAGES */ +}; + +static int pcpu_unit_pages __read_mostly; +static int pcpu_unit_size __read_mostly; +static int pcpu_chunk_size __read_mostly; +static int pcpu_nr_slots __read_mostly; +static size_t pcpu_chunk_struct_size __read_mostly; + +/* the address of the first chunk which starts with the kernel static area */ +void *pcpu_base_addr __read_mostly; +EXPORT_SYMBOL_GPL(pcpu_base_addr); + +/* optional reserved chunk, only accessible for reserved allocations */ +static struct pcpu_chunk *pcpu_reserved_chunk; +/* offset limit of the reserved chunk */ +static int pcpu_reserved_chunk_limit; + +/* + * Synchronization rules. + * + * There are two locks - pcpu_alloc_mutex and pcpu_lock. The former + * protects allocation/reclaim paths, chunks and chunk->page arrays. + * The latter is a spinlock and protects the index data structures - + * chunk slots, rbtree, chunks and area maps in chunks. + * + * During allocation, pcpu_alloc_mutex is kept locked all the time and + * pcpu_lock is grabbed and released as necessary. All actual memory + * allocations are done using GFP_KERNEL with pcpu_lock released. + * + * Free path accesses and alters only the index data structures, so it + * can be safely called from atomic context. When memory needs to be + * returned to the system, free path schedules reclaim_work which + * grabs both pcpu_alloc_mutex and pcpu_lock, unlinks chunks to be + * reclaimed, release both locks and frees the chunks. Note that it's + * necessary to grab both locks to remove a chunk from circulation as + * allocation path might be referencing the chunk with only + * pcpu_alloc_mutex locked. + */ +static DEFINE_MUTEX(pcpu_alloc_mutex); /* protects whole alloc and reclaim */ +static DEFINE_SPINLOCK(pcpu_lock); /* protects index data structures */ + +static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ +static struct rb_root pcpu_addr_root = RB_ROOT; /* chunks by address */ + +/* reclaim work to release fully free chunks, scheduled from free path */ +static void pcpu_reclaim(struct work_struct *work); +static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim); + +static int __pcpu_size_to_slot(int size) +{ + int highbit = fls(size); /* size is in bytes */ + return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); +} + +static int pcpu_size_to_slot(int size) +{ + if (size == pcpu_unit_size) + return pcpu_nr_slots - 1; + return __pcpu_size_to_slot(size); +} + +static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) +{ + if (chunk->free_size < sizeof(int) || chunk->contig_hint < sizeof(int)) + return 0; + + return pcpu_size_to_slot(chunk->free_size); +} + +static int pcpu_page_idx(unsigned int cpu, int page_idx) +{ + return cpu * pcpu_unit_pages + page_idx; +} + +static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return &chunk->page[pcpu_page_idx(cpu, page_idx)]; +} + +static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return (unsigned long)chunk->vm->addr + + (pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT); +} + +static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, + int page_idx) +{ + return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; +} + +/** + * pcpu_mem_alloc - allocate memory + * @size: bytes to allocate + * + * Allocate @size bytes. If @size is smaller than PAGE_SIZE, + * kzalloc() is used; otherwise, vmalloc() is used. The returned + * memory is always zeroed. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Pointer to the allocated area on success, NULL on failure. + */ +static void *pcpu_mem_alloc(size_t size) +{ + if (size <= PAGE_SIZE) + return kzalloc(size, GFP_KERNEL); + else { + void *ptr = vmalloc(size); + if (ptr) + memset(ptr, 0, size); + return ptr; + } +} + +/** + * pcpu_mem_free - free memory + * @ptr: memory to free + * @size: size of the area + * + * Free @ptr. @ptr should have been allocated using pcpu_mem_alloc(). + */ +static void pcpu_mem_free(void *ptr, size_t size) +{ + if (size <= PAGE_SIZE) + kfree(ptr); + else + vfree(ptr); +} + +/** + * pcpu_chunk_relocate - put chunk in the appropriate chunk slot + * @chunk: chunk of interest + * @oslot: the previous slot it was on + * + * This function is called after an allocation or free changed @chunk. + * New slot according to the changed state is determined and @chunk is + * moved to the slot. Note that the reserved chunk is never put on + * chunk slots. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) +{ + int nslot = pcpu_chunk_slot(chunk); + + if (chunk != pcpu_reserved_chunk && oslot != nslot) { + if (oslot < nslot) + list_move(&chunk->list, &pcpu_slot[nslot]); + else + list_move_tail(&chunk->list, &pcpu_slot[nslot]); + } +} + +static struct rb_node **pcpu_chunk_rb_search(void *addr, + struct rb_node **parentp) +{ + struct rb_node **p = &pcpu_addr_root.rb_node; + struct rb_node *parent = NULL; + struct pcpu_chunk *chunk; + + while (*p) { + parent = *p; + chunk = rb_entry(parent, struct pcpu_chunk, rb_node); + + if (addr < chunk->vm->addr) + p = &(*p)->rb_left; + else if (addr > chunk->vm->addr) + p = &(*p)->rb_right; + else + break; + } + + if (parentp) + *parentp = parent; + return p; +} + +/** + * pcpu_chunk_addr_search - search for chunk containing specified address + * @addr: address to search for + * + * Look for chunk which might contain @addr. More specifically, it + * searchs for the chunk with the highest start address which isn't + * beyond @addr. + * + * CONTEXT: + * pcpu_lock. + * + * RETURNS: + * The address of the found chunk. + */ +static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) +{ + struct rb_node *n, *parent; + struct pcpu_chunk *chunk; + + /* is it in the reserved chunk? */ + if (pcpu_reserved_chunk) { + void *start = pcpu_reserved_chunk->vm->addr; + + if (addr >= start && addr < start + pcpu_reserved_chunk_limit) + return pcpu_reserved_chunk; + } + + /* nah... search the regular ones */ + n = *pcpu_chunk_rb_search(addr, &parent); + if (!n) { + /* no exactly matching chunk, the parent is the closest */ + n = parent; + BUG_ON(!n); + } + chunk = rb_entry(n, struct pcpu_chunk, rb_node); + + if (addr < chunk->vm->addr) { + /* the parent was the next one, look for the previous one */ + n = rb_prev(n); + BUG_ON(!n); + chunk = rb_entry(n, struct pcpu_chunk, rb_node); + } + + return chunk; +} + +/** + * pcpu_chunk_addr_insert - insert chunk into address rb tree + * @new: chunk to insert + * + * Insert @new into address rb tree. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_chunk_addr_insert(struct pcpu_chunk *new) +{ + struct rb_node **p, *parent; + + p = pcpu_chunk_rb_search(new->vm->addr, &parent); + BUG_ON(*p); + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, &pcpu_addr_root); +} + +/** + * pcpu_extend_area_map - extend area map for allocation + * @chunk: target chunk + * + * Extend area map of @chunk so that it can accomodate an allocation. + * A single allocation can split an area into three areas, so this + * function makes sure that @chunk->map has at least two extra slots. + * + * CONTEXT: + * pcpu_alloc_mutex, pcpu_lock. pcpu_lock is released and reacquired + * if area map is extended. + * + * RETURNS: + * 0 if noop, 1 if successfully extended, -errno on failure. + */ +static int pcpu_extend_area_map(struct pcpu_chunk *chunk) +{ + int new_alloc; + int *new; + size_t size; + + /* has enough? */ + if (chunk->map_alloc >= chunk->map_used + 2) + return 0; + + spin_unlock_irq(&pcpu_lock); + + new_alloc = PCPU_DFL_MAP_ALLOC; + while (new_alloc < chunk->map_used + 2) + new_alloc *= 2; + + new = pcpu_mem_alloc(new_alloc * sizeof(new[0])); + if (!new) { + spin_lock_irq(&pcpu_lock); + return -ENOMEM; + } + + /* + * Acquire pcpu_lock and switch to new area map. Only free + * could have happened inbetween, so map_used couldn't have + * grown. + */ + spin_lock_irq(&pcpu_lock); + BUG_ON(new_alloc < chunk->map_used + 2); + + size = chunk->map_alloc * sizeof(chunk->map[0]); + memcpy(new, chunk->map, size); + + /* + * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is + * one of the first chunks and still using static map. + */ + if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC) + pcpu_mem_free(chunk->map, size); + + chunk->map_alloc = new_alloc; + chunk->map = new; + return 0; +} + +/** + * pcpu_split_block - split a map block + * @chunk: chunk of interest + * @i: index of map block to split + * @head: head size in bytes (can be 0) + * @tail: tail size in bytes (can be 0) + * + * Split the @i'th map block into two or three blocks. If @head is + * non-zero, @head bytes block is inserted before block @i moving it + * to @i+1 and reducing its size by @head bytes. + * + * If @tail is non-zero, the target block, which can be @i or @i+1 + * depending on @head, is reduced by @tail bytes and @tail byte block + * is inserted after the target block. + * + * @chunk->map must have enough free slots to accomodate the split. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_split_block(struct pcpu_chunk *chunk, int i, + int head, int tail) +{ + int nr_extra = !!head + !!tail; + + BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra); + + /* insert new subblocks */ + memmove(&chunk->map[i + nr_extra], &chunk->map[i], + sizeof(chunk->map[0]) * (chunk->map_used - i)); + chunk->map_used += nr_extra; + + if (head) { + chunk->map[i + 1] = chunk->map[i] - head; + chunk->map[i++] = head; + } + if (tail) { + chunk->map[i++] -= tail; + chunk->map[i] = tail; + } +} + +/** + * pcpu_alloc_area - allocate area from a pcpu_chunk + * @chunk: chunk of interest + * @size: wanted size in bytes + * @align: wanted align + * + * Try to allocate @size bytes area aligned at @align from @chunk. + * Note that this function only allocates the offset. It doesn't + * populate or map the area. + * + * @chunk->map must have at least two free slots. + * + * CONTEXT: + * pcpu_lock. + * + * RETURNS: + * Allocated offset in @chunk on success, -1 if no matching area is + * found. + */ +static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) +{ + int oslot = pcpu_chunk_slot(chunk); + int max_contig = 0; + int i, off; + + for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) { + bool is_last = i + 1 == chunk->map_used; + int head, tail; + + /* extra for alignment requirement */ + head = ALIGN(off, align) - off; + BUG_ON(i == 0 && head != 0); + + if (chunk->map[i] < 0) + continue; + if (chunk->map[i] < head + size) { + max_contig = max(chunk->map[i], max_contig); + continue; + } + + /* + * If head is small or the previous block is free, + * merge'em. Note that 'small' is defined as smaller + * than sizeof(int), which is very small but isn't too + * uncommon for percpu allocations. + */ + if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) { + if (chunk->map[i - 1] > 0) + chunk->map[i - 1] += head; + else { + chunk->map[i - 1] -= head; + chunk->free_size -= head; + } + chunk->map[i] -= head; + off += head; + head = 0; + } + + /* if tail is small, just keep it around */ + tail = chunk->map[i] - head - size; + if (tail < sizeof(int)) + tail = 0; + + /* split if warranted */ + if (head || tail) { + pcpu_split_block(chunk, i, head, tail); + if (head) { + i++; + off += head; + max_contig = max(chunk->map[i - 1], max_contig); + } + if (tail) + max_contig = max(chunk->map[i + 1], max_contig); + } + + /* update hint and mark allocated */ + if (is_last) + chunk->contig_hint = max_contig; /* fully scanned */ + else + chunk->contig_hint = max(chunk->contig_hint, + max_contig); + + chunk->free_size -= chunk->map[i]; + chunk->map[i] = -chunk->map[i]; + + pcpu_chunk_relocate(chunk, oslot); + return off; + } + + chunk->contig_hint = max_contig; /* fully scanned */ + pcpu_chunk_relocate(chunk, oslot); + + /* tell the upper layer that this chunk has no matching area */ + return -1; +} + +/** + * pcpu_free_area - free area to a pcpu_chunk + * @chunk: chunk of interest + * @freeme: offset of area to free + * + * Free area starting from @freeme to @chunk. Note that this function + * only modifies the allocation map. It doesn't depopulate or unmap + * the area. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) +{ + int oslot = pcpu_chunk_slot(chunk); + int i, off; + + for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) + if (off == freeme) + break; + BUG_ON(off != freeme); + BUG_ON(chunk->map[i] > 0); + + chunk->map[i] = -chunk->map[i]; + chunk->free_size += chunk->map[i]; + + /* merge with previous? */ + if (i > 0 && chunk->map[i - 1] >= 0) { + chunk->map[i - 1] += chunk->map[i]; + chunk->map_used--; + memmove(&chunk->map[i], &chunk->map[i + 1], + (chunk->map_used - i) * sizeof(chunk->map[0])); + i--; + } + /* merge with next? */ + if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) { + chunk->map[i] += chunk->map[i + 1]; + chunk->map_used--; + memmove(&chunk->map[i + 1], &chunk->map[i + 2], + (chunk->map_used - (i + 1)) * sizeof(chunk->map[0])); + } + + chunk->contig_hint = max(chunk->map[i], chunk->contig_hint); + pcpu_chunk_relocate(chunk, oslot); +} + +/** + * pcpu_unmap - unmap pages out of a pcpu_chunk + * @chunk: chunk of interest + * @page_start: page index of the first page to unmap + * @page_end: page index of the last page to unmap + 1 + * @flush: whether to flush cache and tlb or not + * + * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. + * If @flush is true, vcache is flushed before unmapping and tlb + * after. + */ +static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, + bool flush) +{ + unsigned int last = num_possible_cpus() - 1; + unsigned int cpu; + + /* unmap must not be done on immutable chunk */ + WARN_ON(chunk->immutable); + + /* + * Each flushing trial can be very expensive, issue flush on + * the whole region at once rather than doing it for each cpu. + * This could be an overkill but is more scalable. + */ + if (flush) + flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); + + for_each_possible_cpu(cpu) + unmap_kernel_range_noflush( + pcpu_chunk_addr(chunk, cpu, page_start), + (page_end - page_start) << PAGE_SHIFT); + + /* ditto as flush_cache_vunmap() */ + if (flush) + flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); +} + +/** + * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk + * @chunk: chunk to depopulate + * @off: offset to the area to depopulate + * @size: size of the area to depopulate in bytes + * @flush: whether to flush cache and tlb or not + * + * For each cpu, depopulate and unmap pages [@page_start,@page_end) + * from @chunk. If @flush is true, vcache is flushed before unmapping + * and tlb after. + * + * CONTEXT: + * pcpu_alloc_mutex. + */ +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size, + bool flush) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int unmap_start = -1; + int uninitialized_var(unmap_end); + unsigned int cpu; + int i; + + for (i = page_start; i < page_end; i++) { + for_each_possible_cpu(cpu) { + struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + + if (!*pagep) + continue; + + __free_page(*pagep); + + /* + * If it's partial depopulation, it might get + * populated or depopulated again. Mark the + * page gone. + */ + *pagep = NULL; + + unmap_start = unmap_start < 0 ? i : unmap_start; + unmap_end = i + 1; + } + } + + if (unmap_start >= 0) + pcpu_unmap(chunk, unmap_start, unmap_end, flush); +} + +/** + * pcpu_map - map pages into a pcpu_chunk + * @chunk: chunk of interest + * @page_start: page index of the first page to map + * @page_end: page index of the last page to map + 1 + * + * For each cpu, map pages [@page_start,@page_end) into @chunk. + * vcache is flushed afterwards. + */ +static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) +{ + unsigned int last = num_possible_cpus() - 1; + unsigned int cpu; + int err; + + /* map must not be done on immutable chunk */ + WARN_ON(chunk->immutable); + + for_each_possible_cpu(cpu) { + err = map_kernel_range_noflush( + pcpu_chunk_addr(chunk, cpu, page_start), + (page_end - page_start) << PAGE_SHIFT, + PAGE_KERNEL, + pcpu_chunk_pagep(chunk, cpu, page_start)); + if (err < 0) + return err; + } + + /* flush at once, please read comments in pcpu_unmap() */ + flush_cache_vmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); + return 0; +} + +/** + * pcpu_populate_chunk - populate and map an area of a pcpu_chunk + * @chunk: chunk of interest + * @off: offset to the area to populate + * @size: size of the area to populate in bytes + * + * For each cpu, populate and map pages [@page_start,@page_end) into + * @chunk. The area is cleared on return. + * + * CONTEXT: + * pcpu_alloc_mutex, does GFP_KERNEL allocation. + */ +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + const gfp_t alloc_mask = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int map_start = -1; + int uninitialized_var(map_end); + unsigned int cpu; + int i; + + for (i = page_start; i < page_end; i++) { + if (pcpu_chunk_page_occupied(chunk, i)) { + if (map_start >= 0) { + if (pcpu_map(chunk, map_start, map_end)) + goto err; + map_start = -1; + } + continue; + } + + map_start = map_start < 0 ? i : map_start; + map_end = i + 1; + + for_each_possible_cpu(cpu) { + struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + + *pagep = alloc_pages_node(cpu_to_node(cpu), + alloc_mask, 0); + if (!*pagep) + goto err; + } + } + + if (map_start >= 0 && pcpu_map(chunk, map_start, map_end)) + goto err; + + for_each_possible_cpu(cpu) + memset(chunk->vm->addr + cpu * pcpu_unit_size + off, 0, + size); + + return 0; +err: + /* likely under heavy memory pressure, give memory back */ + pcpu_depopulate_chunk(chunk, off, size, true); + return -ENOMEM; +} + +static void free_pcpu_chunk(struct pcpu_chunk *chunk) +{ + if (!chunk) + return; + if (chunk->vm) + free_vm_area(chunk->vm); + pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); + kfree(chunk); +} + +static struct pcpu_chunk *alloc_pcpu_chunk(void) +{ + struct pcpu_chunk *chunk; + + chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); + if (!chunk) + return NULL; + + chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); + chunk->map_alloc = PCPU_DFL_MAP_ALLOC; + chunk->map[chunk->map_used++] = pcpu_unit_size; + chunk->page = chunk->page_ar; + + chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL); + if (!chunk->vm) { + free_pcpu_chunk(chunk); + return NULL; + } + + INIT_LIST_HEAD(&chunk->list); + chunk->free_size = pcpu_unit_size; + chunk->contig_hint = pcpu_unit_size; + + return chunk; +} + +/** + * pcpu_alloc - the percpu allocator + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * @reserved: allocate from the reserved chunk if available + * + * Allocate percpu area of @size bytes aligned at @align. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +static void *pcpu_alloc(size_t size, size_t align, bool reserved) +{ + struct pcpu_chunk *chunk; + int slot, off; + + if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { + WARN(true, "illegal size (%zu) or align (%zu) for " + "percpu allocation\n", size, align); + return NULL; + } + + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irq(&pcpu_lock); + + /* serve reserved allocations from the reserved chunk if available */ + if (reserved && pcpu_reserved_chunk) { + chunk = pcpu_reserved_chunk; + if (size > chunk->contig_hint || + pcpu_extend_area_map(chunk) < 0) + goto fail_unlock; + off = pcpu_alloc_area(chunk, size, align); + if (off >= 0) + goto area_found; + goto fail_unlock; + } + +restart: + /* search through normal chunks */ + for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { + list_for_each_entry(chunk, &pcpu_slot[slot], list) { + if (size > chunk->contig_hint) + continue; + + switch (pcpu_extend_area_map(chunk)) { + case 0: + break; + case 1: + goto restart; /* pcpu_lock dropped, restart */ + default: + goto fail_unlock; + } + + off = pcpu_alloc_area(chunk, size, align); + if (off >= 0) + goto area_found; + } + } + + /* hmmm... no space left, create a new chunk */ + spin_unlock_irq(&pcpu_lock); + + chunk = alloc_pcpu_chunk(); + if (!chunk) + goto fail_unlock_mutex; + + spin_lock_irq(&pcpu_lock); + pcpu_chunk_relocate(chunk, -1); + pcpu_chunk_addr_insert(chunk); + goto restart; + +area_found: + spin_unlock_irq(&pcpu_lock); + + /* populate, map and clear the area */ + if (pcpu_populate_chunk(chunk, off, size)) { + spin_lock_irq(&pcpu_lock); + pcpu_free_area(chunk, off); + goto fail_unlock; + } + + mutex_unlock(&pcpu_alloc_mutex); + + return __addr_to_pcpu_ptr(chunk->vm->addr + off); + +fail_unlock: + spin_unlock_irq(&pcpu_lock); +fail_unlock_mutex: + mutex_unlock(&pcpu_alloc_mutex); + return NULL; +} + +/** + * __alloc_percpu - allocate dynamic percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align. Might + * sleep. Might trigger writeouts. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, false); +} +EXPORT_SYMBOL_GPL(__alloc_percpu); + +/** + * __alloc_reserved_percpu - allocate reserved percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align from reserved + * percpu area if arch has set it up; otherwise, allocation is served + * from the same dynamic area. Might sleep. Might trigger writeouts. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_reserved_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, true); +} + +/** + * pcpu_reclaim - reclaim fully free chunks, workqueue function + * @work: unused + * + * Reclaim all fully free chunks except for the first one. + * + * CONTEXT: + * workqueue context. + */ +static void pcpu_reclaim(struct work_struct *work) +{ + LIST_HEAD(todo); + struct list_head *head = &pcpu_slot[pcpu_nr_slots - 1]; + struct pcpu_chunk *chunk, *next; + + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irq(&pcpu_lock); + + list_for_each_entry_safe(chunk, next, head, list) { + WARN_ON(chunk->immutable); + + /* spare the first one */ + if (chunk == list_first_entry(head, struct pcpu_chunk, list)) + continue; + + rb_erase(&chunk->rb_node, &pcpu_addr_root); + list_move(&chunk->list, &todo); + } + + spin_unlock_irq(&pcpu_lock); + mutex_unlock(&pcpu_alloc_mutex); + + list_for_each_entry_safe(chunk, next, &todo, list) { + pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false); + free_pcpu_chunk(chunk); + } +} + +/** + * free_percpu - free percpu area + * @ptr: pointer to area to free + * + * Free percpu area @ptr. + * + * CONTEXT: + * Can be called from atomic context. + */ +void free_percpu(void *ptr) +{ + void *addr = __pcpu_ptr_to_addr(ptr); + struct pcpu_chunk *chunk; + unsigned long flags; + int off; + + if (!ptr) + return; + + spin_lock_irqsave(&pcpu_lock, flags); + + chunk = pcpu_chunk_addr_search(addr); + off = addr - chunk->vm->addr; + + pcpu_free_area(chunk, off); + + /* if there are more than one fully free chunks, wake up grim reaper */ + if (chunk->free_size == pcpu_unit_size) { + struct pcpu_chunk *pos; + + list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list) + if (pos != chunk) { + schedule_work(&pcpu_reclaim_work); + break; + } + } + + spin_unlock_irqrestore(&pcpu_lock, flags); +} +EXPORT_SYMBOL_GPL(free_percpu); + +/** + * pcpu_setup_first_chunk - initialize the first percpu chunk + * @get_page_fn: callback to fetch page pointer + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_size: free size for dynamic allocation in bytes, -1 for auto + * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * @base_addr: mapped address, NULL for auto + * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary + * + * Initialize the first percpu chunk which contains the kernel static + * perpcu area. This function is to be called from arch percpu area + * setup path. The first two parameters are mandatory. The rest are + * optional. + * + * @get_page_fn() should return pointer to percpu page given cpu + * number and page number. It should at least return enough pages to + * cover the static area. The returned pages for static area should + * have been initialized with valid data. If @unit_size is specified, + * it can also return pages after the static area. NULL return + * indicates end of pages for the cpu. Note that @get_page_fn() must + * return the same number of pages for all cpus. + * + * @reserved_size, if non-zero, specifies the amount of bytes to + * reserve after the static area in the first chunk. This reserves + * the first chunk such that it's available only through reserved + * percpu allocation. This is primarily used to serve module percpu + * static areas on architectures where the addressing model has + * limited offset range for symbol relocations to guarantee module + * percpu symbols fall inside the relocatable range. + * + * @dyn_size, if non-negative, determines the number of bytes + * available for dynamic allocation in the first chunk. Specifying + * non-negative value makes percpu leave alone the area beyond + * @static_size + @reserved_size + @dyn_size. + * + * @unit_size, if non-negative, specifies unit size and must be + * aligned to PAGE_SIZE and equal to or larger than @static_size + + * @reserved_size + if non-negative, @dyn_size. + * + * Non-null @base_addr means that the caller already allocated virtual + * region for the first chunk and mapped it. percpu must not mess + * with the chunk. Note that @base_addr with 0 @unit_size or non-NULL + * @populate_pte_fn doesn't make any sense. + * + * @populate_pte_fn is used to populate the pagetable. NULL means the + * caller already populated the pagetable. + * + * If the first chunk ends up with both reserved and dynamic areas, it + * is served by two chunks - one to serve the core static and reserved + * areas and the other for the dynamic area. They share the same vm + * and page map but uses different area allocation map to stay away + * from each other. The latter chunk is circulated in the chunk slots + * and available for dynamic allocation like any other chunks. + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access. + */ +size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, + size_t static_size, size_t reserved_size, + ssize_t dyn_size, ssize_t unit_size, + void *base_addr, + pcpu_populate_pte_fn_t populate_pte_fn) +{ + static struct vm_struct first_vm; + static int smap[2], dmap[2]; + size_t size_sum = static_size + reserved_size + + (dyn_size >= 0 ? dyn_size : 0); + struct pcpu_chunk *schunk, *dchunk = NULL; + unsigned int cpu; + int nr_pages; + int err, i; + + /* santiy checks */ + BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC || + ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC); + BUG_ON(!static_size); + if (unit_size >= 0) { + BUG_ON(unit_size < size_sum); + BUG_ON(unit_size & ~PAGE_MASK); + BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE); + } else + BUG_ON(base_addr); + BUG_ON(base_addr && populate_pte_fn); + + if (unit_size >= 0) + pcpu_unit_pages = unit_size >> PAGE_SHIFT; + else + pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, + PFN_UP(size_sum)); + + pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; + pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size; + pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + + num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *); + + if (dyn_size < 0) + dyn_size = pcpu_unit_size - static_size - reserved_size; + + /* + * Allocate chunk slots. The additional last slot is for + * empty chunks. + */ + pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; + pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0])); + for (i = 0; i < pcpu_nr_slots; i++) + INIT_LIST_HEAD(&pcpu_slot[i]); + + /* + * Initialize static chunk. If reserved_size is zero, the + * static chunk covers static area + dynamic allocation area + * in the first chunk. If reserved_size is not zero, it + * covers static area + reserved area (mostly used for module + * static percpu allocation). + */ + schunk = alloc_bootmem(pcpu_chunk_struct_size); + INIT_LIST_HEAD(&schunk->list); + schunk->vm = &first_vm; + schunk->map = smap; + schunk->map_alloc = ARRAY_SIZE(smap); + schunk->page = schunk->page_ar; + + if (reserved_size) { + schunk->free_size = reserved_size; + pcpu_reserved_chunk = schunk; /* not for dynamic alloc */ + } else { + schunk->free_size = dyn_size; + dyn_size = 0; /* dynamic area covered */ + } + schunk->contig_hint = schunk->free_size; + + schunk->map[schunk->map_used++] = -static_size; + if (schunk->free_size) + schunk->map[schunk->map_used++] = schunk->free_size; + + pcpu_reserved_chunk_limit = static_size + schunk->free_size; + + /* init dynamic chunk if necessary */ + if (dyn_size) { + dchunk = alloc_bootmem(sizeof(struct pcpu_chunk)); + INIT_LIST_HEAD(&dchunk->list); + dchunk->vm = &first_vm; + dchunk->map = dmap; + dchunk->map_alloc = ARRAY_SIZE(dmap); + dchunk->page = schunk->page_ar; /* share page map with schunk */ + + dchunk->contig_hint = dchunk->free_size = dyn_size; + dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit; + dchunk->map[dchunk->map_used++] = dchunk->free_size; + } + + /* allocate vm address */ + first_vm.flags = VM_ALLOC; + first_vm.size = pcpu_chunk_size; + + if (!base_addr) + vm_area_register_early(&first_vm, PAGE_SIZE); + else { + /* + * Pages already mapped. No need to remap into + * vmalloc area. In this case the first chunks can't + * be mapped or unmapped by percpu and are marked + * immutable. + */ + first_vm.addr = base_addr; + schunk->immutable = true; + if (dchunk) + dchunk->immutable = true; + } + + /* assign pages */ + nr_pages = -1; + for_each_possible_cpu(cpu) { + for (i = 0; i < pcpu_unit_pages; i++) { + struct page *page = get_page_fn(cpu, i); + + if (!page) + break; + *pcpu_chunk_pagep(schunk, cpu, i) = page; + } + + BUG_ON(i < PFN_UP(static_size)); + + if (nr_pages < 0) + nr_pages = i; + else + BUG_ON(nr_pages != i); + } + + /* map them */ + if (populate_pte_fn) { + for_each_possible_cpu(cpu) + for (i = 0; i < nr_pages; i++) + populate_pte_fn(pcpu_chunk_addr(schunk, + cpu, i)); + + err = pcpu_map(schunk, 0, nr_pages); + if (err) + panic("failed to setup static percpu area, err=%d\n", + err); + } + + /* link the first chunk in */ + if (!dchunk) { + pcpu_chunk_relocate(schunk, -1); + pcpu_chunk_addr_insert(schunk); + } else { + pcpu_chunk_relocate(dchunk, -1); + pcpu_chunk_addr_insert(dchunk); + } + + /* we're done */ + pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); + return pcpu_unit_size; +} + +/* + * Embedding first chunk setup helper. + */ +static void *pcpue_ptr __initdata; +static size_t pcpue_size __initdata; +static size_t pcpue_unit_size __initdata; + +static struct page * __init pcpue_get_page(unsigned int cpu, int pageno) +{ + size_t off = (size_t)pageno << PAGE_SHIFT; + + if (off >= pcpue_size) + return NULL; + + return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off); +} + +/** + * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_size: free size for dynamic allocation in bytes, -1 for auto + * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * + * This is a helper to ease setting up embedded first percpu chunk and + * can be called where pcpu_setup_first_chunk() is expected. + * + * If this function is used to setup the first chunk, it is allocated + * as a contiguous area using bootmem allocator and used as-is without + * being mapped into vmalloc area. This enables the first chunk to + * piggy back on the linear physical mapping which often uses larger + * page size. + * + * When @dyn_size is positive, dynamic area might be larger than + * specified to fill page alignment. Also, when @dyn_size is auto, + * @dyn_size does not fill the whole first chunk but only what's + * necessary for page alignment after static and reserved areas. + * + * If the needed size is smaller than the minimum or specified unit + * size, the leftover is returned to the bootmem allocator. + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access on success, -errno on failure. + */ +ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, + ssize_t dyn_size, ssize_t unit_size) +{ + unsigned int cpu; + + /* determine parameters and allocate */ + pcpue_size = PFN_ALIGN(static_size + reserved_size + + (dyn_size >= 0 ? dyn_size : 0)); + if (dyn_size != 0) + dyn_size = pcpue_size - static_size - reserved_size; + + if (unit_size >= 0) { + BUG_ON(unit_size < pcpue_size); + pcpue_unit_size = unit_size; + } else + pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); + + pcpue_ptr = __alloc_bootmem_nopanic( + num_possible_cpus() * pcpue_unit_size, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + if (!pcpue_ptr) + return -ENOMEM; + + /* return the leftover and copy */ + for_each_possible_cpu(cpu) { + void *ptr = pcpue_ptr + cpu * pcpue_unit_size; + + free_bootmem(__pa(ptr + pcpue_size), + pcpue_unit_size - pcpue_size); + memcpy(ptr, __per_cpu_load, static_size); + } + + /* we're ready, commit */ + pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", + pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); + + return pcpu_setup_first_chunk(pcpue_get_page, static_size, + reserved_size, dyn_size, + pcpue_unit_size, pcpue_ptr, NULL); +} diff --git a/mm/readahead.c b/mm/readahead.c index bec83c15a78f..9ce303d4b810 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -17,19 +17,6 @@ #include <linux/pagevec.h> #include <linux/pagemap.h> -void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) -{ -} -EXPORT_SYMBOL(default_unplug_io_fn); - -struct backing_dev_info default_backing_dev_info = { - .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, - .state = 0, - .capabilities = BDI_CAP_MAP_COPY, - .unplug_io_fn = default_unplug_io_fn, -}; -EXPORT_SYMBOL_GPL(default_backing_dev_info); - /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. @@ -233,18 +220,6 @@ unsigned long max_sane_readahead(unsigned long nr) + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2); } -static int __init readahead_init(void) -{ - int err; - - err = bdi_init(&default_backing_dev_info); - if (!err) - bdi_register(&default_backing_dev_info, NULL, "default"); - - return err; -} -subsys_initcall(readahead_init); - /* * Submit IO for the read-ahead request in file_ra_state. */ diff --git a/mm/rmap.c b/mm/rmap.c index ac4af8cffbf9..16521664010d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1072,7 +1072,8 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration) spin_lock(&mapping->i_mmap_lock); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { if (MLOCK_PAGES && unlikely(unlock)) { - if (!(vma->vm_flags & VM_LOCKED)) + if (!((vma->vm_flags & VM_LOCKED) && + page_mapped_in_vma(page, vma))) continue; /* must visit all vmas */ ret = SWAP_MLOCK; } else { diff --git a/mm/shmem.c b/mm/shmem.c index 19d566ccdeea..7ec78e24a30d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -28,6 +28,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/swap.h> +#include <linux/ima.h> static struct vfsmount *shm_mnt; @@ -169,13 +170,13 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { - return (flags & VM_ACCOUNT) ? - security_vm_enough_memory_kern(VM_ACCT(size)) : 0; + return (flags & VM_NORESERVE) ? + 0 : security_vm_enough_memory_kern(VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { - if (flags & VM_ACCOUNT) + if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } @@ -187,13 +188,13 @@ static inline void shmem_unacct_size(unsigned long flags, loff_t size) */ static inline int shmem_acct_block(unsigned long flags) { - return (flags & VM_ACCOUNT) ? - 0 : security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)); + return (flags & VM_NORESERVE) ? + security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0; } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { - if (!(flags & VM_ACCOUNT)) + if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE)); } @@ -1515,8 +1516,8 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static struct inode * -shmem_get_inode(struct super_block *sb, int mode, dev_t dev) +static struct inode *shmem_get_inode(struct super_block *sb, int mode, + dev_t dev, unsigned long flags) { struct inode *inode; struct shmem_inode_info *info; @@ -1537,6 +1538,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); + info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->swaplist); switch (mode & S_IFMT) { @@ -1779,9 +1781,10 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) static int shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) { - struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev); + struct inode *inode; int error = -ENOSPC; + inode = shmem_get_inode(dir->i_sb, mode, dev, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, NULL, NULL, NULL); @@ -1920,7 +1923,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (len > PAGE_CACHE_SIZE) return -ENAMETOOLONG; - inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0); + inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE); if (!inode) return -ENOSPC; @@ -2332,7 +2335,7 @@ static int shmem_fill_super(struct super_block *sb, sb->s_flags |= MS_POSIXACL; #endif - inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0); + inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (!inode) goto failed; inode->i_uid = sbinfo->uid; @@ -2574,12 +2577,12 @@ int shmem_unuse(swp_entry_t entry, struct page *page) return 0; } -#define shmem_file_operations ramfs_file_operations -#define shmem_vm_ops generic_file_vm_ops -#define shmem_get_inode ramfs_get_inode -#define shmem_acct_size(a, b) 0 -#define shmem_unacct_size(a, b) do {} while (0) -#define SHMEM_MAX_BYTES LLONG_MAX +#define shmem_vm_ops generic_file_vm_ops +#define shmem_file_operations ramfs_file_operations +#define shmem_get_inode(sb, mode, dev, flags) ramfs_get_inode(sb, mode, dev) +#define shmem_acct_size(flags, size) 0 +#define shmem_unacct_size(flags, size) do {} while (0) +#define SHMEM_MAX_BYTES LLONG_MAX #endif /* CONFIG_SHMEM */ @@ -2589,7 +2592,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page) * shmem_file_setup - get an unlinked file living in tmpfs * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file - * @flags: vm_flags + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) { @@ -2623,13 +2626,10 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) goto put_dentry; error = -ENOSPC; - inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0); + inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0, flags); if (!inode) goto close_file; -#ifdef CONFIG_SHMEM - SHMEM_I(inode)->flags = (flags & VM_NORESERVE) ? 0 : VM_ACCOUNT; -#endif d_instantiate(dentry, inode); inode->i_size = size; inode->i_nlink = 0; /* It is unlinked */ @@ -2666,6 +2666,7 @@ int shmem_zero_setup(struct vm_area_struct *vma) if (IS_ERR(file)) return PTR_ERR(file); + ima_shm_check(file); if (vma->vm_file) fput(vma->vm_file); vma->vm_file = file; diff --git a/mm/slab.c b/mm/slab.c index 6b61de8543ec..825c606f691d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4461,3 +4461,4 @@ size_t ksize(const void *objp) return obj_size(virt_to_cache(objp)); } +EXPORT_SYMBOL(ksize); diff --git a/mm/slob.c b/mm/slob.c index 4b1c0c1d63cb..7a3411524dac 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -126,9 +126,9 @@ static LIST_HEAD(free_slob_medium); static LIST_HEAD(free_slob_large); /* - * slob_page: True for all slob pages (false for bigblock pages) + * is_slob_page: True for all slob pages (false for bigblock pages) */ -static inline int slob_page(struct slob_page *sp) +static inline int is_slob_page(struct slob_page *sp) { return PageSlobPage((struct page *)sp); } @@ -143,6 +143,11 @@ static inline void clear_slob_page(struct slob_page *sp) __ClearPageSlobPage((struct page *)sp); } +static inline struct slob_page *slob_page(const void *addr) +{ + return (struct slob_page *)virt_to_page(addr); +} + /* * slob_page_free: true for pages on free_slob_pages list. */ @@ -230,7 +235,7 @@ static int slob_last(slob_t *s) return !((unsigned long)slob_next(s) & ~PAGE_MASK); } -static void *slob_new_page(gfp_t gfp, int order, int node) +static void *slob_new_pages(gfp_t gfp, int order, int node) { void *page; @@ -247,12 +252,17 @@ static void *slob_new_page(gfp_t gfp, int order, int node) return page_address(page); } +static void slob_free_pages(void *b, int order) +{ + free_pages((unsigned long)b, order); +} + /* * Allocate a slob block within a given slob_page sp. */ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align) { - slob_t *prev, *cur, *aligned = 0; + slob_t *prev, *cur, *aligned = NULL; int delta = 0, units = SLOB_UNITS(size); for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) { @@ -349,10 +359,10 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) /* Not enough space: must allocate a new page */ if (!b) { - b = slob_new_page(gfp & ~__GFP_ZERO, 0, node); + b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node); if (!b) - return 0; - sp = (struct slob_page *)virt_to_page(b); + return NULL; + sp = slob_page(b); set_slob_page(sp); spin_lock_irqsave(&slob_lock, flags); @@ -384,7 +394,7 @@ static void slob_free(void *block, int size) return; BUG_ON(!size); - sp = (struct slob_page *)virt_to_page(block); + sp = slob_page(block); units = SLOB_UNITS(size); spin_lock_irqsave(&slob_lock, flags); @@ -393,10 +403,11 @@ static void slob_free(void *block, int size) /* Go directly to page allocator. Do not pass slob allocator */ if (slob_page_free(sp)) clear_slob_page_free(sp); + spin_unlock_irqrestore(&slob_lock, flags); clear_slob_page(sp); free_slob_page(sp); free_page((unsigned long)b); - goto out; + return; } if (!slob_page_free(sp)) { @@ -478,7 +489,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) } else { void *ret; - ret = slob_new_page(gfp | __GFP_COMP, get_order(size), node); + ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node); if (ret) { struct page *page; page = virt_to_page(ret); @@ -496,8 +507,8 @@ void kfree(const void *block) if (unlikely(ZERO_OR_NULL_PTR(block))) return; - sp = (struct slob_page *)virt_to_page(block); - if (slob_page(sp)) { + sp = slob_page(block); + if (is_slob_page(sp)) { int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); @@ -515,14 +526,15 @@ size_t ksize(const void *block) if (unlikely(block == ZERO_SIZE_PTR)) return 0; - sp = (struct slob_page *)virt_to_page(block); - if (slob_page(sp)) { + sp = slob_page(block); + if (is_slob_page(sp)) { int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); return SLOB_UNITS(*m) * SLOB_UNIT; } else return sp->page.private; } +EXPORT_SYMBOL(ksize); struct kmem_cache { unsigned int size, align; @@ -574,7 +586,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) if (c->size < PAGE_SIZE) b = slob_alloc(c->size, flags, c->align, node); else - b = slob_new_page(flags, get_order(c->size), node); + b = slob_new_pages(flags, get_order(c->size), node); if (c->ctor) c->ctor(b); @@ -588,7 +600,7 @@ static void __kmem_cache_free(void *b, int size) if (size < PAGE_SIZE) slob_free(b, size); else - free_pages((unsigned long)b, get_order(size)); + slob_free_pages(b, get_order(size)); } static void kmem_rcu_free(struct rcu_head *head) diff --git a/mm/slub.c b/mm/slub.c index 214eb207c513..c4ea9158c9fb 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -374,14 +374,8 @@ static struct track *get_track(struct kmem_cache *s, void *object, static void set_track(struct kmem_cache *s, void *object, enum track_item alloc, unsigned long addr) { - struct track *p; - - if (s->offset) - p = object + s->offset + sizeof(void *); - else - p = object + s->inuse; + struct track *p = get_track(s, object, alloc); - p += alloc; if (addr) { p->addr = addr; p->cpu = smp_processor_id(); @@ -1335,7 +1329,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) n = get_node(s, zone_to_nid(zone)); if (n && cpuset_zone_allowed_hardwall(zone, flags) && - n->nr_partial > n->min_partial) { + n->nr_partial > s->min_partial) { page = get_partial_node(n); if (page) return page; @@ -1387,7 +1381,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail) slab_unlock(page); } else { stat(c, DEACTIVATE_EMPTY); - if (n->nr_partial < n->min_partial) { + if (n->nr_partial < s->min_partial) { /* * Adding an empty slab to the partial slabs in order * to avoid page allocator overhead. This slab needs @@ -1725,7 +1719,7 @@ static __always_inline void slab_free(struct kmem_cache *s, c = get_cpu_slab(s, smp_processor_id()); debug_check_no_locks_freed(object, c->objsize); if (!(s->flags & SLAB_DEBUG_OBJECTS)) - debug_check_no_obj_freed(object, s->objsize); + debug_check_no_obj_freed(object, c->objsize); if (likely(page == c->page && c->node >= 0)) { object[c->offset] = c->freelist; c->freelist = object; @@ -1845,6 +1839,7 @@ static inline int calculate_order(int size) int order; int min_objects; int fraction; + int max_objects; /* * Attempt to find best configuration for a slab. This @@ -1857,6 +1852,9 @@ static inline int calculate_order(int size) min_objects = slub_min_objects; if (!min_objects) min_objects = 4 * (fls(nr_cpu_ids) + 1); + max_objects = (PAGE_SIZE << slub_max_order)/size; + min_objects = min(min_objects, max_objects); + while (min_objects > 1) { fraction = 16; while (fraction >= 4) { @@ -1866,7 +1864,7 @@ static inline int calculate_order(int size) return order; fraction /= 2; } - min_objects /= 2; + min_objects --; } /* @@ -1929,17 +1927,6 @@ static void init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s) { n->nr_partial = 0; - - /* - * The larger the object size is, the more pages we want on the partial - * list to avoid pounding the page allocator excessively. - */ - n->min_partial = ilog2(s->size); - if (n->min_partial < MIN_PARTIAL) - n->min_partial = MIN_PARTIAL; - else if (n->min_partial > MAX_PARTIAL) - n->min_partial = MAX_PARTIAL; - spin_lock_init(&n->list_lock); INIT_LIST_HEAD(&n->partial); #ifdef CONFIG_SLUB_DEBUG @@ -2182,6 +2169,15 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags) } #endif +static void set_min_partial(struct kmem_cache *s, unsigned long min) +{ + if (min < MIN_PARTIAL) + min = MIN_PARTIAL; + else if (min > MAX_PARTIAL) + min = MAX_PARTIAL; + s->min_partial = min; +} + /* * calculate_sizes() determines the order and the distribution of data within * a slab object. @@ -2320,6 +2316,11 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags, if (!calculate_sizes(s, -1)) goto error; + /* + * The larger the object size is, the more pages we want on the partial + * list to avoid pounding the page allocator excessively. + */ + set_min_partial(s, ilog2(s->size)); s->refcount = 1; #ifdef CONFIG_NUMA s->remote_node_defrag_ratio = 1000; @@ -2476,7 +2477,7 @@ EXPORT_SYMBOL(kmem_cache_destroy); * Kmalloc subsystem *******************************************************************/ -struct kmem_cache kmalloc_caches[PAGE_SHIFT + 1] __cacheline_aligned; +struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT] __cacheline_aligned; EXPORT_SYMBOL(kmalloc_caches); static int __init setup_slub_min_order(char *str) @@ -2538,7 +2539,7 @@ panic: } #ifdef CONFIG_ZONE_DMA -static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT + 1]; +static struct kmem_cache *kmalloc_caches_dma[SLUB_PAGE_SHIFT]; static void sysfs_add_func(struct work_struct *w) { @@ -2659,7 +2660,7 @@ void *__kmalloc(size_t size, gfp_t flags) { struct kmem_cache *s; - if (unlikely(size > PAGE_SIZE)) + if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large(size, flags); s = get_slab(size, flags); @@ -2687,7 +2688,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) { struct kmem_cache *s; - if (unlikely(size > PAGE_SIZE)) + if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large_node(size, flags, node); s = get_slab(size, flags); @@ -2737,6 +2738,7 @@ size_t ksize(const void *object) */ return s->size; } +EXPORT_SYMBOL(ksize); void kfree(const void *x) { @@ -2986,7 +2988,7 @@ void __init kmem_cache_init(void) caches++; } - for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++) { + for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) { create_kmalloc_cache(&kmalloc_caches[i], "kmalloc", 1 << i, GFP_KERNEL); caches++; @@ -3023,7 +3025,7 @@ void __init kmem_cache_init(void) slab_state = UP; /* Provide the correct kmalloc names now that the caches are up */ - for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++) + for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) kmalloc_caches[i]. name = kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i); @@ -3223,7 +3225,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) { struct kmem_cache *s; - if (unlikely(size > PAGE_SIZE)) + if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large(size, gfpflags); s = get_slab(size, gfpflags); @@ -3239,7 +3241,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, { struct kmem_cache *s; - if (unlikely(size > PAGE_SIZE)) + if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large_node(size, gfpflags, node); s = get_slab(size, gfpflags); @@ -3836,6 +3838,26 @@ static ssize_t order_show(struct kmem_cache *s, char *buf) } SLAB_ATTR(order); +static ssize_t min_partial_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%lu\n", s->min_partial); +} + +static ssize_t min_partial_store(struct kmem_cache *s, const char *buf, + size_t length) +{ + unsigned long min; + int err; + + err = strict_strtoul(buf, 10, &min); + if (err) + return err; + + set_min_partial(s, min); + return length; +} +SLAB_ATTR(min_partial); + static ssize_t ctor_show(struct kmem_cache *s, char *buf) { if (s->ctor) { @@ -4151,6 +4173,7 @@ static struct attribute *slab_attrs[] = { &object_size_attr.attr, &objs_per_slab_attr.attr, &order_attr.attr, + &min_partial_attr.attr, &objects_attr.attr, &objects_partial_attr.attr, &total_objects_attr.attr, diff --git a/mm/swapfile.c b/mm/swapfile.c index 7e6304dfafab..312fafe0ab6e 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -635,7 +635,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) if (!bdev) { if (bdev_p) - *bdev_p = sis->bdev; + *bdev_p = bdget(sis->bdev->bd_dev); spin_unlock(&swap_lock); return i; @@ -647,7 +647,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) struct swap_extent, list); if (se->start_block == offset) { if (bdev_p) - *bdev_p = sis->bdev; + *bdev_p = bdget(sis->bdev->bd_dev); spin_unlock(&swap_lock); bdput(bdev); diff --git a/mm/util.c b/mm/util.c index cb00b748ce47..37eaccdf3054 100644 --- a/mm/util.c +++ b/mm/util.c @@ -129,6 +129,26 @@ void *krealloc(const void *p, size_t new_size, gfp_t flags) } EXPORT_SYMBOL(krealloc); +/** + * kzfree - like kfree but zero memory + * @p: object to free memory of + * + * The memory of the object @p points to is zeroed before freed. + * If @p is %NULL, kzfree() does nothing. + */ +void kzfree(const void *p) +{ + size_t ks; + void *mem = (void *)p; + + if (unlikely(ZERO_OR_NULL_PTR(mem))) + return; + ks = ksize(mem); + memset(mem, 0, ks); + kfree(mem); +} +EXPORT_SYMBOL(kzfree); + /* * strndup_user - duplicate an existing string from user space * @s: The string to duplicate diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 75f49d312e8c..af58324c361a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -24,6 +24,7 @@ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/bootmem.h> +#include <linux/pfn.h> #include <asm/atomic.h> #include <asm/uaccess.h> @@ -152,8 +153,8 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr, * * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N] */ -static int vmap_page_range(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages) +static int vmap_page_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages) { pgd_t *pgd; unsigned long next; @@ -169,13 +170,22 @@ static int vmap_page_range(unsigned long start, unsigned long end, if (err) break; } while (pgd++, addr = next, addr != end); - flush_cache_vmap(start, end); if (unlikely(err)) return err; return nr; } +static int vmap_page_range(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages) +{ + int ret; + + ret = vmap_page_range_noflush(start, end, prot, pages); + flush_cache_vmap(start, end); + return ret; +} + static inline int is_vmalloc_or_module_addr(const void *x) { /* @@ -323,6 +333,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long addr; int purged = 0; + BUG_ON(!size); BUG_ON(size & ~PAGE_MASK); va = kmalloc_node(sizeof(struct vmap_area), @@ -334,6 +345,9 @@ retry: addr = ALIGN(vstart, align); spin_lock(&vmap_area_lock); + if (addr + size - 1 < addr) + goto overflow; + /* XXX: could have a last_hole cache */ n = vmap_area_root.rb_node; if (n) { @@ -365,6 +379,8 @@ retry: while (addr + size > first->va_start && addr + size <= vend) { addr = ALIGN(first->va_end + PAGE_SIZE, align); + if (addr + size - 1 < addr) + goto overflow; n = rb_next(&first->rb_node); if (n) @@ -375,6 +391,7 @@ retry: } found: if (addr + size > vend) { +overflow: spin_unlock(&vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); @@ -498,6 +515,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, static DEFINE_SPINLOCK(purge_lock); LIST_HEAD(valist); struct vmap_area *va; + struct vmap_area *n_va; int nr = 0; /* @@ -537,7 +555,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, if (nr) { spin_lock(&vmap_area_lock); - list_for_each_entry(va, &valist, purge_list) + list_for_each_entry_safe(va, n_va, &valist, purge_list) __free_vmap_area(va); spin_unlock(&vmap_area_lock); } @@ -982,6 +1000,32 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro } EXPORT_SYMBOL(vm_map_ram); +/** + * vm_area_register_early - register vmap area early during boot + * @vm: vm_struct to register + * @align: requested alignment + * + * This function is used to register kernel vm area before + * vmalloc_init() is called. @vm->size and @vm->flags should contain + * proper values on entry and other fields should be zero. On return, + * vm->addr contains the allocated address. + * + * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. + */ +void __init vm_area_register_early(struct vm_struct *vm, size_t align) +{ + static size_t vm_init_off __initdata; + unsigned long addr; + + addr = ALIGN(VMALLOC_START + vm_init_off, align); + vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; + + vm->addr = (void *)addr; + + vm->next = vmlist; + vmlist = vm; +} + void __init vmalloc_init(void) { struct vmap_area *va; @@ -1009,9 +1053,63 @@ void __init vmalloc_init(void) vmap_initialized = true; } +/** + * map_kernel_range_noflush - map kernel VM area with the specified pages + * @addr: start of the VM area to map + * @size: size of the VM area to map + * @prot: page protection flags to use + * @pages: pages to map + * + * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size + * specify should have been allocated using get_vm_area() and its + * friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is + * responsible for calling flush_cache_vmap() on to-be-mapped areas + * before calling this function. + * + * RETURNS: + * The number of pages mapped on success, -errno on failure. + */ +int map_kernel_range_noflush(unsigned long addr, unsigned long size, + pgprot_t prot, struct page **pages) +{ + return vmap_page_range_noflush(addr, addr + size, prot, pages); +} + +/** + * unmap_kernel_range_noflush - unmap kernel VM area + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size + * specify should have been allocated using get_vm_area() and its + * friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is + * responsible for calling flush_cache_vunmap() on to-be-mapped areas + * before calling this function and flush_tlb_kernel_range() after. + */ +void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) +{ + vunmap_page_range(addr, addr + size); +} + +/** + * unmap_kernel_range - unmap kernel VM area and flush cache and TLB + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Similar to unmap_kernel_range_noflush() but flushes vcache before + * the unmapping and tlb after. + */ void unmap_kernel_range(unsigned long addr, unsigned long size) { unsigned long end = addr + size; + + flush_cache_vunmap(addr, end); vunmap_page_range(addr, end); flush_tlb_kernel_range(addr, end); } @@ -1106,6 +1204,14 @@ struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, } EXPORT_SYMBOL_GPL(__get_vm_area); +struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, + unsigned long start, unsigned long end, + void *caller) +{ + return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL, + caller); +} + /** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area @@ -1249,6 +1355,7 @@ EXPORT_SYMBOL(vfree); void vunmap(const void *addr) { BUG_ON(in_interrupt()); + might_sleep(); __vunmap(addr, 0); } EXPORT_SYMBOL(vunmap); @@ -1268,6 +1375,8 @@ void *vmap(struct page **pages, unsigned int count, { struct vm_struct *area; + might_sleep(); + if (count > num_physpages) return NULL; diff --git a/mm/vmscan.c b/mm/vmscan.c index cf8441345277..479e46719394 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1262,7 +1262,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, * Move the pages to the [file or anon] inactive list. */ pagevec_init(&pvec, 1); - pgmoved = 0; lru = LRU_BASE + file * LRU_FILE; spin_lock_irq(&zone->lru_lock); @@ -1274,6 +1273,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, */ reclaim_stat->recent_rotated[!!file] += pgmoved; + pgmoved = 0; while (!list_empty(&l_inactive)) { page = lru_to_page(&l_inactive); prefetchw_prev_lru_page(page, &l_inactive, flags); @@ -1469,7 +1469,7 @@ static void shrink_zone(int priority, struct zone *zone, int file = is_file_lru(l); int scan; - scan = zone_page_state(zone, NR_LRU_BASE + l); + scan = zone_nr_pages(zone, sc, l); if (priority) { scan >>= priority; scan = (scan * percent[file]) / 100; @@ -2059,31 +2059,31 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio, int pass, struct scan_control *sc) { struct zone *zone; - unsigned long nr_to_scan, ret = 0; - enum lru_list l; + unsigned long ret = 0; for_each_zone(zone) { + enum lru_list l; if (!populated_zone(zone)) continue; - if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY) continue; for_each_evictable_lru(l) { + enum zone_stat_item ls = NR_LRU_BASE + l; + unsigned long lru_pages = zone_page_state(zone, ls); + /* For pass = 0, we don't shrink the active list */ - if (pass == 0 && - (l == LRU_ACTIVE || l == LRU_ACTIVE_FILE)) + if (pass == 0 && (l == LRU_ACTIVE_ANON || + l == LRU_ACTIVE_FILE)) continue; - zone->lru[l].nr_scan += - (zone_page_state(zone, NR_LRU_BASE + l) - >> prio) + 1; + zone->lru[l].nr_scan += (lru_pages >> prio) + 1; if (zone->lru[l].nr_scan >= nr_pages || pass > 3) { + unsigned long nr_to_scan; + zone->lru[l].nr_scan = 0; - nr_to_scan = min(nr_pages, - zone_page_state(zone, - NR_LRU_BASE + l)); + nr_to_scan = min(nr_pages, lru_pages); ret += shrink_list(l, nr_to_scan, zone, sc, prio); if (ret >= nr_pages) @@ -2091,7 +2091,6 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio, } } } - return ret; } @@ -2114,7 +2113,6 @@ unsigned long shrink_all_memory(unsigned long nr_pages) .may_swap = 0, .swap_cluster_max = nr_pages, .may_writepage = 1, - .swappiness = vm_swappiness, .isolate_pages = isolate_pages_global, }; @@ -2148,10 +2146,8 @@ unsigned long shrink_all_memory(unsigned long nr_pages) int prio; /* Force reclaiming mapped pages in the passes #3 and #4 */ - if (pass > 2) { + if (pass > 2) sc.may_swap = 1; - sc.swappiness = 100; - } for (prio = DEF_PRIORITY; prio >= 0; prio--) { unsigned long nr_to_scan = nr_pages - ret; |