diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Makefile | 1 | ||||
| -rw-r--r-- | mm/backing-dev.c | 5 | ||||
| -rw-r--r-- | mm/bounce.c | 14 | ||||
| -rw-r--r-- | mm/failslab.c | 59 | ||||
| -rw-r--r-- | mm/filemap.c | 15 | ||||
| -rw-r--r-- | mm/memory.c | 89 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 9 | ||||
| -rw-r--r-- | mm/mempolicy.c | 9 | ||||
| -rw-r--r-- | mm/migrate.c | 68 | ||||
| -rw-r--r-- | mm/mlock.c | 45 | ||||
| -rw-r--r-- | mm/mmap.c | 2 | ||||
| -rw-r--r-- | mm/mprotect.c | 2 | ||||
| -rw-r--r-- | mm/mremap.c | 2 | ||||
| -rw-r--r-- | mm/msync.c | 2 | ||||
| -rw-r--r-- | mm/nommu.c | 2 | ||||
| -rw-r--r-- | mm/oom_kill.c | 12 | ||||
| -rw-r--r-- | mm/page_cgroup.c | 59 | ||||
| -rw-r--r-- | mm/pdflush.c | 16 | ||||
| -rw-r--r-- | mm/shmem.c | 8 | ||||
| -rw-r--r-- | mm/slab.c | 91 | ||||
| -rw-r--r-- | mm/slob.c | 2 | ||||
| -rw-r--r-- | mm/slub.c | 126 | ||||
| -rw-r--r-- | mm/sparse.c | 2 | ||||
| -rw-r--r-- | mm/swap.c | 20 | ||||
| -rw-r--r-- | mm/swapfile.c | 9 | ||||
| -rw-r--r-- | mm/vmalloc.c | 27 | ||||
| -rw-r--r-- | mm/vmscan.c | 6 | ||||
| -rw-r--r-- | mm/vmstat.c | 4 |
28 files changed, 456 insertions, 250 deletions
diff --git a/mm/Makefile b/mm/Makefile index c06b45a..51c2770 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_SLOB) += slob.o obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o +obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f2e574d..a7c6c56 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -176,6 +176,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, int ret = 0; struct device *dev; + if (bdi->dev) /* The driver needs to use separate queues per device */ + goto exit; + va_start(args, fmt); dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args); va_end(args); @@ -220,7 +223,7 @@ int bdi_init(struct backing_dev_info *bdi) bdi->max_prop_frac = PROP_FRAC_BASE; for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { - err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0); + err = percpu_counter_init(&bdi->bdi_stat[i], 0); if (err) goto err; } diff --git a/mm/bounce.c b/mm/bounce.c index 06722c4..e590272 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -14,6 +14,7 @@ #include <linux/hash.h> #include <linux/highmem.h> #include <linux/blktrace_api.h> +#include <trace/block.h> #include <asm/tlbflush.h> #define POOL_SIZE 64 @@ -21,6 +22,8 @@ static mempool_t *page_pool, *isa_page_pool; +DEFINE_TRACE(block_bio_bounce); + #ifdef CONFIG_HIGHMEM static __init int init_emergency_pool(void) { @@ -195,8 +198,13 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, /* * irk, bounce it */ - if (!bio) - bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt); + if (!bio) { + unsigned int cnt = (*bio_orig)->bi_vcnt; + + bio = bio_alloc(GFP_NOIO, cnt); + memset(bio->bi_io_vec, 0, cnt * sizeof(struct bio_vec)); + } + to = bio->bi_io_vec + i; @@ -222,7 +230,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, if (!bio) return; - blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE); + trace_block_bio_bounce(q, *bio_orig); /* * at least one page was bounced, fill in possible non-highmem diff --git a/mm/failslab.c b/mm/failslab.c new file mode 100644 index 0000000..7c6ea64 --- /dev/null +++ b/mm/failslab.c @@ -0,0 +1,59 @@ +#include <linux/fault-inject.h> + +static struct { + struct fault_attr attr; + u32 ignore_gfp_wait; +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + struct dentry *ignore_gfp_wait_file; +#endif +} failslab = { + .attr = FAULT_ATTR_INITIALIZER, + .ignore_gfp_wait = 1, +}; + +bool should_failslab(size_t size, gfp_t gfpflags) +{ + if (gfpflags & __GFP_NOFAIL) + return false; + + if (failslab.ignore_gfp_wait && (gfpflags & __GFP_WAIT)) + return false; + + return should_fail(&failslab.attr, size); +} + +static int __init setup_failslab(char *str) +{ + return setup_fault_attr(&failslab.attr, str); +} +__setup("failslab=", setup_failslab); + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + +static int __init failslab_debugfs_init(void) +{ + mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; + struct dentry *dir; + int err; + + err = init_fault_attr_dentries(&failslab.attr, "failslab"); + if (err) + return err; + dir = failslab.attr.dentries.dir; + + failslab.ignore_gfp_wait_file = + debugfs_create_bool("ignore-gfp-wait", mode, dir, + &failslab.ignore_gfp_wait); + + if (!failslab.ignore_gfp_wait_file) { + err = -ENOMEM; + debugfs_remove(failslab.ignore_gfp_wait_file); + cleanup_fault_attr_dentries(&failslab.attr); + } + + return err; +} + +late_initcall(failslab_debugfs_init); + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ diff --git a/mm/filemap.c b/mm/filemap.c index f3e5f89..f5769b4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1766,7 +1766,7 @@ int should_remove_suid(struct dentry *dentry) if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; - if (unlikely(kill && !capable(CAP_FSETID))) + if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; @@ -2140,19 +2140,24 @@ EXPORT_SYMBOL(generic_file_direct_write); * Find or create a page at the given pagecache position. Return the locked * page. This function is specifically for buffered writes. */ -struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index) +struct page *grab_cache_page_write_begin(struct address_space *mapping, + pgoff_t index, unsigned flags) { int status; struct page *page; + gfp_t gfp_notmask = 0; + if (flags & AOP_FLAG_NOFS) + gfp_notmask = __GFP_FS; repeat: page = find_lock_page(mapping, index); if (likely(page)) return page; - page = page_cache_alloc(mapping); + page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask); if (!page) return NULL; - status = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); + status = add_to_page_cache_lru(page, mapping, index, + GFP_KERNEL & ~gfp_notmask); if (unlikely(status)) { page_cache_release(page); if (status == -EEXIST) @@ -2161,7 +2166,7 @@ repeat: } return page; } -EXPORT_SYMBOL(__grab_cache_page); +EXPORT_SYMBOL(grab_cache_page_write_begin); static ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) diff --git a/mm/memory.c b/mm/memory.c index 164951c..7b9db65 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -669,6 +669,16 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); + if (unlikely(is_pfn_mapping(vma))) { + /* + * We do not free on error cases below as remove_vma + * gets called on error from higher level routine + */ + ret = track_pfn_vma_copy(vma); + if (ret) + return ret; + } + /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the @@ -915,6 +925,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, if (vma->vm_flags & VM_ACCOUNT) *nr_accounted += (end - start) >> PAGE_SHIFT; + if (unlikely(is_pfn_mapping(vma))) + untrack_pfn_vma(vma, 0, 0); + while (start != end) { if (!tlb_start_valid) { tlb_start = start; @@ -1430,6 +1443,7 @@ out: int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { + int ret; /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like @@ -1444,7 +1458,15 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; - return insert_pfn(vma, addr, pfn, vma->vm_page_prot); + if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE)) + return -EINVAL; + + ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot); + + if (ret) + untrack_pfn_vma(vma, pfn, PAGE_SIZE); + + return ret; } EXPORT_SYMBOL(vm_insert_pfn); @@ -1575,14 +1597,17 @@ 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 (is_cow_mapping(vma->vm_flags)) { - if (addr != vma->vm_start || end != vma->vm_end) - return -EINVAL; + if (addr == vma->vm_start && end == vma->vm_end) vma->vm_pgoff = pfn; - } + else if (is_cow_mapping(vma->vm_flags)) + return -EINVAL; vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size)); + if (err) + return -EINVAL; + BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); @@ -1594,6 +1619,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, if (err) break; } while (pgd++, addr = next, addr != end); + + if (err) + untrack_pfn_vma(vma, pfn, PAGE_ALIGN(size)); + return err; } EXPORT_SYMBOL(remap_pfn_range); @@ -2237,7 +2266,7 @@ int vmtruncate(struct inode * inode, loff_t offset) unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); } - if (inode->i_op && inode->i_op->truncate) + if (inode->i_op->truncate) inode->i_op->truncate(inode); return 0; @@ -2257,7 +2286,7 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) * a way to truncate a range of blocks (punch a hole) - * we should return failure right now. */ - if (!inode->i_op || !inode->i_op->truncate_range) + if (!inode->i_op->truncate_range) return -ENOSYS; mutex_lock(&inode->i_mutex); @@ -2865,9 +2894,9 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ #ifdef CONFIG_HAVE_IOREMAP_PROT -static resource_size_t follow_phys(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned long *prot) +int follow_phys(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned long *prot, resource_size_t *phys) { pgd_t *pgd; pud_t *pud; @@ -2876,24 +2905,26 @@ static resource_size_t follow_phys(struct vm_area_struct *vma, spinlock_t *ptl; resource_size_t phys_addr = 0; struct mm_struct *mm = vma->vm_mm; + int ret = -EINVAL; - VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP))); + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto no_page_table; + goto out; pud = pud_offset(pgd, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) - goto no_page_table; + goto out; pmd = pmd_offset(pud, address); if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - goto no_page_table; + goto out; /* We cannot handle huge page PFN maps. Luckily they don't exist. */ if (pmd_huge(*pmd)) - goto no_page_table; + goto out; ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) @@ -2908,13 +2939,13 @@ static resource_size_t follow_phys(struct vm_area_struct *vma, phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */ *prot = pgprot_val(pte_pgprot(pte)); + *phys = phys_addr; + ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: - return phys_addr; -no_page_table: - return 0; + return ret; } int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, @@ -2925,12 +2956,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *maddr; int offset = addr & (PAGE_SIZE-1); - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - return -EINVAL; - - phys_addr = follow_phys(vma, addr, write, &prot); - - if (!phys_addr) + if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); @@ -3049,3 +3075,18 @@ void print_vma_addr(char *prefix, unsigned long ip) } up_read(¤t->mm->mmap_sem); } + +#ifdef CONFIG_PROVE_LOCKING +void might_fault(void) +{ + might_sleep(); + /* + * it would be nicer only to annotate paths which are not under + * pagefault_disable, however that requires a larger audit and + * providing helpers like get_user_atomic. + */ + if (!in_atomic() && current->mm) + might_lock_read(¤t->mm->mmap_sem); +} +EXPORT_SYMBOL(might_fault); +#endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b5b2b15..b173711 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -189,7 +189,7 @@ static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn, pgdat->node_start_pfn; } -static int __add_zone(struct zone *zone, unsigned long phys_start_pfn) +static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) { struct pglist_data *pgdat = zone->zone_pgdat; int nr_pages = PAGES_PER_SECTION; @@ -216,7 +216,7 @@ static int __add_zone(struct zone *zone, unsigned long phys_start_pfn) return 0; } -static int __add_section(struct zone *zone, unsigned long phys_start_pfn) +static int __meminit __add_section(struct zone *zone, unsigned long phys_start_pfn) { int nr_pages = PAGES_PER_SECTION; int ret; @@ -273,7 +273,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms) * call this function after deciding the zone to which to * add the new pages. */ -int __add_pages(struct zone *zone, unsigned long phys_start_pfn, +int __ref __add_pages(struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) { unsigned long i; @@ -470,7 +470,8 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat) } -int add_memory(int nid, u64 start, u64 size) +/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ +int __ref add_memory(int nid, u64 start, u64 size) { pg_data_t *pgdat = NULL; int new_pgdat = 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e9493b1..e412ffa 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1114,6 +1114,7 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { + const struct cred *cred = current_cred(), *tcred; struct mm_struct *mm; struct task_struct *task; nodemask_t old; @@ -1148,12 +1149,16 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, * capabilities, superuser privileges or the same * userid as the target process. */ - if ((current->euid != task->suid) && (current->euid != task->uid) && - (current->uid != task->suid) && (current->uid != task->uid) && + rcu_read_lock(); + tcred = __task_cred(task); + if (cred->euid != tcred->suid && cred->euid != tcred->uid && + cred->uid != tcred->suid && cred->uid != tcred->uid && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); err = -EPERM; goto out; } + rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ diff --git a/mm/migrate.c b/mm/migrate.c index 1e0d6b2..21631ab 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -987,25 +987,18 @@ out: /* * Determine the nodes of an array of pages and store it in an array of status. */ -static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, - const void __user * __user *pages, - int __user *status) +static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, + const void __user **pages, int *status) { unsigned long i; - int err; down_read(&mm->mmap_sem); for (i = 0; i < nr_pages; i++) { - const void __user *p; - unsigned long addr; + unsigned long addr = (unsigned long)(*pages); struct vm_area_struct *vma; struct page *page; - - err = -EFAULT; - if (get_user(p, pages+i)) - goto out; - addr = (unsigned long) p; + int err = -EFAULT; vma = find_vma(mm, addr); if (!vma) @@ -1024,12 +1017,52 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, err = page_to_nid(page); set_status: - put_user(err, status+i); + *status = err; + + pages++; + status++; + } + + up_read(&mm->mmap_sem); +} + +/* + * Determine the nodes of a user array of pages and store it in + * a user array of status. + */ +static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, + const void __user * __user *pages, + int __user *status) +{ +#define DO_PAGES_STAT_CHUNK_NR 16 + const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; + int chunk_status[DO_PAGES_STAT_CHUNK_NR]; + unsigned long i, chunk_nr = DO_PAGES_STAT_CHUNK_NR; + int err; + + for (i = 0; i < nr_pages; i += chunk_nr) { + if (chunk_nr + i > nr_pages) + chunk_nr = nr_pages - i; + + err = copy_from_user(chunk_pages, &pages[i], + chunk_nr * sizeof(*chunk_pages)); + if (err) { + err = -EFAULT; + goto out; + } + + do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status); + + err = copy_to_user(&status[i], chunk_status, + chunk_nr * sizeof(*chunk_status)); + if (err) { + err = -EFAULT; + goto out; + } } err = 0; out: - up_read(&mm->mmap_sem); return err; } @@ -1042,6 +1075,7 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, const int __user *nodes, int __user *status, int flags) { + const struct cred *cred = current_cred(), *tcred; struct task_struct *task; struct mm_struct *mm; int err; @@ -1072,12 +1106,16 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, * capabilities, superuser privileges or the same * userid as the target process. */ - if ((current->euid != task->suid) && (current->euid != task->uid) && - (current->uid != task->suid) && (current->uid != task->uid) && + rcu_read_lock(); + tcred = __task_cred(task); + if (cred->euid != tcred->suid && cred->euid != tcred->uid && + cred->uid != tcred->suid && cred->uid != tcred->uid && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); err = -EPERM; goto out; } + rcu_read_unlock(); err = security_task_movememory(task); if (err) @@ -667,3 +667,48 @@ void user_shm_unlock(size_t size, struct user_struct *user) spin_unlock(&shmlock_user_lock); free_uid(user); } + +void *alloc_locked_buffer(size_t size) +{ + unsigned long rlim, vm, pgsz; + void *buffer = NULL; + + pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; + + down_write(¤t->mm->mmap_sem); + + rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; + vm = current->mm->total_vm + pgsz; + if (rlim < vm) + goto out; + + rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; + vm = current->mm->locked_vm + pgsz; + if (rlim < vm) + goto out; + + buffer = kzalloc(size, GFP_KERNEL); + if (!buffer) + goto out; + + current->mm->total_vm += pgsz; + current->mm->locked_vm += pgsz; + + out: + up_write(¤t->mm->mmap_sem); + return buffer; +} + +void free_locked_buffer(void *buffer, size_t size) +{ + unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; + + down_write(¤t->mm->mmap_sem); + + current->mm->total_vm -= pgsz; + current->mm->locked_vm -= pgsz; + + up_write(¤t->mm->mmap_sem); + + kfree(buffer); +} @@ -3,7 +3,7 @@ * * Written by obz. * - * Address space accounting code <alan@redhat.com> + * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ #include <linux/slab.h> diff --git a/mm/mprotect.c b/mm/mprotect.c index fded06f..cfb4c48 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -4,7 +4,7 @@ * (C) Copyright 1994 Linus Torvalds * (C) Copyright 2002 Christoph Hellwig * - * Address space accounting code <alan@redhat.com> + * Address space accounting code <alan@lxorguk.ukuu.org.uk> * (C) Copyright 2002 Red Hat Inc, All Rights Reserved */ diff --git a/mm/mremap.c b/mm/mremap.c index 58a2908..646de95 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -3,7 +3,7 @@ * * (C) Copyright 1996 Linus Torvalds * - * Address space accounting code <alan@redhat.com> + * Address space accounting code <alan@lxorguk.ukuu.org.uk> * (C) Copyright 2002 Red Hat Inc, All Rights Reserved */ @@ -82,7 +82,7 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags) (vma->vm_flags & VM_SHARED)) { get_file(file); up_read(&mm->mmap_sem); - error = do_fsync(file, 0); + error = vfs_fsync(file, file->f_path.dentry, 0); fput(file); if (error || start >= end) goto out; @@ -86,7 +86,7 @@ do_expand: i_size_write(inode, offset); out_truncate: - if (inode->i_op && inode->i_op->truncate) + if (inode->i_op->truncate) inode->i_op->truncate(inode); return 0; out_sig: diff --git a/mm/oom_kill.c b/mm/oom_kill.c index a0a0190..558f9af 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -128,8 +128,8 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * Superuser processes are usually more important, so we make it * less likely that we kill those. */ - if (has_capability(p, CAP_SYS_ADMIN) || - has_capability(p, CAP_SYS_RESOURCE)) + if (has_capability_noaudit(p, CAP_SYS_ADMIN) || + has_capability_noaudit(p, CAP_SYS_RESOURCE)) points /= 4; /* @@ -138,7 +138,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * tend to only have this flag set on applications they think * of as important. */ - if (has_capability(p, CAP_SYS_RAWIO)) + if (has_capability_noaudit(p, CAP_SYS_RAWIO)) points /= 4; /* @@ -299,9 +299,9 @@ static void dump_tasks(const struct mem_cgroup *mem) task_lock(p); printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", - p->pid, p->uid, p->tgid, p->mm->total_vm, - get_mm_rss(p->mm), (int)task_cpu(p), p->oomkilladj, - p->comm); + p->pid, __task_cred(p)->uid, p->tgid, + p->mm->total_vm, get_mm_rss(p->mm), (int)task_cpu(p), + p->oomkilladj, p->comm); task_unlock(p); } while_each_thread(g, p); } diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 1223d92..ab27ff7 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -21,7 +21,7 @@ static unsigned long total_usage; #if !defined(CONFIG_SPARSEMEM) -void __init pgdat_page_cgroup_init(struct pglist_data *pgdat) +void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) { pgdat->node_page_cgroup = NULL; } @@ -49,6 +49,9 @@ static int __init alloc_node_page_cgroup(int nid) start_pfn = NODE_DATA(nid)->node_start_pfn; nr_pages = NODE_DATA(nid)->node_spanned_pages; + if (!nr_pages) + return 0; + table_size = sizeof(struct page_cgroup) * nr_pages; base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), @@ -97,7 +100,8 @@ struct page_cgroup *lookup_page_cgroup(struct page *page) return section->page_cgroup + pfn; } -int __meminit init_section_page_cgroup(unsigned long pfn) +/* __alloc_bootmem...() is protected by !slab_available() */ +int __init_refok init_section_page_cgroup(unsigned long pfn) { struct mem_section *section; struct page_cgroup *base, *pc; @@ -106,19 +110,29 @@ int __meminit init_section_page_cgroup(unsigned long pfn) section = __pfn_to_section(pfn); - if (section->page_cgroup) - return 0; - - 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); - if (!base) - base = vmalloc_node(table_size, nid); - } else { - base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), table_size, + if (!section->page_cgroup) { + 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); + if (!base) + base = vmalloc_node(table_size, nid); + } else { + base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), + table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + } + } else { + /* + * We don't have to allocate page_cgroup again, but + * address of memmap may be changed. So, we have to initialize + * again. + */ + base = section->page_cgroup + pfn; + table_size = 0; + /* check address of memmap is changed or not. */ + if (base->page == pfn_to_page(pfn)) + return 0; } if (!base) { @@ -158,7 +172,7 @@ void __free_page_cgroup(unsigned long pfn) } } -int online_page_cgroup(unsigned long start_pfn, +int __meminit online_page_cgroup(unsigned long start_pfn, unsigned long nr_pages, int nid) { @@ -183,7 +197,7 @@ int online_page_cgroup(unsigned long start_pfn, return -ENOMEM; } -int offline_page_cgroup(unsigned long start_pfn, +int __meminit offline_page_cgroup(unsigned long start_pfn, unsigned long nr_pages, int nid) { unsigned long start, end, pfn; @@ -197,7 +211,7 @@ int offline_page_cgroup(unsigned long start_pfn, } -static int page_cgroup_callback(struct notifier_block *self, +static int __meminit page_cgroup_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; @@ -207,18 +221,23 @@ static int page_cgroup_callback(struct notifier_block *self, ret = online_page_cgroup(mn->start_pfn, mn->nr_pages, mn->status_change_nid); break; - case MEM_CANCEL_ONLINE: case MEM_OFFLINE: offline_page_cgroup(mn->start_pfn, mn->nr_pages, mn->status_change_nid); break; + case MEM_CANCEL_ONLINE: case MEM_GOING_OFFLINE: break; case MEM_ONLINE: case MEM_CANCEL_OFFLINE: break; } - ret = notifier_from_errno(ret); + + if (ret) + ret = notifier_from_errno(ret); + else + ret = NOTIFY_OK; + return ret; } @@ -248,7 +267,7 @@ void __init page_cgroup_init(void) " want\n"); } -void __init pgdat_page_cgroup_init(struct pglist_data *pgdat) +void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) { return; } diff --git a/mm/pdflush.c b/mm/pdflush.c index a0a14c4..15de509 100644 --- a/mm/pdflush.c +++ b/mm/pdflush.c @@ -172,7 +172,16 @@ static int __pdflush(struct pdflush_work *my_work) static int pdflush(void *dummy) { struct pdflush_work my_work; - cpumask_t cpus_allowed; + cpumask_var_t cpus_allowed; + + /* + * Since the caller doesn't even check kthread_run() worked, let's not + * freak out too much if this fails. + */ + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { + printk(KERN_WARNING "pdflush failed to allocate cpumask\n"); + return 0; + } /* * pdflush can spend a lot of time doing encryption via dm-crypt. We @@ -187,8 +196,9 @@ static int pdflush(void *dummy) * This is needed as pdflush's are dynamically created and destroyed. * The boottime pdflush's are easily placed w/o these 2 lines. */ - cpuset_cpus_allowed(current, &cpus_allowed); - set_cpus_allowed_ptr(current, &cpus_allowed); + cpuset_cpus_allowed(current, cpus_allowed); + set_cpus_allowed_ptr(current, cpus_allowed); + free_cpumask_var(cpus_allowed); return __pdflush(&my_work); } @@ -1513,8 +1513,8 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) inode = new_inode(sb); if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -2278,8 +2278,8 @@ static int shmem_fill_super(struct super_block *sb, sbinfo->max_blocks = 0; sbinfo->max_inodes = 0; sbinfo->mode = S_IRWXUGO | S_ISVTX; - sbinfo->uid = current->fsuid; - sbinfo->gid = current->fsgid; + sbinfo->uid = current_fsuid(); + sbinfo->gid = current_fsgid(); sbinfo->mpol = NULL; sb->s_fs_info = sbinfo; @@ -2123,6 +2123,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep) * * @name must be valid until the cache is destroyed. This implies that * the module calling this has to destroy the cache before getting unloaded. + * Note that kmem_cache_name() is not guaranteed to return the same pointer, + * therefore applications must manage it themselves. * * The flags are * @@ -2155,7 +2157,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, /* * We use cache_chain_mutex to ensure a consistent view of - * cpu_online_map as well. Please see cpuup_callback + * cpu_online_mask as well. Please see cpuup_callback */ get_online_cpus(); mutex_lock(&cache_chain_mutex); @@ -2609,7 +2611,7 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp, if (OFF_SLAB(cachep)) { /* Slab management obj is off-slab. */ slabp = kmem_cache_alloc_node(cachep->slabp_cache, - local_flags & ~GFP_THISNODE, nodeid); + local_flags, nodeid); if (!slabp) return NULL; } else { @@ -2997,7 +2999,7 @@ retry: * there must be at least one object available for * allocation. */ - BUG_ON(slabp->inuse < 0 || slabp->inuse >= cachep->num); + BUG_ON(slabp->inuse >= cachep->num); while (slabp->inuse < cachep->num && batchcount--) { STATS_INC_ALLOCED(cachep); @@ -3106,79 +3108,14 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, #define cache_alloc_debugcheck_after(a,b,objp,d) (objp) #endif -#ifdef CONFIG_FAILSLAB - -static struct failslab_attr { - - struct fault_attr attr; - - u32 ignore_gfp_wait; -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - struct dentry *ignore_gfp_wait_file; -#endif - -} failslab = { - .attr = FAULT_ATTR_INITIALIZER, - .ignore_gfp_wait = 1, -}; - -static int __init setup_failslab(char *str) -{ - return setup_fault_attr(&failslab.attr, str); -} -__setup("failslab=", setup_failslab); - -static int should_failslab(struct kmem_cache *cachep, gfp_t flags) +static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags) { if (cachep == &cache_cache) - return 0; - if (flags & __GFP_NOFAIL) - return 0; - if (failslab.ignore_gfp_wait && (flags & __GFP_WAIT)) - return 0; + return false; - return should_fail(&failslab.attr, obj_size(cachep)); + return should_failslab(obj_size(cachep), flags); } -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - -static int __init failslab_debugfs(void) -{ - mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; - struct dentry *dir; - int err; - - err = init_fault_attr_dentries(&failslab.attr, "failslab"); - if (err) - return err; - dir = failslab.attr.dentries.dir; - - failslab.ignore_gfp_wait_file = - debugfs_create_bool("ignore-gfp-wait", mode, dir, - &failslab.ignore_gfp_wait); - - if (!failslab.ignore_gfp_wait_file) { - err = -ENOMEM; - debugfs_remove(failslab.ignore_gfp_wait_file); - cleanup_fault_attr_dentries(&failslab.attr); - } - - return err; -} - -late_initcall(failslab_debugfs); - -#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ - -#else /* CONFIG_FAILSLAB */ - -static inline int should_failslab(struct kmem_cache *cachep, gfp_t flags) -{ - return 0; -} - -#endif /* CONFIG_FAILSLAB */ - static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) { void *objp; @@ -3381,7 +3318,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, unsigned long save_flags; void *ptr; - if (should_failslab(cachep, flags)) + if (slab_should_failslab(cachep, flags)) return NULL; cache_alloc_debugcheck_before(cachep, flags); @@ -3457,7 +3394,7 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) unsigned long save_flags; void *objp; - if (should_failslab(cachep, flags)) + if (slab_should_failslab(cachep, flags)) return NULL; cache_alloc_debugcheck_before(cachep, flags); @@ -3686,9 +3623,9 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) EXPORT_SYMBOL(__kmalloc_node); void *__kmalloc_node_track_caller(size_t size, gfp_t flags, - int node, void *caller) + int node, unsigned long caller) { - return __do_kmalloc_node(size, flags, node, caller); + return __do_kmalloc_node(size, flags, node, (void *)caller); } EXPORT_SYMBOL(__kmalloc_node_track_caller); #else @@ -3730,9 +3667,9 @@ void *__kmalloc(size_t size, gfp_t flags) } EXPORT_SYMBOL(__kmalloc); -void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller) +void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) { - return __do_kmalloc(size, flags, caller); + return __do_kmalloc(size, flags, (void *)caller); } EXPORT_SYMBOL(__kmalloc_track_caller); @@ -535,7 +535,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, struct kmem_cache *c; c = slob_alloc(sizeof(struct kmem_cache), - flags, ARCH_KMALLOC_MINALIGN, -1); + GFP_KERNEL, ARCH_KMALLOC_MINALIGN, -1); if (c) { c->name = name; @@ -24,6 +24,7 @@ #include <linux/kallsyms.h> #include <linux/memory.h> #include <linux/math64.h> +#include <linux/fault-inject.h> /* * Lock order: @@ -153,6 +154,10 @@ #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif +#define OO_SHIFT 16 +#define OO_MASK ((1 << OO_SHIFT) - 1) +#define MAX_OBJS_PER_PAGE 65535 /* since page.objects is u16 */ + /* Internal SLUB flags */ #define __OBJECT_POISON 0x80000000 /* Poison object */ #define __SYSFS_ADD_DEFERRED 0x40000000 /* Not yet visible via sysfs */ @@ -178,7 +183,7 @@ static LIST_HEAD(slab_caches); * Tracking user of a slab. */ struct track { - void *addr; /* Called from address */ + unsigned long addr; /* Called from address */ int cpu; /* Was running on cpu */ int pid; /* Pid context */ unsigned long when; /* When did the operation occur */ @@ -290,7 +295,7 @@ static inline struct kmem_cache_order_objects oo_make(int order, unsigned long size) { struct kmem_cache_order_objects x = { - (order << 16) + (PAGE_SIZE << order) / size + (order << OO_SHIFT) + (PAGE_SIZE << order) / size }; return x; @@ -298,12 +303,12 @@ static inline struct kmem_cache_order_objects oo_make(int order, static inline int oo_order(struct kmem_cache_order_objects x) { - return x.x >> 16; + return x.x >> OO_SHIFT; } static inline int oo_objects(struct kmem_cache_order_objects x) { - return x.x & ((1 << 16) - 1); + return x.x & OO_MASK; } #ifdef CONFIG_SLUB_DEBUG @@ -367,7 +372,7 @@ 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, void *addr) + enum track_item alloc, unsigned long addr) { struct track *p; @@ -391,8 +396,8 @@ static void init_tracking(struct kmem_cache *s, void *object) if (!(s->flags & SLAB_STORE_USER)) return; - set_track(s, object, TRACK_FREE, NULL); - set_track(s, object, TRACK_ALLOC, NULL); + set_track(s, object, TRACK_FREE, 0UL); + set_track(s, object, TRACK_ALLOC, 0UL); } static void print_track(const char *s, struct track *t) @@ -401,7 +406,7 @@ static void print_track(const char *s, struct track *t) return; printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n", - s, t->addr, jiffies - t->when, t->cpu, t->pid); + s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid); } static void print_tracking(struct kmem_cache *s, void *object) @@ -692,7 +697,7 @@ static int check_object(struct kmem_cache *s, struct page *page, if (!check_valid_pointer(s, page, get_freepointer(s, p))) { object_err(s, page, p, "Freepointer corrupt"); /* - * No choice but to zap it and thus loose the remainder + * No choice but to zap it and thus lose the remainder * of the free objects in this slab. May cause * another error because the object count is now wrong. */ @@ -764,8 +769,8 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search) } max_objects = (PAGE_SIZE << compound_order(page)) / s->size; - if (max_objects > 65535) - max_objects = 65535; + if (max_objects > MAX_OBJS_PER_PAGE) + max_objects = MAX_OBJS_PER_PAGE; if (page->objects != max_objects) { slab_err(s, page, "Wrong number of objects. Found %d but " @@ -866,7 +871,7 @@ static void setup_object_debug(struct kmem_cache *s, struct page *page, } static int alloc_debug_processing(struct kmem_cache *s, struct page *page, - void *object, void *addr) + void *object, unsigned long addr) { if (!check_slab(s, page)) goto bad; @@ -906,7 +911,7 @@ bad: } static int free_debug_processing(struct kmem_cache *s, struct page *page, - void *object, void *addr) + void *object, unsigned long addr) { if (!check_slab(s, page)) goto fail; @@ -1029,10 +1034,10 @@ static inline void setup_object_debug(struct kmem_cache *s, struct page *page, void *object) {} static inline int alloc_debug_processing(struct kmem_cache *s, - struct page *page, void *object, void *addr) { return 0; } + struct page *page, void *object, unsigned long addr) { return 0; } static inline int free_debug_processing(struct kmem_cache *s, - struct page *page, void *object, void *addr) { return 0; } + struct page *page, void *object, unsigned long addr) { return 0; } static inline int slab_pad_check(struct kmem_cache *s, struct page *page) { return 1; } @@ -1499,8 +1504,8 @@ static inline int node_match(struct kmem_cache_cpu *c, int node) * we need to allocate a new slab. This is the slowest path since it involves * a call to the page allocator and the setup of a new slab. */ -static void *__slab_alloc(struct kmem_cache *s, - gfp_t gfpflags, int node, void *addr, struct kmem_cache_cpu *c) +static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) { void **object; struct page *new; @@ -1584,13 +1589,18 @@ debug: * Otherwise we can simply pick the next object from the lockless free list. */ static __always_inline void *slab_alloc(struct kmem_cache *s, - gfp_t gfpflags, int node, void *addr) + gfp_t gfpflags, int node, unsigned long addr) { void **object; struct kmem_cache_cpu *c; unsigned long flags; unsigned int objsize; + might_sleep_if(gfpflags & __GFP_WAIT); + + if (should_failslab(s->objsize, gfpflags)) + return NULL; + local_irq_save(flags); c = get_cpu_slab(s, smp_processor_id()); objsize = c->objsize; @@ -1613,14 +1623,14 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { - return slab_alloc(s, gfpflags, -1, __builtin_return_address(0)); + return slab_alloc(s, gfpflags, -1, _RET_IP_); } EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) { - return slab_alloc(s, gfpflags, node, __builtin_return_address(0)); + return slab_alloc(s, gfpflags, node, _RET_IP_); } EXPORT_SYMBOL(kmem_cache_alloc_node); #endif @@ -1634,7 +1644,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_node); * handling required then we can return immediately. */ static void __slab_free(struct kmem_cache *s, struct page *page, - void *x, void *addr, unsigned int offset) + void *x, unsigned long addr, unsigned int offset) { void *prior; void **object = (void *)x; @@ -1704,7 +1714,7 @@ debug: * with all sorts of special processing. */ static __always_inline void slab_free(struct kmem_cache *s, - struct page *page, void *x, void *addr) + struct page *page, void *x, unsigned long addr) { void **object = (void *)x; struct kmem_cache_cpu *c; @@ -1731,11 +1741,11 @@ void kmem_cache_free(struct kmem_cache *s, void *x) page = virt_to_head_page(x); - slab_free(s, page, x, __builtin_return_address(0)); + slab_free(s, page, x, _RET_IP_); } EXPORT_SYMBOL(kmem_cache_free); -/* Figure out on which slab object the object resides */ +/* Figure out on which slab page the object resides */ static struct page *get_object_page(const void *x) { struct page *page = virt_to_head_page(x); @@ -1807,8 +1817,8 @@ static inline int slab_order(int size, int min_objects, int rem; int min_order = slub_min_order; - if ((PAGE_SIZE << min_order) / size > 65535) - return get_order(size * 65535) - 1; + if ((PAGE_SIZE << min_order) / size > MAX_OBJS_PER_PAGE) + return get_order(size * MAX_OBJS_PER_PAGE) - 1; for (order = max(min_order, fls(min_objects * size - 1) - PAGE_SHIFT); @@ -1960,7 +1970,7 @@ static DEFINE_PER_CPU(struct kmem_cache_cpu, kmem_cache_cpu)[NR_KMEM_CACHE_CPU]; static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free); -static cpumask_t kmem_cach_cpu_free_init_once = CPU_MASK_NONE; +static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS); static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s, int cpu, gfp_t flags) @@ -2035,13 +2045,13 @@ static void init_alloc_cpu_cpu(int cpu) { int i; - if (cpu_isset(cpu, kmem_cach_cpu_free_init_once)) + if (cpumask_test_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once))) return; for (i = NR_KMEM_CACHE_CPU - 1; i >= 0; i--) free_kmem_cache_cpu(&per_cpu(kmem_cache_cpu, cpu)[i], cpu); - cpu_set(cpu, kmem_cach_cpu_free_init_once); + cpumask_set_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once)); } static void __init init_alloc_cpu(void) @@ -2073,8 +2083,7 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags) * when allocating for the kmalloc_node_cache. This is used for bootstrapping * memory on a fresh node that has no slab structures yet. */ -static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags, - int node) +static void early_kmem_cache_node_alloc(gfp_t gfpflags, int node) { struct page *page; struct kmem_cache_node *n; @@ -2112,7 +2121,6 @@ static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags, local_irq_save(flags); add_partial(n, page, 0); local_irq_restore(flags); - return n; } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -2144,8 +2152,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags) n = &s->local_node; else { if (slab_state == DOWN) { - n = early_kmem_cache_node_alloc(gfpflags, - node); + early_kmem_cache_node_alloc(gfpflags, node); continue; } n = kmem_cache_alloc_node(kmalloc_caches, @@ -2659,7 +2666,7 @@ void *__kmalloc(size_t size, gfp_t flags) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, flags, -1, __builtin_return_address(0)); + return slab_alloc(s, flags, -1, _RET_IP_); } EXPORT_SYMBOL(__kmalloc); @@ -2687,7 +2694,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, flags, node, __builtin_return_address(0)); + return slab_alloc(s, flags, node, _RET_IP_); } EXPORT_SYMBOL(__kmalloc_node); #endif @@ -2744,7 +2751,7 @@ void kfree(const void *x) put_page(page); return; } - slab_free(page->slab, page, object, __builtin_return_address(0)); + slab_free(page->slab, page, object, _RET_IP_); } EXPORT_SYMBOL(kfree); @@ -2931,8 +2938,10 @@ static int slab_memory_callback(struct notifier_block *self, case MEM_CANCEL_OFFLINE: break; } - - ret = notifier_from_errno(ret); + if (ret) + ret = notifier_from_errno(ret); + else + ret = NOTIFY_OK; return ret; } @@ -3121,8 +3130,12 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *))); up_write(&slub_lock); - if (sysfs_slab_alias(s, name)) + if (sysfs_slab_alias(s, name)) { + down_write(&slub_lock); + s->refcount--; + up_write(&slub_lock); goto err; + } return s; } @@ -3132,8 +3145,13 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size, align, flags, ctor)) { list_add(&s->list, &slab_caches); up_write(&slub_lock); - if (sysfs_slab_add(s)) + if (sysfs_slab_add(s)) { + down_write(&slub_lock); + list_del(&s->list); + up_write(&slub_lock); + kfree(s); goto err; + } return s; } kfree(s); @@ -3200,7 +3218,7 @@ static struct notifier_block __cpuinitdata slab_notifier = { #endif -void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller) +void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) { struct kmem_cache *s; @@ -3216,7 +3234,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller) } void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, - int node, void *caller) + int node, unsigned long caller) { struct kmem_cache *s; @@ -3427,13 +3445,13 @@ static void resiliency_test(void) {}; struct location { unsigned long count; - void *addr; + unsigned long addr; long long sum_time; long min_time; long max_time; long min_pid; long max_pid; - cpumask_t cpus; + DECLARE_BITMAP(cpus, NR_CPUS); nodemask_t nodes; }; @@ -3475,7 +3493,7 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, { long start, end, pos; struct location *l; - void *caddr; + unsigned long caddr; unsigned long age = jiffies - track->when; start = -1; @@ -3508,7 +3526,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, if (track->pid > l->max_pid) l->max_pid = track->pid; - cpu_set(track->cpu, l->cpus); + cpumask_set_cpu(track->cpu, + to_cpumask(l->cpus)); } node_set(page_to_nid(virt_to_page(track)), l->nodes); return 1; @@ -3538,8 +3557,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, l->max_time = age; l->min_pid = track->pid; l->max_pid = track->pid; - cpus_clear(l->cpus); - cpu_set(track->cpu, l->cpus); + cpumask_clear(to_cpumask(l->cpus)); + cpumask_set_cpu(track->cpu, to_cpumask(l->cpus)); nodes_clear(l->nodes); node_set(page_to_nid(virt_to_page(track)), l->nodes); return 1; @@ -3595,7 +3614,7 @@ static int list_locations(struct kmem_cache *s, char *buf, for (i = 0; i < t.count; i++) { struct location *l = &t.loc[i]; - if (len > PAGE_SIZE - 100) + if (len > PAGE_SIZE - KSYM_SYMBOL_LEN - 100) break; len += sprintf(buf + len, "%7ld ", l->count); @@ -3620,11 +3639,12 @@ static int list_locations(struct kmem_cache *s, char *buf, len += sprintf(buf + len, " pid=%ld", l->min_pid); - if (num_online_cpus() > 1 && !cpus_empty(l->cpus) && + if (num_online_cpus() > 1 && + !cpumask_empty(to_cpumask(l->cpus)) && len < PAGE_SIZE - 60) { len += sprintf(buf + len, " cpus="); len += cpulist_scnprintf(buf + len, PAGE_SIZE - len - 50, - l->cpus); + to_cpumask(l->cpus)); } if (num_online_nodes() > 1 && !nodes_empty(l->nodes) && @@ -4343,7 +4363,7 @@ static void sysfs_slab_remove(struct kmem_cache *s) /* * Need to buffer aliases during bootup until sysfs becomes - * available lest we loose that information. + * available lest we lose that information. */ struct saved_alias { struct kmem_cache *s; diff --git a/mm/sparse.c b/mm/sparse.c index 39db301..083f5b6 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -570,7 +570,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap) * set. If this is <=0, then that means that the passed-in * map was not consumed and must be freed. */ -int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, +int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages) { unsigned long section_nr = pfn_to_section_nr(start_pfn); @@ -299,7 +299,6 @@ void lru_add_drain(void) put_cpu(); } -#if defined(CONFIG_NUMA) || defined(CONFIG_UNEVICTABLE_LRU) static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); @@ -313,18 +312,6 @@ int lru_add_drain_all(void) return schedule_on_each_cpu(lru_add_drain_per_cpu); } -#else - -/* - * Returns 0 for success - */ -int lru_add_drain_all(void) -{ - lru_add_drain(); - return 0; -} -#endif - /* * Batched page_cache_release(). Decrement the reference count on all the * passed pages. If it fell to zero then remove the page from the LRU and @@ -445,6 +432,7 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru) for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; struct zone *pagezone = page_zone(page); + int file; if (pagezone != zone) { if (zone) @@ -456,8 +444,12 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru) VM_BUG_ON(PageUnevictable(page)); VM_BUG_ON(PageLRU(page)); SetPageLRU(page); - if (is_active_lru(lru)) + file = is_file_lru(lru); + zone->recent_scanned[file]++; + if (is_active_lru(lru)) { SetPageActive(page); + zone->recent_rotated[file]++; + } add_page_to_lru_list(zone, page, lru); } if (zone) diff --git a/mm/swapfile.c b/mm/swapfile.c index 90cb67a..54a9f87 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1462,6 +1462,15 @@ static int __init procswaps_init(void) __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ +#ifdef MAX_SWAPFILES_CHECK +static int __init max_swapfiles_check(void) +{ + MAX_SWAPFILES_CHECK(); + return 0; +} +late_initcall(max_swapfiles_check); +#endif + /* * Written 01/25/92 by Simmule Turner, heavily changed by Linus. * diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 30f826d..7465f22 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -77,7 +77,6 @@ static void vunmap_page_range(unsigned long addr, unsigned long end) BUG_ON(addr >= end); pgd = pgd_offset_k(addr); - flush_cache_vunmap(addr, end); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) @@ -152,11 +151,12 @@ 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 addr, unsigned long end, +static int vmap_page_range(unsigned long start, unsigned long end, pgprot_t prot, struct page **pages) { pgd_t *pgd; unsigned long next; + unsigned long addr = start; int err = 0; int nr = 0; @@ -168,7 +168,7 @@ static int vmap_page_range(unsigned long addr, unsigned long end, if (err) break; } while (pgd++, addr = next, addr != end); - flush_cache_vmap(addr, end); + flush_cache_vmap(start, end); if (unlikely(err)) return err; @@ -543,9 +543,10 @@ static void purge_vmap_area_lazy(void) } /* - * Free and unmap a vmap area + * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been + * called for the correct range previously. */ -static void free_unmap_vmap_area(struct vmap_area *va) +static void free_unmap_vmap_area_noflush(struct vmap_area *va) { va->flags |= VM_LAZY_FREE; atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); @@ -553,6 +554,15 @@ static void free_unmap_vmap_area(struct vmap_area *va) try_purge_vmap_area_lazy(); } +/* + * Free and unmap a vmap area + */ +static void free_unmap_vmap_area(struct vmap_area *va) +{ + flush_cache_vunmap(va->va_start, va->va_end); + free_unmap_vmap_area_noflush(va); +} + static struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_area *va; @@ -734,7 +744,7 @@ static void free_vmap_block(struct vmap_block *vb) spin_unlock(&vmap_block_tree_lock); BUG_ON(tmp != vb); - free_unmap_vmap_area(vb->va); + free_unmap_vmap_area_noflush(vb->va); call_rcu(&vb->rcu_head, rcu_free_vb); } @@ -796,6 +806,9 @@ static void vb_free(const void *addr, unsigned long size) BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); + + flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size); + order = get_order(size); offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1); @@ -1705,7 +1718,7 @@ static int s_show(struct seq_file *m, void *p) v->addr, v->addr + v->size, v->size); if (v->caller) { - char buff[2 * KSYM_NAME_LEN]; + char buff[KSYM_SYMBOL_LEN]; seq_putc(m, ' '); sprint_symbol(buff, (unsigned long)v->caller); diff --git a/mm/vmscan.c b/mm/vmscan.c index 7ea1440..d196f46 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1248,6 +1248,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, list_add(&page->lru, &l_inactive); } + spin_lock_irq(&zone->lru_lock); /* * Count referenced pages from currently used mappings as * rotated, even though they are moved to the inactive list. @@ -1263,7 +1264,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, pgmoved = 0; lru = LRU_BASE + file * LRU_FILE; - spin_lock_irq(&zone->lru_lock); while (!list_empty(&l_inactive)) { page = lru_to_page(&l_inactive); prefetchw_prev_lru_page(page, &l_inactive, flags); @@ -1902,7 +1902,7 @@ static int kswapd(void *p) }; node_to_cpumask_ptr(cpumask, pgdat->node_id); - if (!cpus_empty(*cpumask)) + if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); current->reclaim_state = &reclaim_state; @@ -2141,7 +2141,7 @@ static int __devinit cpu_callback(struct notifier_block *nfb, pg_data_t *pgdat = NODE_DATA(nid); node_to_cpumask_ptr(mask, pgdat->node_id); - if (any_online_cpu(*mask) < nr_cpu_ids) + if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) /* One of our CPUs online: restore mask */ set_cpus_allowed_ptr(pgdat->kswapd, mask); } diff --git a/mm/vmstat.c b/mm/vmstat.c index c3ccfda..9114974 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -20,7 +20,7 @@ DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; EXPORT_PER_CPU_SYMBOL(vm_event_states); -static void sum_vm_events(unsigned long *ret, cpumask_t *cpumask) +static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask) { int cpu; int i; @@ -43,7 +43,7 @@ static void sum_vm_events(unsigned long *ret, cpumask_t *cpumask) void all_vm_events(unsigned long *ret) { get_online_cpus(); - sum_vm_events(ret, &cpu_online_map); + sum_vm_events(ret, cpu_online_mask); put_online_cpus(); } EXPORT_SYMBOL_GPL(all_vm_events); |