diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Makefile | 2 | ||||
| -rw-r--r-- | mm/filemap.c | 2 | ||||
| -rw-r--r-- | mm/memory.c | 2 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 10 | ||||
| -rw-r--r-- | mm/mmap.c | 17 | ||||
| -rw-r--r-- | mm/nommu.c | 10 | ||||
| -rw-r--r-- | mm/prfile.c | 86 | ||||
| -rw-r--r-- | mm/shmem.c | 88 |
8 files changed, 167 insertions, 50 deletions
diff --git a/mm/Makefile b/mm/Makefile index b4773abcb..6218349e5 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -21,7 +21,7 @@ obj-y := filemap.o mempool.o oom_kill.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o vmacache.o \ interval_tree.o list_lru.o workingset.o \ - debug.o $(mmu-y) + prfile.o debug.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/filemap.c b/mm/filemap.c index 1283fc825..128f18fc4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2089,7 +2089,7 @@ int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) int ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + vma_file_update_time(vma); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); diff --git a/mm/memory.c b/mm/memory.c index bf1f96a11..106ae6439 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2066,7 +2066,7 @@ static inline int wp_page_reuse(struct mm_struct *mm, } if (!page_mkwrite) - file_update_time(vma->vm_file); + vma_file_update_time(vma); } return VM_FAULT_WRITE; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 6da82bcb0..8fd97dac5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1248,6 +1248,14 @@ int __ref add_memory(int nid, u64 start, u64 size) mem_hotplug_begin(); + /* + * Add new range to memblock so that when hotadd_new_pgdat() is called + * to allocate new pgdat, get_pfn_range_for_nid() will be able to find + * this new range and calculate total pages correctly. The range will + * be removed at hot-remove time. + */ + memblock_add_node(start, size, nid); + new_node = !node_online(nid); if (new_node) { pgdat = hotadd_new_pgdat(nid, start); @@ -1277,7 +1285,6 @@ int __ref add_memory(int nid, u64 start, u64 size) /* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); - memblock_add_node(start, size, nid); goto out; @@ -1286,6 +1293,7 @@ error: if (new_pgdat) rollback_node_hotadd(nid, pgdat); release_memory_resource(res); + memblock_remove(start, size); out: mem_hotplug_done(); @@ -275,7 +275,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (vma->vm_file) - fput(vma->vm_file); + vma_fput(vma); mpol_put(vma_policy(vma)); uksm_remove_vma(vma); kmem_cache_free(vm_area_cachep, vma); @@ -896,7 +896,7 @@ again: remove_next = 1 + (end > next->vm_end); if (remove_next) { if (file) { uprobe_munmap(next, next->vm_start, next->vm_end); - fput(file); + vma_fput(vma); } if (next->anon_vma) anon_vma_merge(vma, next); @@ -1691,8 +1691,8 @@ out: return addr; unmap_and_free_vma: + vma_fput(vma); vma->vm_file = NULL; - fput(file); /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); @@ -2494,7 +2494,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, goto out_free_mpol; if (new->vm_file) - get_file(new->vm_file); + vma_get_file(new); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); @@ -2515,7 +2515,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (new->vm_ops && new->vm_ops->close) new->vm_ops->close(new); if (new->vm_file) - fput(new->vm_file); + vma_fput(new); unlink_anon_vmas(new); out_free_mpol: mpol_put(vma_policy(new)); @@ -2658,7 +2658,6 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, struct vm_area_struct *vma; unsigned long populate = 0; unsigned long ret = -EINVAL; - struct file *file; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " "See Documentation/vm/remap_file_pages.txt.\n", @@ -2702,10 +2701,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, munlock_vma_pages_range(vma, start, start + size); } - file = get_file(vma->vm_file); + vma_get_file(vma); ret = do_mmap_pgoff(vma->vm_file, start, size, prot, flags, pgoff, &populate); - fput(file); + vma_fput(vma); out: up_write(&mm->mmap_sem); if (populate) @@ -2985,7 +2984,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) - get_file(new_vma->vm_file); + vma_get_file(new_vma); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); diff --git a/mm/nommu.c b/mm/nommu.c index 58ea3643b..f937b7e52 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -671,7 +671,7 @@ static void __put_nommu_region(struct vm_region *region) up_write(&nommu_region_sem); if (region->vm_file) - fput(region->vm_file); + vmr_fput(region); /* IO memory and memory shared directly out of the pagecache * from ramfs/tmpfs mustn't be released here */ @@ -829,7 +829,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (vma->vm_file) - fput(vma->vm_file); + vma_fput(vma); put_nommu_region(vma->vm_region); kmem_cache_free(vm_area_cachep, vma); } @@ -1354,7 +1354,7 @@ unsigned long do_mmap_pgoff(struct file *file, goto error_just_free; } } - fput(region->vm_file); + vmr_fput(region); kmem_cache_free(vm_region_jar, region); region = pregion; result = start; @@ -1429,10 +1429,10 @@ error_just_free: up_write(&nommu_region_sem); error: if (region->vm_file) - fput(region->vm_file); + vmr_fput(region); kmem_cache_free(vm_region_jar, region); if (vma->vm_file) - fput(vma->vm_file); + vma_fput(vma); kmem_cache_free(vm_area_cachep, vma); return ret; diff --git a/mm/prfile.c b/mm/prfile.c new file mode 100644 index 000000000..b323b8af9 --- /dev/null +++ b/mm/prfile.c @@ -0,0 +1,86 @@ +/* + * Mainly for aufs which mmap(2) diffrent file and wants to print different path + * in /proc/PID/maps. + * Call these functions via macros defined in linux/mm.h. + * + * See Documentation/filesystems/aufs/design/06mmap.txt + * + * Copyright (c) 2014 Junjro R. Okajima + * Copyright (c) 2014 Ian Campbell + */ + +#include <linux/mm.h> +#include <linux/file.h> +#include <linux/fs.h> + +/* #define PRFILE_TRACE */ +static inline void prfile_trace(struct file *f, struct file *pr, + const char func[], int line, const char func2[]) +{ +#ifdef PRFILE_TRACE + if (pr) + pr_info("%s:%d: %s, %s\n", func, line, func2, + f ? (char *)f->f_path.dentry->d_name.name : "(null)"); +#endif +} + +void vma_do_file_update_time(struct vm_area_struct *vma, const char func[], + int line) +{ + struct file *f = vma->vm_file, *pr = vma->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + file_update_time(f); + if (f && pr) + file_update_time(pr); +} + +struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[], + int line) +{ + struct file *f = vma->vm_file, *pr = vma->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + return (f && pr) ? pr : f; +} + +void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line) +{ + struct file *f = vma->vm_file, *pr = vma->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + get_file(f); + if (f && pr) + get_file(pr); +} + +void vma_do_fput(struct vm_area_struct *vma, const char func[], int line) +{ + struct file *f = vma->vm_file, *pr = vma->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + fput(f); + if (f && pr) + fput(pr); +} + +#ifndef CONFIG_MMU +struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[], + int line) +{ + struct file *f = region->vm_file, *pr = region->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + return (f && pr) ? pr : f; +} + +void vmr_do_fput(struct vm_region *region, const char func[], int line) +{ + struct file *f = region->vm_file, *pr = region->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + fput(f); + if (f && pr) + fput(pr); +} +#endif /* !CONFIG_MMU */ diff --git a/mm/shmem.c b/mm/shmem.c index d88bf98f0..8c5467e4e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -110,9 +110,13 @@ static unsigned long shmem_default_max_blocks(void) return totalram_pages / 2; } -static unsigned long shmem_default_max_inodes(void) +static int shmem_default_max_inodes(void) { - return min(totalram_pages - totalhigh_pages, totalram_pages / 2); + unsigned long ul; + + ul = INT_MAX; + ul = min3(ul, totalram_pages - totalhigh_pages, totalram_pages / 2); + return ul; } #endif @@ -587,6 +591,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) static void shmem_evict_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (inode->i_mapping->a_ops == &shmem_aops) { shmem_unacct_size(info->flags, inode->i_size); @@ -602,6 +607,11 @@ static void shmem_evict_inode(struct inode *inode) simple_xattrs_free(&info->xattrs); WARN_ON(inode->i_blocks); + if (!sbinfo->idr_nouse && inode->i_ino) { + mutex_lock(&sbinfo->idr_lock); + idr_remove(&sbinfo->idr, inode->i_ino); + mutex_unlock(&sbinfo->idr_lock); + } shmem_free_inode(inode->i_sb); clear_inode(inode); } @@ -1401,13 +1411,13 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode struct inode *inode; struct shmem_inode_info *info; struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + int ino; if (shmem_reserve_inode(sb)) return NULL; inode = new_inode(sb); if (inode) { - inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -1450,6 +1460,25 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode mpol_shared_policy_init(&info->policy, NULL); break; } + + if (!sbinfo->idr_nouse) { + /* inum 0 and 1 are unused */ + mutex_lock(&sbinfo->idr_lock); + ino = idr_alloc(&sbinfo->idr, inode, 2, INT_MAX, + GFP_NOFS); + if (ino > 0) { + inode->i_ino = ino; + mutex_unlock(&sbinfo->idr_lock); + __insert_inode_hash(inode, inode->i_ino); + } else { + inode->i_ino = 0; + mutex_unlock(&sbinfo->idr_lock); + iput(inode); + /* shmem_free_inode() will be called */ + inode = NULL; + } + } else + inode->i_ino = get_next_ino(); } else shmem_free_inode(sb); return inode; @@ -2667,8 +2696,7 @@ static struct dentry *shmem_get_parent(struct dentry *child) static int shmem_match(struct inode *ino, void *vfh) { __u32 *fh = vfh; - __u64 inum = fh[2]; - inum = (inum << 32) | fh[1]; + __u64 inum = fh[1]; return ino->i_ino == inum && fh[0] == ino->i_generation; } @@ -2679,14 +2707,11 @@ static struct dentry *shmem_fh_to_dentry(struct super_block *sb, struct dentry *dentry = NULL; u64 inum; - if (fh_len < 3) + if (fh_len < 2) return NULL; - inum = fid->raw[2]; - inum = (inum << 32) | fid->raw[1]; - - inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]), - shmem_match, fid->raw); + inum = fid->raw[1]; + inode = ilookup5(sb, inum, shmem_match, fid->raw); if (inode) { dentry = d_find_alias(inode); iput(inode); @@ -2698,30 +2723,15 @@ static struct dentry *shmem_fh_to_dentry(struct super_block *sb, static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len, struct inode *parent) { - if (*len < 3) { - *len = 3; + if (*len < 2) { + *len = 2; return FILEID_INVALID; } - if (inode_unhashed(inode)) { - /* Unfortunately insert_inode_hash is not idempotent, - * so as we hash inodes here rather than at creation - * time, we need a lock to ensure we only try - * to do it once - */ - static DEFINE_SPINLOCK(lock); - spin_lock(&lock); - if (inode_unhashed(inode)) - __insert_inode_hash(inode, - inode->i_ino + inode->i_generation); - spin_unlock(&lock); - } - fh[0] = inode->i_generation; fh[1] = inode->i_ino; - fh[2] = ((__u64)inode->i_ino) >> 32; - *len = 3; + *len = 2; return 1; } @@ -2786,7 +2796,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, goto bad_val; } else if (!strcmp(this_char,"nr_inodes")) { sbinfo->max_inodes = memparse(value, &rest); - if (*rest) + if (*rest || sbinfo->max_inodes < 2) goto bad_val; } else if (!strcmp(this_char,"mode")) { if (remount) @@ -2839,7 +2849,7 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); struct shmem_sb_info config = *sbinfo; - unsigned long inodes; + int inodes; int error = -EINVAL; config.mpol = NULL; @@ -2887,7 +2897,7 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) seq_printf(seq, ",size=%luk", sbinfo->max_blocks << (PAGE_CACHE_SHIFT - 10)); if (sbinfo->max_inodes != shmem_default_max_inodes()) - seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); + seq_printf(seq, ",nr_inodes=%d", sbinfo->max_inodes); if (sbinfo->mode != (S_IRWXUGO | S_ISVTX)) seq_printf(seq, ",mode=%03ho", sbinfo->mode); if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) @@ -2976,6 +2986,8 @@ static void shmem_put_super(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + if (!sbinfo->idr_nouse) + idr_destroy(&sbinfo->idr); percpu_counter_destroy(&sbinfo->used_blocks); mpol_put(sbinfo->mpol); kfree(sbinfo); @@ -2994,6 +3006,8 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) if (!sbinfo) return -ENOMEM; + mutex_init(&sbinfo->idr_lock); + idr_init(&sbinfo->idr); sbinfo->mode = S_IRWXUGO | S_ISVTX; sbinfo->uid = current_fsuid(); sbinfo->gid = current_fsgid(); @@ -3097,6 +3111,15 @@ static void shmem_destroy_inodecache(void) kmem_cache_destroy(shmem_inode_cachep); } +static __init void shmem_no_idr(struct super_block *sb) +{ + struct shmem_sb_info *sbinfo; + + sbinfo = SHMEM_SB(sb); + sbinfo->idr_nouse = true; + idr_destroy(&sbinfo->idr); +} + static const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, @@ -3232,6 +3255,7 @@ int __init shmem_init(void) printk(KERN_ERR "Could not kern_mount tmpfs\n"); goto out1; } + shmem_no_idr(shm_mnt->mnt_sb); return 0; out1: |