aufs3.16 mmap patch diff --git a/fs/buffer.c b/fs/buffer.c index eba6e4f..31f0b2d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2460,7 +2460,7 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, * Update file times before taking page lock. We may end up failing the * fault so this update may be superfluous but who really cares... */ - file_update_time(vma->vm_file); + vma_file_update_time(vma); ret = __block_page_mkwrite(vma, vmf, get_block); sb_end_pagefault(sb); diff --git a/fs/proc/base.c b/fs/proc/base.c index 2d696b0..fb92686 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1799,7 +1799,7 @@ static int proc_map_files_get_link(struct dentry *dentry, struct path *path) down_read(&mm->mmap_sem); vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { - *path = vma->vm_file->f_path; + *path = vma_pr_or_file(vma)->f_path; path_get(path); rc = 0; } diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index d4a3574..1397181 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -45,7 +45,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region) file = region->vm_file; if (file) { - struct inode *inode = file_inode(region->vm_file); + struct inode *inode; + + file = vmr_pr_or_file(region); + inode = file_inode(file); dev = inode->i_sb->s_dev; ino = inode->i_ino; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index cfa63ee..bf4919e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -265,7 +265,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) const char *name = NULL; if (file) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode; + + file = vma_pr_or_file(vma); + inode = file_inode(file); dev = inode->i_sb->s_dev; ino = inode->i_ino; pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT; @@ -1390,7 +1393,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) struct proc_maps_private *proc_priv = &numa_priv->proc_maps; struct vm_area_struct *vma = v; struct numa_maps *md = &numa_priv->md; - struct file *file = vma->vm_file; + struct file *file = vma_pr_or_file(vma); struct task_struct *task = proc_priv->task; struct mm_struct *mm = vma->vm_mm; struct mm_walk walk = {}; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 678455d..0ef7ef4 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -141,7 +141,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, file = vma->vm_file; if (file) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode; + + file = vma_pr_or_file(file); + inode = file_inode(file); dev = inode->i_sb->s_dev; ino = inode->i_ino; pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT; diff --git a/include/linux/mm.h b/include/linux/mm.h index e03dd29..dd32624 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1184,6 +1184,28 @@ static inline int fixup_user_fault(struct task_struct *tsk, } #endif +#ifdef CONFIG_MMU +extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int); +extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[], + int); +extern void vma_do_get_file(struct vm_area_struct *, const char[], int); +extern void vma_do_fput(struct vm_area_struct *, const char[], int); + +#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \ + __LINE__) +#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \ + __LINE__) +#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__) +#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__) +#else +extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int); +extern void vmr_do_fput(struct vm_region *, const char[], int); + +#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \ + __LINE__) +#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__) +#endif /* CONFIG_MMU */ + extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, int write); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 96c5750..a087ecd 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -232,6 +232,7 @@ struct vm_region { unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ + struct file *vm_prfile; /* the virtual backing file or NULL */ int vm_usage; /* region usage count (access under nommu_region_sem) */ bool vm_icache_flushed : 1; /* true if the icache has been flushed for @@ -300,6 +301,7 @@ struct vm_area_struct { unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE units, *not* PAGE_CACHE_SIZE */ struct file * vm_file; /* File we map to (can be NULL). */ + struct file *vm_prfile; /* shadow of vm_file */ void * vm_private_data; /* was vm_pte (shared mem) */ #ifndef CONFIG_MMU diff --git a/kernel/fork.c b/kernel/fork.c index 6a13c46..714302c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -416,7 +416,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) struct inode *inode = file_inode(file); struct address_space *mapping = file->f_mapping; - get_file(file); + vma_get_file(tmp); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); mutex_lock(&mapping->i_mmap_mutex); diff --git a/mm/Makefile b/mm/Makefile index 4064f3e..0003fdf 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -18,7 +18,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o balloon_compaction.o vmacache.o \ interval_tree.o list_lru.o workingset.o \ - iov_iter.o $(mmu-y) + iov_iter.o prfile.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/filemap.c b/mm/filemap.c index 900edfa..f4dda0c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2040,7 +2040,7 @@ 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/fremap.c b/mm/fremap.c index 72b8fa3..a00bbf0 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -224,16 +224,28 @@ get_write_lock: */ if (mapping_cap_account_dirty(mapping)) { unsigned long addr; - struct file *file = get_file(vma->vm_file); + struct file *file = vma->vm_file, + *prfile = vma->vm_prfile; + /* mmap_region may free vma; grab the info now */ vm_flags = vma->vm_flags; + vma_get_file(vma); addr = mmap_region(file, start, size, vm_flags, pgoff); - fput(file); + vma_fput(vma); if (IS_ERR_VALUE(addr)) { err = addr; } else { BUG_ON(addr != start); + if (prfile) { + struct vm_area_struct *new_vma; + + new_vma = find_vma(mm, addr); + if (!new_vma->vm_prfile) + new_vma->vm_prfile = prfile; + if (new_vma != vma) + get_file(prfile); + } err = 0; } goto out_freed; diff --git a/mm/madvise.c b/mm/madvise.c index a402f8f..134e15d 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -327,12 +327,12 @@ static long madvise_remove(struct vm_area_struct *vma, * vma's reference to the file) can go away as soon as we drop * mmap_sem. */ - get_file(f); + vma_get_file(vma); up_read(¤t->mm->mmap_sem); error = do_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); - fput(f); + vma_fput(vma); down_read(¤t->mm->mmap_sem); return error; } diff --git a/mm/memory.c b/mm/memory.c index 8b44f76..69a72bf 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2161,7 +2161,7 @@ reuse: set_page_dirty_balance(dirty_page); /* file_update_time outside page_lock */ if (vma->vm_file) - file_update_time(vma->vm_file); + vma_file_update_time(vma); } put_page(dirty_page); if (page_mkwrite) { diff --git a/mm/mmap.c b/mm/mmap.c index 129b847..869d1d7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -253,7 +253,7 @@ 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)); kmem_cache_free(vm_area_cachep, vma); return next; @@ -863,7 +863,7 @@ 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); @@ -1661,8 +1661,8 @@ 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); @@ -2434,7 +2434,7 @@ 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); @@ -2453,7 +2453,7 @@ 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)); @@ -2842,7 +2842,7 @@ 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/msync.c b/mm/msync.c index 992a167..ce1915b 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -84,13 +84,13 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) start = vma->vm_end; if ((flags & MS_SYNC) && file && (vma->vm_flags & VM_SHARED)) { - get_file(file); + vma_get_file(vma); up_read(&mm->mmap_sem); if (vma->vm_flags & VM_NONLINEAR) error = vfs_fsync(file, 1); else error = vfs_fsync_range(file, fstart, fend, 1); - fput(file); + vma_fput(vma); if (error || start >= end) goto out; down_read(&mm->mmap_sem); diff --git a/mm/nommu.c b/mm/nommu.c index 4a852f6..b369644 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -658,7 +658,7 @@ 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 */ @@ -823,7 +823,7 @@ 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); } @@ -1385,7 +1385,7 @@ 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; @@ -1461,10 +1461,10 @@ 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); kleave(" = %d", ret); return ret; diff --git a/mm/prfile.c b/mm/prfile.c new file mode 100644 index 0000000..fc708d2 --- /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 +#include +#include + +/* #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, %p\n", func, line, func2, + f ? (char *)f->f_dentry->d_name.name : "(null)"); +#endif +} + +#ifdef CONFIG_MMU +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); +} +#else +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 */