X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fshmem.c;h=d94d2e9146bc4dfa5d946449274be75419f0b8da;hb=58984ce21d315b70df1a43644df7416ea7c9bfd8;hp=b2a35ebf071a2162dcfd32896c18970b9a8af322;hpb=16a100190d39592d1d56ff5a0b978b20288c3427;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/shmem.c b/mm/shmem.c index b2a35eb..d94d2e9 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -14,30 +14,40 @@ * Copyright (c) 2004, Luke Kenneth Casson Leighton * Copyright (c) 2004 Red Hat, Inc., James Morris * + * tiny-shmem: + * Copyright (c) 2004, 2008 Matt Mackall + * * This file is released under the GPL. */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct vfsmount *shm_mnt; + +#ifdef CONFIG_SHMEM /* * This virtual memory filesystem is heavily based on the ramfs. It * extends ramfs by the ability to use swap and honor resource limits * which makes it a completely usable filesystem. */ -#include -#include -#include #include +#include #include -#include #include -#include -#include #include #include #include #include #include -#include #include #include #include @@ -48,15 +58,13 @@ #include #include #include -#include +#include +#include #include #include #include -/* This magic number is used in glibc for posix shared memory */ -#define TMPFS_MAGIC 0x01021994 - #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) #define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) #define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) @@ -78,12 +86,24 @@ /* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */ enum sgp_type { - SGP_QUICK, /* don't try more than file page cache lookup */ SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ + SGP_DIRTY, /* like SGP_CACHE, but set new page dirty */ SGP_WRITE, /* may exceed i_size, may allocate page */ }; +#ifdef CONFIG_TMPFS +static unsigned long shmem_default_max_blocks(void) +{ + return totalram_pages / 2; +} + +static unsigned long shmem_default_max_inodes(void) +{ + return min(totalram_pages - totalhigh_pages, totalram_pages / 2); +} +#endif + static int shmem_getpage(struct inode *inode, unsigned long idx, struct page **pagep, enum sgp_type sgp, int *type); @@ -93,8 +113,11 @@ static inline struct page *shmem_dir_alloc(gfp_t gfp_mask) * The above definition of ENTRIES_PER_PAGE, and the use of * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE: * might be reconsidered if it ever diverges from PAGE_SIZE. + * + * Mobility flags are masked out as swap vectors cannot move */ - return alloc_pages(gfp_mask, PAGE_CACHE_SHIFT-PAGE_SHIFT); + return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO, + PAGE_CACHE_SHIFT-PAGE_SHIFT); } static inline void shmem_dir_free(struct page *page) @@ -147,13 +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(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)); } @@ -165,13 +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(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)); } @@ -185,12 +208,12 @@ static struct vm_operations_struct shmem_vm_ops; static struct backing_dev_info shmem_backing_dev_info __read_mostly = { .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK, + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, .unplug_io_fn = default_unplug_io_fn, }; static LIST_HEAD(shmem_swaplist); -static DEFINE_SPINLOCK(shmem_swaplist_lock); +static DEFINE_MUTEX(shmem_swaplist_mutex); static void shmem_free_blocks(struct inode *inode, long pages) { @@ -203,9 +226,33 @@ static void shmem_free_blocks(struct inode *inode, long pages) } } -/* +static int shmem_reserve_inode(struct super_block *sb) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + if (sbinfo->max_inodes) { + spin_lock(&sbinfo->stat_lock); + if (!sbinfo->free_inodes) { + spin_unlock(&sbinfo->stat_lock); + return -ENOSPC; + } + sbinfo->free_inodes--; + spin_unlock(&sbinfo->stat_lock); + } + return 0; +} + +static void shmem_free_inode(struct super_block *sb) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + if (sbinfo->max_inodes) { + spin_lock(&sbinfo->stat_lock); + sbinfo->free_inodes++; + spin_unlock(&sbinfo->stat_lock); + } +} + +/** * shmem_recalc_inode - recalculate the size of an inode - * * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop @@ -229,9 +276,8 @@ static void shmem_recalc_inode(struct inode *inode) } } -/* +/** * shmem_swp_entry - find the swap vector position in the info structure - * * @info: info structure for the inode * @index: index of the page to find * @page: optional page to add to the structure. Has to be preset to @@ -333,13 +379,13 @@ static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, uns } } -/* +/** * shmem_swp_alloc - get the position of the swap entry for the page. - * If it does not exist allocate the entry. - * * @info: info structure for the inode * @index: index of the page to find * @sgp: check and recheck i_size? skip allocation? + * + * If the entry does not exist, allocate it. */ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp) { @@ -372,7 +418,7 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long } spin_unlock(&info->lock); - page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO); + page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping)); if (page) set_page_private(page, 0); spin_lock(&info->lock); @@ -399,9 +445,8 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long return entry; } -/* +/** * shmem_free_swp - free some swap entries in a directory - * * @dir: pointer to the directory * @edir: pointer after last entry of the directory * @punch_lock: pointer to spinlock when needed for the holepunch case @@ -727,6 +772,8 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) (void) shmem_getpage(inode, attr->ia_size>>PAGE_CACHE_SHIFT, &page, SGP_READ, NULL); + if (page) + unlock_page(page); } /* * Reset SHMEM_PAGEIN flag so that shmem_truncate can @@ -758,7 +805,6 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) static void shmem_delete_inode(struct inode *inode) { - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct shmem_inode_info *info = SHMEM_I(inode); if (inode->i_op->truncate == shmem_truncate) { @@ -767,17 +813,13 @@ static void shmem_delete_inode(struct inode *inode) inode->i_size = 0; shmem_truncate(inode); if (!list_empty(&info->swaplist)) { - spin_lock(&shmem_swaplist_lock); + mutex_lock(&shmem_swaplist_mutex); list_del_init(&info->swaplist); - spin_unlock(&shmem_swaplist_lock); + mutex_unlock(&shmem_swaplist_mutex); } } BUG_ON(inode->i_blocks); - if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); - } + shmem_free_inode(inode->i_sb); clear_inode(inode); } @@ -803,19 +845,22 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s struct page *subdir; swp_entry_t *ptr; int offset; + int error; idx = 0; ptr = info->i_direct; spin_lock(&info->lock); + if (!info->swapped) { + list_del_init(&info->swaplist); + goto lost2; + } limit = info->next_index; size = limit; if (size > SHMEM_NR_DIRECT) size = SHMEM_NR_DIRECT; offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) { - shmem_swp_balance_unmap(); + if (offset >= 0) goto found; - } if (!info->i_indirect) goto lost2; @@ -825,6 +870,14 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) { if (unlikely(idx == stage)) { shmem_dir_unmap(dir-1); + if (cond_resched_lock(&info->lock)) { + /* check it has not been truncated */ + if (limit > info->next_index) { + limit = info->next_index; + if (idx >= limit) + goto lost2; + } + } dir = shmem_dir_map(info->i_indirect) + ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; while (!*dir) { @@ -845,11 +898,11 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s if (size > ENTRIES_PER_PAGE) size = ENTRIES_PER_PAGE; offset = shmem_find_swp(entry, ptr, ptr+size); + shmem_swp_unmap(ptr); if (offset >= 0) { shmem_dir_unmap(dir); goto found; } - shmem_swp_unmap(ptr); } } lost1: @@ -859,19 +912,77 @@ lost2: return 0; found: idx += offset; - inode = &info->vfs_inode; - if (move_from_swap_cache(page, idx, inode->i_mapping) == 0) { - info->flags |= SHMEM_PAGEIN; - shmem_swp_set(info, ptr + offset, 0); - } - shmem_swp_unmap(ptr); + inode = igrab(&info->vfs_inode); spin_unlock(&info->lock); + /* - * Decrement swap count even when the entry is left behind: - * try_to_unuse will skip over mms, then reincrement count. + * Move _head_ to start search for next from here. + * But be careful: shmem_delete_inode checks list_empty without taking + * mutex, and there's an instant in list_move_tail when info->swaplist + * would appear empty, if it were the only one on shmem_swaplist. We + * could avoid doing it if inode NULL; or use this minor optimization. */ - swap_free(entry); - return 1; + if (shmem_swaplist.next != &info->swaplist) + list_move_tail(&shmem_swaplist, &info->swaplist); + mutex_unlock(&shmem_swaplist_mutex); + + error = 1; + if (!inode) + goto out; + /* + * Charge page using GFP_KERNEL while we can wait. + * Charged back to the user(not to caller) when swap account is used. + * add_to_page_cache() will be called with GFP_NOWAIT. + */ + error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); + if (error) + goto out; + error = radix_tree_preload(GFP_KERNEL); + if (error) { + mem_cgroup_uncharge_cache_page(page); + goto out; + } + error = 1; + + spin_lock(&info->lock); + ptr = shmem_swp_entry(info, idx, NULL); + if (ptr && ptr->val == entry.val) { + error = add_to_page_cache_locked(page, inode->i_mapping, + idx, GFP_NOWAIT); + /* does mem_cgroup_uncharge_cache_page on error */ + } else /* we must compensate for our precharge above */ + mem_cgroup_uncharge_cache_page(page); + + if (error == -EEXIST) { + struct page *filepage = find_get_page(inode->i_mapping, idx); + error = 1; + if (filepage) { + /* + * There might be a more uptodate page coming down + * from a stacked writepage: forget our swappage if so. + */ + if (PageUptodate(filepage)) + error = 0; + page_cache_release(filepage); + } + } + if (!error) { + delete_from_swap_cache(page); + set_page_dirty(page); + info->flags |= SHMEM_PAGEIN; + shmem_swp_set(info, ptr, 0); + swap_free(entry); + error = 1; /* not an error, but entry was found */ + } + if (ptr) + shmem_swp_unmap(ptr); + spin_unlock(&info->lock); + radix_tree_preload_end(); +out: + unlock_page(page); + page_cache_release(page); + iput(inode); /* allows for NULL */ + return error; } /* @@ -883,20 +994,16 @@ int shmem_unuse(swp_entry_t entry, struct page *page) struct shmem_inode_info *info; int found = 0; - spin_lock(&shmem_swaplist_lock); + mutex_lock(&shmem_swaplist_mutex); list_for_each_safe(p, next, &shmem_swaplist) { info = list_entry(p, struct shmem_inode_info, swaplist); - if (!info->swapped) - list_del_init(&info->swaplist); - else if (shmem_unuse_inode(info, entry, page)) { - /* move head to start search for next from here */ - list_move_tail(&shmem_swaplist, &info->swaplist); - found = 1; - break; - } + found = shmem_unuse_inode(info, entry, page); + cond_resched(); + if (found) + goto out; } - spin_unlock(&shmem_swaplist_lock); - return found; + mutex_unlock(&shmem_swaplist_mutex); +out: return found; /* 0 or 1 or -ENOMEM */ } /* @@ -911,39 +1018,64 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode; BUG_ON(!PageLocked(page)); - BUG_ON(page_mapped(page)); - mapping = page->mapping; index = page->index; inode = mapping->host; info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; - swap = get_swap_page(); - if (!swap.val) + if (!total_swap_pages) goto redirty; + /* + * shmem_backing_dev_info's capabilities prevent regular writeback or + * sync from ever calling shmem_writepage; but a stacking filesystem + * may use the ->writepage of its underlying filesystem, in which case + * tmpfs should write out to swap only in response to memory pressure, + * and not for pdflush or sync. However, in those cases, we do still + * want to check if there's a redundant swappage to be discarded. + */ + if (wbc->for_reclaim) + swap = get_swap_page(); + else + swap.val = 0; + spin_lock(&info->lock); - shmem_recalc_inode(inode); if (index >= info->next_index) { BUG_ON(!(info->flags & SHMEM_TRUNCATE)); goto unlock; } entry = shmem_swp_entry(info, index, NULL); - BUG_ON(!entry); - BUG_ON(entry->val); + if (entry->val) { + /* + * The more uptodate page coming down from a stacked + * writepage should replace our old swappage. + */ + free_swap_and_cache(*entry); + shmem_swp_set(info, entry, 0); + } + shmem_recalc_inode(inode); - if (move_to_swap_cache(page, swap) == 0) { + if (swap.val && add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { + remove_from_page_cache(page); shmem_swp_set(info, entry, swap.val); shmem_swp_unmap(entry); + if (list_empty(&info->swaplist)) + inode = igrab(inode); + else + inode = NULL; spin_unlock(&info->lock); - if (list_empty(&info->swaplist)) { - spin_lock(&shmem_swaplist_lock); + swap_duplicate(swap); + BUG_ON(page_mapped(page)); + page_cache_release(page); /* pagecache ref */ + swap_writepage(page, wbc); + if (inode) { + mutex_lock(&shmem_swaplist_mutex); /* move instead of add in case we're racing */ list_move_tail(&info->swaplist, &shmem_swaplist); - spin_unlock(&shmem_swaplist_lock); + mutex_unlock(&shmem_swaplist_mutex); + iput(inode); } - unlock_page(page); return 0; } @@ -953,123 +1085,98 @@ unlock: swap_free(swap); redirty: set_page_dirty(page); - return AOP_WRITEPAGE_ACTIVATE; /* Return with the page locked */ + if (wbc->for_reclaim) + return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */ + unlock_page(page); + return 0; } #ifdef CONFIG_NUMA -static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes) +#ifdef CONFIG_TMPFS +static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { - char *nodelist = strchr(value, ':'); - int err = 1; + char buffer[64]; - if (nodelist) { - /* NUL-terminate policy string */ - *nodelist++ = '\0'; - if (nodelist_parse(nodelist, *policy_nodes)) - goto out; - } - if (!strcmp(value, "default")) { - *policy = MPOL_DEFAULT; - /* Don't allow a nodelist */ - if (!nodelist) - err = 0; - } else if (!strcmp(value, "prefer")) { - *policy = MPOL_PREFERRED; - /* Insist on a nodelist of one node only */ - if (nodelist) { - char *rest = nodelist; - while (isdigit(*rest)) - rest++; - if (!*rest) - err = 0; - } - } else if (!strcmp(value, "bind")) { - *policy = MPOL_BIND; - /* Insist on a nodelist */ - if (nodelist) - err = 0; - } else if (!strcmp(value, "interleave")) { - *policy = MPOL_INTERLEAVE; - /* Default to nodes online if no nodelist */ - if (!nodelist) - *policy_nodes = node_online_map; - err = 0; + if (!mpol || mpol->mode == MPOL_DEFAULT) + return; /* show nothing */ + + mpol_to_str(buffer, sizeof(buffer), mpol, 1); + + seq_printf(seq, ",mpol=%s", buffer); +} + +static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) +{ + struct mempolicy *mpol = NULL; + if (sbinfo->mpol) { + spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ + mpol = sbinfo->mpol; + mpol_get(mpol); + spin_unlock(&sbinfo->stat_lock); } -out: - /* Restore string for error message */ - if (nodelist) - *--nodelist = ':'; - return err; + return mpol; } +#endif /* CONFIG_TMPFS */ -static struct page *shmem_swapin_async(struct shared_policy *p, - swp_entry_t entry, unsigned long idx) +static struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp, + struct shmem_inode_info *info, unsigned long idx) { - struct page *page; + struct mempolicy mpol, *spol; struct vm_area_struct pvma; + struct page *page; + + spol = mpol_cond_copy(&mpol, + mpol_shared_policy_lookup(&info->policy, idx)); /* Create a pseudo vma that just contains the policy */ - memset(&pvma, 0, sizeof(struct vm_area_struct)); - pvma.vm_end = PAGE_SIZE; + pvma.vm_start = 0; pvma.vm_pgoff = idx; - pvma.vm_policy = mpol_shared_policy_lookup(p, idx); - page = read_swap_cache_async(entry, &pvma, 0); - mpol_free(pvma.vm_policy); + pvma.vm_ops = NULL; + pvma.vm_policy = spol; + page = swapin_readahead(entry, gfp, &pvma, 0); return page; } -struct page *shmem_swapin(struct shmem_inode_info *info, swp_entry_t entry, - unsigned long idx) -{ - struct shared_policy *p = &info->policy; - int i, num; - struct page *page; - unsigned long offset; - - num = valid_swaphandles(entry, &offset); - for (i = 0; i < num; offset++, i++) { - page = shmem_swapin_async(p, - swp_entry(swp_type(entry), offset), idx); - if (!page) - break; - page_cache_release(page); - } - lru_add_drain(); /* Push any new pages onto the LRU now */ - return shmem_swapin_async(p, entry, idx); -} - -static struct page * -shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info, - unsigned long idx) +static struct page *shmem_alloc_page(gfp_t gfp, + struct shmem_inode_info *info, unsigned long idx) { struct vm_area_struct pvma; - struct page *page; - memset(&pvma, 0, sizeof(struct vm_area_struct)); - pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx); + /* Create a pseudo vma that just contains the policy */ + pvma.vm_start = 0; pvma.vm_pgoff = idx; - pvma.vm_end = PAGE_SIZE; - page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0); - mpol_free(pvma.vm_policy); - return page; + pvma.vm_ops = NULL; + pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx); + + /* + * alloc_page_vma() will drop the shared policy reference + */ + return alloc_page_vma(gfp, &pvma, 0); } -#else -static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes) +#else /* !CONFIG_NUMA */ +#ifdef CONFIG_TMPFS +static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *p) { - return 1; +} +#endif /* CONFIG_TMPFS */ + +static inline struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp, + struct shmem_inode_info *info, unsigned long idx) +{ + return swapin_readahead(entry, gfp, NULL, 0); } -static inline struct page * -shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx) +static inline struct page *shmem_alloc_page(gfp_t gfp, + struct shmem_inode_info *info, unsigned long idx) { - swapin_readahead(entry, 0, NULL); - return read_swap_cache_async(entry, NULL, 0); + return alloc_page(gfp); } +#endif /* CONFIG_NUMA */ -static inline struct page * -shmem_alloc_page(gfp_t gfp,struct shmem_inode_info *info, unsigned long idx) +#if !defined(CONFIG_NUMA) || !defined(CONFIG_TMPFS) +static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { - return alloc_page(gfp | __GFP_ZERO); + return NULL; } #endif @@ -1090,17 +1197,22 @@ static int shmem_getpage(struct inode *inode, unsigned long idx, struct page *swappage; swp_entry_t *entry; swp_entry_t swap; + gfp_t gfp; int error; if (idx >= SHMEM_MAX_INDEX) return -EFBIG; + + if (type) + *type = 0; + /* * Normally, filepage is NULL on entry, and either found * uptodate immediately, or allocated and zeroed, or read * in under swappage, which is then assigned to filepage. - * But shmem_prepare_write passes in a locked filepage, - * which may be found not uptodate by other callers too, - * and may need to be copied from the swappage read in. + * But shmem_readpage (required for splice) passes in a locked + * filepage, which may be found not uptodate by other callers + * too, and may need to be copied from the swappage read in. */ repeat: if (!filepage) @@ -1108,8 +1220,17 @@ repeat: if (filepage && PageUptodate(filepage)) goto done; error = 0; - if (sgp == SGP_QUICK) - goto failed; + gfp = mapping_gfp_mask(mapping); + if (!filepage) { + /* + * Try to preload while we can wait, to not make a habit of + * draining atomic reserves; but don't latch on to this cpu. + */ + error = radix_tree_preload(gfp & ~__GFP_HIGHMEM); + if (error) + goto failed; + radix_tree_preload_end(); + } spin_lock(&info->lock); shmem_recalc_inode(inode); @@ -1127,12 +1248,12 @@ repeat: if (!swappage) { shmem_swp_unmap(entry); /* here we actually do the io */ - if (type && *type == VM_FAULT_MINOR) { + if (type && !(*type & VM_FAULT_MAJOR)) { __count_vm_event(PGMAJFAULT); - *type = VM_FAULT_MAJOR; + *type |= VM_FAULT_MAJOR; } spin_unlock(&info->lock); - swappage = shmem_swapin(info, swap, idx); + swappage = shmem_swapin(swap, gfp, info, idx); if (!swappage) { spin_lock(&info->lock); entry = shmem_swp_alloc(info, idx, sgp); @@ -1154,7 +1275,7 @@ repeat: } /* We have to do this with page locked to prevent races */ - if (TestSetPageLocked(swappage)) { + if (!trylock_page(swappage)) { shmem_swp_unmap(entry); spin_unlock(&info->lock); wait_on_page_locked(swappage); @@ -1190,30 +1311,39 @@ repeat: SetPageUptodate(filepage); set_page_dirty(filepage); swap_free(swap); - } else if (!(error = move_from_swap_cache( - swappage, idx, mapping))) { + } else if (!(error = add_to_page_cache_locked(swappage, mapping, + idx, GFP_NOWAIT))) { info->flags |= SHMEM_PAGEIN; shmem_swp_set(info, entry, 0); shmem_swp_unmap(entry); + delete_from_swap_cache(swappage); spin_unlock(&info->lock); filepage = swappage; + set_page_dirty(filepage); swap_free(swap); } else { shmem_swp_unmap(entry); spin_unlock(&info->lock); - unlock_page(swappage); - page_cache_release(swappage); if (error == -ENOMEM) { - /* let kswapd refresh zone for GFP_ATOMICs */ - congestion_wait(WRITE, HZ/50); + /* allow reclaim from this memory cgroup */ + error = mem_cgroup_shrink_usage(swappage, + current->mm, + gfp); + if (error) { + unlock_page(swappage); + page_cache_release(swappage); + goto failed; + } } + unlock_page(swappage); + page_cache_release(swappage); goto repeat; } } else if (sgp == SGP_READ && !filepage) { shmem_swp_unmap(entry); filepage = find_get_page(mapping, idx); if (filepage && - (!PageUptodate(filepage) || TestSetPageLocked(filepage))) { + (!PageUptodate(filepage) || !trylock_page(filepage))) { spin_unlock(&info->lock); wait_on_page_locked(filepage); page_cache_release(filepage); @@ -1243,16 +1373,28 @@ repeat: } if (!filepage) { + int ret; + spin_unlock(&info->lock); - filepage = shmem_alloc_page(mapping_gfp_mask(mapping), - info, - idx); + filepage = shmem_alloc_page(gfp, info, idx); if (!filepage) { shmem_unacct_blocks(info->flags, 1); shmem_free_blocks(inode, 1); error = -ENOMEM; goto failed; } + SetPageSwapBacked(filepage); + + /* Precharge page while we can wait, compensate after */ + error = mem_cgroup_cache_charge(filepage, current->mm, + GFP_KERNEL); + if (error) { + page_cache_release(filepage); + shmem_unacct_blocks(info->flags, 1); + shmem_free_blocks(inode, 1); + filepage = NULL; + goto failed; + } spin_lock(&info->lock); entry = shmem_swp_alloc(info, idx, sgp); @@ -1262,8 +1404,17 @@ repeat: swap = *entry; shmem_swp_unmap(entry); } - if (error || swap.val || 0 != add_to_page_cache_lru( - filepage, mapping, idx, GFP_ATOMIC)) { + ret = error || swap.val; + if (ret) + mem_cgroup_uncharge_cache_page(filepage); + else + ret = add_to_page_cache_lru(filepage, mapping, + idx, GFP_NOWAIT); + /* + * At add_to_page_cache_lru() failure, uncharge will + * be done automatically. + */ + if (ret) { spin_unlock(&info->lock); page_cache_release(filepage); shmem_unacct_blocks(info->flags, 1); @@ -1278,14 +1429,14 @@ repeat: info->alloced++; spin_unlock(&info->lock); + clear_highpage(filepage); flush_dcache_page(filepage); SetPageUptodate(filepage); + if (sgp == SGP_DIRTY) + set_page_dirty(filepage); } done: - if (*pagep != filepage) { - unlock_page(filepage); - *pagep = filepage; - } + *pagep = filepage; return 0; failed: @@ -1296,83 +1447,31 @@ failed: return error; } -static struct page *shmem_nopage(struct vm_area_struct *vma, - unsigned long address, int *type) +static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = vma->vm_file->f_path.dentry->d_inode; - struct page *page = NULL; - unsigned long idx; int error; + int ret; - idx = (address - vma->vm_start) >> PAGE_SHIFT; - idx += vma->vm_pgoff; - idx >>= PAGE_CACHE_SHIFT - PAGE_SHIFT; - if (((loff_t) idx << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - return NOPAGE_SIGBUS; + if (((loff_t)vmf->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) + return VM_FAULT_SIGBUS; - error = shmem_getpage(inode, idx, &page, SGP_CACHE, type); + error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); if (error) - return (error == -ENOMEM)? NOPAGE_OOM: NOPAGE_SIGBUS; + return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); - mark_page_accessed(page); - return page; -} - -static int shmem_populate(struct vm_area_struct *vma, - unsigned long addr, unsigned long len, - pgprot_t prot, unsigned long pgoff, int nonblock) -{ - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; - struct mm_struct *mm = vma->vm_mm; - enum sgp_type sgp = nonblock? SGP_QUICK: SGP_CACHE; - unsigned long size; - - size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (pgoff >= size || pgoff + (len >> PAGE_SHIFT) > size) - return -EINVAL; - - while ((long) len > 0) { - struct page *page = NULL; - int err; - /* - * Will need changing if PAGE_CACHE_SIZE != PAGE_SIZE - */ - err = shmem_getpage(inode, pgoff, &page, sgp, NULL); - if (err) - return err; - /* Page may still be null, but only if nonblock was set. */ - if (page) { - mark_page_accessed(page); - err = install_page(mm, vma, addr, page, prot); - if (err) { - page_cache_release(page); - return err; - } - } else if (vma->vm_flags & VM_NONLINEAR) { - /* No page was found just because we can't read it in - * now (being here implies nonblock != 0), but the page - * may exist, so set the PTE to fault it in later. */ - err = install_file_pte(mm, vma, addr, pgoff, prot); - if (err) - return err; - } - - len -= PAGE_SIZE; - addr += PAGE_SIZE; - pgoff++; - } - return 0; + return ret | VM_FAULT_LOCKED; } #ifdef CONFIG_NUMA -int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new) +static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { struct inode *i = vma->vm_file->f_path.dentry->d_inode; return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new); } -struct mempolicy * -shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) +static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, + unsigned long addr) { struct inode *i = vma->vm_file->f_path.dentry->d_inode; unsigned long idx; @@ -1393,12 +1492,16 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) if (!user_shm_lock(inode->i_size, user)) goto out_nomem; info->flags |= VM_LOCKED; + mapping_set_unevictable(file->f_mapping); } if (!lock && (info->flags & VM_LOCKED) && user) { user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; + mapping_clear_unevictable(file->f_mapping); + scan_mapping_unevictable_pages(file->f_mapping); } retval = 0; + out_nomem: spin_unlock(&info->lock); return retval; @@ -1408,39 +1511,33 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &shmem_vm_ops; + vma->vm_flags |= VM_CAN_NONLINEAR; 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; struct shmem_sb_info *sbinfo = SHMEM_SB(sb); - if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - if (!sbinfo->free_inodes) { - spin_unlock(&sbinfo->stat_lock); - return NULL; - } - sbinfo->free_inodes--; - spin_unlock(&sbinfo->stat_lock); - } + if (shmem_reserve_inode(sb)) + return NULL; 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->a_ops = &shmem_aops; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_generation = get_seconds(); 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) { @@ -1449,10 +1546,11 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) init_special_inode(inode, mode, dev); break; case S_IFREG: + inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_inode_operations; inode->i_fop = &shmem_file_operations; - mpol_shared_policy_init(&info->policy, sbinfo->policy, - &sbinfo->policy_nodes); + mpol_shared_policy_init(&info->policy, + shmem_get_sbmpol(sbinfo)); break; case S_IFDIR: inc_nlink(inode); @@ -1466,15 +1564,11 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) * Must not load anything in the rbtree, * mpol_free_shared_policy will not be called. */ - mpol_shared_policy_init(&info->policy, MPOL_DEFAULT, - NULL); + mpol_shared_policy_init(&info->policy, NULL); break; } - } else if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); - } + } else + shmem_free_inode(sb); return inode; } @@ -1483,117 +1577,44 @@ static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_symlink_inline_operations; /* - * Normally tmpfs makes no use of shmem_prepare_write, but it - * lets a tmpfs file be used read-write below the loop driver. + * Normally tmpfs avoids the use of shmem_readpage and shmem_write_begin; + * but providing them allows a tmpfs file to be used for splice, sendfile, and + * below the loop driver, in the generic fashion that many filesystems support. */ -static int -shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to) +static int shmem_readpage(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; - return shmem_getpage(inode, page->index, &page, SGP_WRITE, NULL); + int error = shmem_getpage(inode, page->index, &page, SGP_CACHE, NULL); + unlock_page(page); + return error; } -static ssize_t -shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +static int +shmem_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) { - struct inode *inode = file->f_path.dentry->d_inode; - loff_t pos; - unsigned long written; - ssize_t err; - - if ((ssize_t) count < 0) - return -EINVAL; - - if (!access_ok(VERIFY_READ, buf, count)) - return -EFAULT; - - mutex_lock(&inode->i_mutex); - - pos = *ppos; - written = 0; - - err = generic_write_checks(file, &pos, &count, 0); - if (err || !count) - goto out; - - err = remove_suid(file->f_path.dentry); - if (err) - goto out; - - inode->i_ctime = inode->i_mtime = CURRENT_TIME; - - do { - struct page *page = NULL; - unsigned long bytes, index, offset; - char *kaddr; - int left; - - offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */ - index = pos >> PAGE_CACHE_SHIFT; - bytes = PAGE_CACHE_SIZE - offset; - if (bytes > count) - bytes = count; - - /* - * We don't hold page lock across copy from user - - * what would it guard against? - so no deadlock here. - * But it still may be a good idea to prefault below. - */ - - err = shmem_getpage(inode, index, &page, SGP_WRITE, NULL); - if (err) - break; - - left = bytes; - if (PageHighMem(page)) { - volatile unsigned char dummy; - __get_user(dummy, buf); - __get_user(dummy, buf + bytes - 1); - - kaddr = kmap_atomic(page, KM_USER0); - left = __copy_from_user_inatomic(kaddr + offset, - buf, bytes); - kunmap_atomic(kaddr, KM_USER0); - } - if (left) { - kaddr = kmap(page); - left = __copy_from_user(kaddr + offset, buf, bytes); - kunmap(page); - } - - written += bytes; - count -= bytes; - pos += bytes; - buf += bytes; - if (pos > inode->i_size) - i_size_write(inode, pos); - - flush_dcache_page(page); - set_page_dirty(page); - mark_page_accessed(page); - page_cache_release(page); + struct inode *inode = mapping->host; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; + *pagep = NULL; + return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); +} - if (left) { - pos -= left; - written -= left; - err = -EFAULT; - break; - } +static int +shmem_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + struct inode *inode = mapping->host; - /* - * Our dirty pages are not counted in nr_dirty, - * and we do not attempt to balance dirty pages. - */ + if (pos + copied > inode->i_size) + i_size_write(inode, pos + copied); - cond_resched(); - } while (count); + unlock_page(page); + set_page_dirty(page); + page_cache_release(page); - *ppos = pos; - if (written) - err = written; -out: - mutex_unlock(&inode->i_mutex); - return err; + return copied; } static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor) @@ -1601,6 +1622,15 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ struct inode *inode = filp->f_path.dentry->d_inode; struct address_space *mapping = inode->i_mapping; unsigned long index, offset; + enum sgp_type sgp = SGP_READ; + + /* + * Might this read be for a stacking filesystem? Then when reading + * holes of a sparse file, we actually need to allocate those pages, + * and even mark them dirty, so it cannot exceed the max_blocks limit. + */ + if (segment_eq(get_fs(), KERNEL_DS)) + sgp = SGP_DIRTY; index = *ppos >> PAGE_CACHE_SHIFT; offset = *ppos & ~PAGE_CACHE_MASK; @@ -1619,12 +1649,14 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ break; } - desc->error = shmem_getpage(inode, index, &page, SGP_READ, NULL); + desc->error = shmem_getpage(inode, index, &page, sgp, NULL); if (desc->error) { if (desc->error == -EINVAL) desc->error = 0; break; } + if (page) + unlock_page(page); /* * We must evaluate after, since reads (unlike writes) @@ -1687,45 +1719,38 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ file_accessed(filp); } -static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - read_descriptor_t desc; - - if ((ssize_t) count < 0) - return -EINVAL; - if (!access_ok(VERIFY_WRITE, buf, count)) - return -EFAULT; - if (!count) - return 0; - - desc.written = 0; - desc.count = count; - desc.arg.buf = buf; - desc.error = 0; - - do_shmem_file_read(filp, ppos, &desc, file_read_actor); - if (desc.written) - return desc.written; - return desc.error; -} - -static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos, - size_t count, read_actor_t actor, void *target) +static ssize_t shmem_file_aio_read(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { - read_descriptor_t desc; + struct file *filp = iocb->ki_filp; + ssize_t retval; + unsigned long seg; + size_t count; + loff_t *ppos = &iocb->ki_pos; - if (!count) - return 0; + retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); + if (retval) + return retval; - desc.written = 0; - desc.count = count; - desc.arg.data = target; - desc.error = 0; + for (seg = 0; seg < nr_segs; seg++) { + read_descriptor_t desc; - do_shmem_file_read(in_file, ppos, &desc, actor); - if (desc.written) - return desc.written; - return desc.error; + desc.written = 0; + desc.arg.buf = iov[seg].iov_base; + desc.count = iov[seg].iov_len; + if (desc.count == 0) + continue; + desc.error = 0; + do_shmem_file_read(filp, ppos, &desc, file_read_actor); + retval += desc.written; + if (desc.error) { + retval = retval ?: desc.error; + break; + } + if (desc.count > 0) + break; + } + return retval; } static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) @@ -1755,9 +1780,10 @@ 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); @@ -1807,22 +1833,16 @@ static int shmem_create(struct inode *dir, struct dentry *dentry, int mode, static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = old_dentry->d_inode; - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + int ret; /* * No ordinary (disk based) filesystem counts links as inodes; * but each new link needs a new dentry, pinning lowmem, and * tmpfs dentries cannot be pruned until they are unlinked. */ - if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - if (!sbinfo->free_inodes) { - spin_unlock(&sbinfo->stat_lock); - return -ENOSPC; - } - sbinfo->free_inodes--; - spin_unlock(&sbinfo->stat_lock); - } + ret = shmem_reserve_inode(inode->i_sb); + if (ret) + goto out; dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; @@ -1830,21 +1850,16 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr atomic_inc(&inode->i_count); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); - return 0; +out: + return ret; } static int shmem_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = dentry->d_inode; - if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) { - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); - } - } + if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) + shmem_free_inode(inode->i_sb); dir->i_size -= BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; @@ -1907,7 +1922,7 @@ 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; @@ -1933,6 +1948,8 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s iput(inode); return error; } + unlock_page(page); + inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; kaddr = kmap_atomic(page, KM_USER0); memcpy(kaddr, symname, len); @@ -1960,6 +1977,8 @@ static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd) struct page *page = NULL; int res = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL); nd_set_link(nd, res ? ERR_PTR(res) : kmap(page)); + if (page) + unlock_page(page); return page; } @@ -1986,7 +2005,7 @@ static const struct inode_operations shmem_symlink_inode_operations = { }; #ifdef CONFIG_TMPFS_POSIX_ACL -/** +/* * Superblocks without xattr inode operations will get security.* xattr * support from the VFS "for free". As soon as we have any other xattrs * like ACLs, we also need to implement the security.* handlers at @@ -2005,8 +2024,7 @@ static int shmem_xattr_security_get(struct inode *inode, const char *name, { if (strcmp(name, "") == 0) return -EINVAL; - return security_inode_getsecurity(inode, name, buffer, size, - -EOPNOTSUPP); + return xattr_getsecurity(inode, name, buffer, size); } static int shmem_xattr_security_set(struct inode *inode, const char *name, @@ -2045,33 +2063,25 @@ static int shmem_match(struct inode *ino, void *vfh) return ino->i_ino == inum && fh[0] == ino->i_generation; } -static struct dentry *shmem_get_dentry(struct super_block *sb, void *vfh) +static struct dentry *shmem_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) { - struct dentry *de = NULL; struct inode *inode; - __u32 *fh = vfh; - __u64 inum = fh[2]; - inum = (inum << 32) | fh[1]; + struct dentry *dentry = NULL; + u64 inum = fid->raw[2]; + inum = (inum << 32) | fid->raw[1]; + + if (fh_len < 3) + return NULL; - inode = ilookup5(sb, (unsigned long)(inum+fh[0]), shmem_match, vfh); + inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]), + shmem_match, fid->raw); if (inode) { - de = d_find_alias(inode); + dentry = d_find_alias(inode); iput(inode); } - return de? de: ERR_PTR(-ESTALE); -} - -static struct dentry *shmem_decode_fh(struct super_block *sb, __u32 *fh, - int len, int type, - int (*acceptable)(void *context, struct dentry *de), - void *context) -{ - if (len < 3) - return ERR_PTR(-ESTALE); - - return sb->s_export_op->find_exported_dentry(sb, fh, NULL, acceptable, - context); + return dentry; } static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len, @@ -2104,16 +2114,14 @@ static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len, return 1; } -static struct export_operations shmem_export_ops = { +static const struct export_operations shmem_export_ops = { .get_parent = shmem_get_parent, - .get_dentry = shmem_get_dentry, .encode_fh = shmem_encode_fh, - .decode_fh = shmem_decode_fh, + .fh_to_dentry = shmem_fh_to_dentry, }; -static int shmem_parse_options(char *options, int *mode, uid_t *uid, - gid_t *gid, unsigned long *blocks, unsigned long *inodes, - int *policy, nodemask_t *policy_nodes) +static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, + bool remount) { char *this_char, *value, *rest; @@ -2156,35 +2164,36 @@ static int shmem_parse_options(char *options, int *mode, uid_t *uid, } if (*rest) goto bad_val; - *blocks = size >> PAGE_CACHE_SHIFT; + sbinfo->max_blocks = + DIV_ROUND_UP(size, PAGE_CACHE_SIZE); } else if (!strcmp(this_char,"nr_blocks")) { - *blocks = memparse(value,&rest); + sbinfo->max_blocks = memparse(value, &rest); if (*rest) goto bad_val; } else if (!strcmp(this_char,"nr_inodes")) { - *inodes = memparse(value,&rest); + sbinfo->max_inodes = memparse(value, &rest); if (*rest) goto bad_val; } else if (!strcmp(this_char,"mode")) { - if (!mode) + if (remount) continue; - *mode = simple_strtoul(value,&rest,8); + sbinfo->mode = simple_strtoul(value, &rest, 8) & 07777; if (*rest) goto bad_val; } else if (!strcmp(this_char,"uid")) { - if (!uid) + if (remount) continue; - *uid = simple_strtoul(value,&rest,0); + sbinfo->uid = simple_strtoul(value, &rest, 0); if (*rest) goto bad_val; } else if (!strcmp(this_char,"gid")) { - if (!gid) + if (remount) continue; - *gid = simple_strtoul(value,&rest,0); + sbinfo->gid = simple_strtoul(value, &rest, 0); if (*rest) goto bad_val; } else if (!strcmp(this_char,"mpol")) { - if (shmem_parse_mpol(value,policy,policy_nodes)) + if (mpol_parse_str(value, &sbinfo->mpol, 1)) goto bad_val; } else { printk(KERN_ERR "tmpfs: Bad mount option %s\n", @@ -2204,24 +2213,20 @@ bad_val: static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); - unsigned long max_blocks = sbinfo->max_blocks; - unsigned long max_inodes = sbinfo->max_inodes; - int policy = sbinfo->policy; - nodemask_t policy_nodes = sbinfo->policy_nodes; + struct shmem_sb_info config = *sbinfo; unsigned long blocks; unsigned long inodes; int error = -EINVAL; - if (shmem_parse_options(data, NULL, NULL, NULL, &max_blocks, - &max_inodes, &policy, &policy_nodes)) + if (shmem_parse_options(data, &config, true)) return error; spin_lock(&sbinfo->stat_lock); blocks = sbinfo->max_blocks - sbinfo->free_blocks; inodes = sbinfo->max_inodes - sbinfo->free_inodes; - if (max_blocks < blocks) + if (config.max_blocks < blocks) goto out; - if (max_inodes < inodes) + if (config.max_inodes < inodes) goto out; /* * Those tests also disallow limited->unlimited while any are in @@ -2229,23 +2234,43 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) * but we must separately disallow unlimited->limited, because * in that case we have no record of how much is already in use. */ - if (max_blocks && !sbinfo->max_blocks) + if (config.max_blocks && !sbinfo->max_blocks) goto out; - if (max_inodes && !sbinfo->max_inodes) + if (config.max_inodes && !sbinfo->max_inodes) goto out; error = 0; - sbinfo->max_blocks = max_blocks; - sbinfo->free_blocks = max_blocks - blocks; - sbinfo->max_inodes = max_inodes; - sbinfo->free_inodes = max_inodes - inodes; - sbinfo->policy = policy; - sbinfo->policy_nodes = policy_nodes; + sbinfo->max_blocks = config.max_blocks; + sbinfo->free_blocks = config.max_blocks - blocks; + sbinfo->max_inodes = config.max_inodes; + sbinfo->free_inodes = config.max_inodes - inodes; + + mpol_put(sbinfo->mpol); + sbinfo->mpol = config.mpol; /* transfers initial ref */ out: spin_unlock(&sbinfo->stat_lock); return error; } -#endif + +static int shmem_show_options(struct seq_file *seq, struct vfsmount *vfs) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(vfs->mnt_sb); + + if (sbinfo->max_blocks != shmem_default_max_blocks()) + 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); + if (sbinfo->mode != (S_IRWXUGO | S_ISVTX)) + seq_printf(seq, ",mode=%03o", sbinfo->mode); + if (sbinfo->uid != 0) + seq_printf(seq, ",uid=%u", sbinfo->uid); + if (sbinfo->gid != 0) + seq_printf(seq, ",gid=%u", sbinfo->gid); + shmem_show_mpol(seq, sbinfo->mpol); + return 0; +} +#endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb) { @@ -2258,15 +2283,22 @@ static int shmem_fill_super(struct super_block *sb, { struct inode *inode; struct dentry *root; - int mode = S_IRWXUGO | S_ISVTX; - uid_t uid = current->fsuid; - gid_t gid = current->fsgid; - int err = -ENOMEM; struct shmem_sb_info *sbinfo; - unsigned long blocks = 0; - unsigned long inodes = 0; - int policy = MPOL_DEFAULT; - nodemask_t policy_nodes = node_online_map; + int err = -ENOMEM; + + /* Round up to L1_CACHE_BYTES to resist false sharing */ + sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info), + L1_CACHE_BYTES), GFP_KERNEL); + if (!sbinfo) + return -ENOMEM; + + sbinfo->max_blocks = 0; + sbinfo->max_inodes = 0; + sbinfo->mode = S_IRWXUGO | S_ISVTX; + sbinfo->uid = current_fsuid(); + sbinfo->gid = current_fsgid(); + sbinfo->mpol = NULL; + sb->s_fs_info = sbinfo; #ifdef CONFIG_TMPFS /* @@ -2275,34 +2307,22 @@ static int shmem_fill_super(struct super_block *sb, * but the internal instance is left unlimited. */ if (!(sb->s_flags & MS_NOUSER)) { - blocks = totalram_pages / 2; - inodes = totalram_pages - totalhigh_pages; - if (inodes > blocks) - inodes = blocks; - if (shmem_parse_options(data, &mode, &uid, &gid, &blocks, - &inodes, &policy, &policy_nodes)) - return -EINVAL; + sbinfo->max_blocks = shmem_default_max_blocks(); + sbinfo->max_inodes = shmem_default_max_inodes(); + if (shmem_parse_options(data, sbinfo, false)) { + err = -EINVAL; + goto failed; + } } sb->s_export_op = &shmem_export_ops; #else sb->s_flags |= MS_NOUSER; #endif - /* Round up to L1_CACHE_BYTES to resist false sharing */ - sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info), - L1_CACHE_BYTES), GFP_KERNEL); - if (!sbinfo) - return -ENOMEM; - spin_lock_init(&sbinfo->stat_lock); - sbinfo->max_blocks = blocks; - sbinfo->free_blocks = blocks; - sbinfo->max_inodes = inodes; - sbinfo->free_inodes = inodes; - sbinfo->policy = policy; - sbinfo->policy_nodes = policy_nodes; + sbinfo->free_blocks = sbinfo->max_blocks; + sbinfo->free_inodes = sbinfo->max_inodes; - sb->s_fs_info = sbinfo; sb->s_maxbytes = SHMEM_MAX_BYTES; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; @@ -2314,11 +2334,11 @@ static int shmem_fill_super(struct super_block *sb, sb->s_flags |= MS_POSIXACL; #endif - inode = shmem_get_inode(sb, S_IFDIR | mode, 0); + inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (!inode) goto failed; - inode->i_uid = uid; - inode->i_gid = gid; + inode->i_uid = sbinfo->uid; + inode->i_gid = sbinfo->gid; root = d_alloc_root(inode); if (!root) goto failed_iput; @@ -2353,28 +2373,22 @@ static void shmem_destroy_inode(struct inode *inode) kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } -static void init_once(void *foo, struct kmem_cache *cachep, - unsigned long flags) +static void init_once(void *foo) { struct shmem_inode_info *p = (struct shmem_inode_info *) foo; - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == - SLAB_CTOR_CONSTRUCTOR) { - inode_init_once(&p->vfs_inode); + inode_init_once(&p->vfs_inode); #ifdef CONFIG_TMPFS_POSIX_ACL - p->i_acl = NULL; - p->i_default_acl = NULL; + p->i_acl = NULL; + p->i_default_acl = NULL; #endif - } } static int init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), - 0, 0, init_once, NULL); - if (shmem_inode_cachep == NULL) - return -ENOMEM; + 0, SLAB_PANIC, init_once); return 0; } @@ -2387,8 +2401,9 @@ static const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, #ifdef CONFIG_TMPFS - .prepare_write = shmem_prepare_write, - .commit_write = simple_commit_write, + .readpage = shmem_readpage, + .write_begin = shmem_write_begin, + .write_end = shmem_write_end, #endif .migratepage = migrate_page, }; @@ -2397,10 +2412,13 @@ static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS .llseek = generic_file_llseek, - .read = shmem_file_read, - .write = shmem_file_write, + .read = do_sync_read, + .write = do_sync_write, + .aio_read = shmem_file_aio_read, + .aio_write = generic_file_aio_write, .fsync = simple_sync_file, - .sendfile = shmem_file_sendfile, + .splice_read = generic_file_splice_read, + .splice_write = generic_file_splice_write, #endif }; @@ -2457,6 +2475,7 @@ static const struct super_operations shmem_ops = { #ifdef CONFIG_TMPFS .statfs = shmem_statfs, .remount_fs = shmem_remount_fs, + .show_options = shmem_show_options, #endif .delete_inode = shmem_delete_inode, .drop_inode = generic_delete_inode, @@ -2464,8 +2483,7 @@ static const struct super_operations shmem_ops = { }; static struct vm_operations_struct shmem_vm_ops = { - .nopage = shmem_nopage, - .populate = shmem_populate, + .fault = shmem_fault, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, @@ -2485,12 +2503,15 @@ static struct file_system_type tmpfs_fs_type = { .get_sb = shmem_get_sb, .kill_sb = kill_litter_super, }; -static struct vfsmount *shm_mnt; static int __init init_tmpfs(void) { int error; + error = bdi_init(&shmem_backing_dev_info); + if (error) + goto out4; + error = init_inodecache(); if (error) goto out3; @@ -2515,17 +2536,62 @@ out1: out2: destroy_inodecache(); out3: + bdi_destroy(&shmem_backing_dev_info); +out4: shm_mnt = ERR_PTR(error); return error; } -module_init(init_tmpfs) + +#else /* !CONFIG_SHMEM */ /* - * shmem_file_setup - get an unlinked file living in tmpfs + * tiny-shmem: simple shmemfs and tmpfs using ramfs code * + * This is intended for small system where the benefits of the full + * shmem code (swap-backed and resource-limited) are outweighed by + * their complexity. On systems without swap this code should be + * effectively equivalent, but much lighter weight. + */ + +#include + +static struct file_system_type tmpfs_fs_type = { + .name = "tmpfs", + .get_sb = ramfs_get_sb, + .kill_sb = kill_litter_super, +}; + +static int __init init_tmpfs(void) +{ + BUG_ON(register_filesystem(&tmpfs_fs_type) != 0); + + shm_mnt = kern_mount(&tmpfs_fs_type); + BUG_ON(IS_ERR(shm_mnt)); + + return 0; +} + +int shmem_unuse(swp_entry_t entry, struct page *page) +{ + return 0; +} + +#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 */ + +/* common code */ + +/** + * shmem_file_setup - get an unlinked file living in tmpfs * @name: name for dentry (to be seen in /proc//maps * @size: size to be set for the file - * + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) { @@ -2559,19 +2625,21 @@ 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; - SHMEM_I(inode)->flags = flags & VM_ACCOUNT; d_instantiate(dentry, inode); inode->i_size = size; inode->i_nlink = 0; /* It is unlinked */ - file->f_path.mnt = mntget(shm_mnt); - file->f_path.dentry = dentry; - file->f_mapping = inode->i_mapping; - file->f_op = &shmem_file_operations; - file->f_mode = FMODE_WRITE | FMODE_READ; + init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ, + &shmem_file_operations); + +#ifndef CONFIG_MMU + error = ramfs_nommu_expand_for_mapping(inode, size); + if (error) + goto close_file; +#endif return file; close_file: @@ -2582,10 +2650,10 @@ put_memory: shmem_unacct_size(flags, size); return ERR_PTR(error); } +EXPORT_SYMBOL_GPL(shmem_file_setup); -/* +/** * shmem_zero_setup - setup a shared anonymous mapping - * * @vma: the vma to be mmapped is prepared by do_mmap_pgoff */ int shmem_zero_setup(struct vm_area_struct *vma) @@ -2597,9 +2665,12 @@ 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; vma->vm_ops = &shmem_vm_ops; return 0; } + +module_init(init_tmpfs)