From 75edd345e8ede51bc8f00672feff5d622f2b3af6 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 19 May 2016 17:12:44 -0700 Subject: tmpfs: preliminary minor tidyups Make a few cleanups in mm/shmem.c, before going on to complicate it. shmem_alloc_page() will become more complicated: we can't afford to to have that complication duplicated between a CONFIG_NUMA version and a !CONFIG_NUMA version, so rearrange the #ifdef'ery there to yield a single shmem_swapin() and a single shmem_alloc_page(). Yes, it's a shame to inflict the horrid pseudo-vma on non-NUMA configurations, but eliminating it is a larger cleanup: I have an alloc_pages_mpol() patchset not yet ready - mpol handling is subtle and bug-prone, and changed yet again since my last version. Move __SetPageLocked, __SetPageSwapBacked from shmem_getpage_gfp() to shmem_alloc_page(): that SwapBacked flag will be useful in future, to help to distinguish different cases appropriately. And the SGP_DIRTY variant of SGP_CACHE is hard to understand and of little use (IIRC it dates back to when shmem_getpage() returned the page unlocked): kill it and do the necessary in shmem_file_read_iter(). But an arm64 build then complained that info may be uninitialized (where shmem_getpage_gfp() deletes a freshly alloced page beyond eof), and advancing to an "sgp <= SGP_CACHE" test jogged it back to reality. Signed-off-by: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Andres Lagar-Cavilla Cc: Yang Shi Cc: Ning Qu Cc: Mel Gorman Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 69 +++++++++++++++++++++++--------------------------------------- 1 file changed, 26 insertions(+), 43 deletions(-) (limited to 'mm/shmem.c') diff --git a/mm/shmem.c b/mm/shmem.c index 9e609d58df73..6d2de2c1bf11 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -101,7 +101,6 @@ struct shmem_falloc { enum sgp_type { 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 !Uptodate page */ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; @@ -169,7 +168,7 @@ static inline int shmem_reacct_size(unsigned long flags, /* * ... whereas tmpfs objects are accounted incrementally as - * pages are allocated, in order to allow huge sparse files. + * pages are allocated, in order to allow large sparse files. * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ @@ -947,8 +946,7 @@ redirty: return 0; } -#ifdef CONFIG_NUMA -#ifdef CONFIG_TMPFS +#if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { char buffer[64]; @@ -972,7 +970,18 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) } return mpol; } -#endif /* CONFIG_TMPFS */ +#else /* !CONFIG_NUMA || !CONFIG_TMPFS */ +static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) +{ +} +static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) +{ + return NULL; +} +#endif /* CONFIG_NUMA && CONFIG_TMPFS */ +#ifndef CONFIG_NUMA +#define vm_policy vm_private_data +#endif static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) @@ -1008,39 +1017,17 @@ static struct page *shmem_alloc_page(gfp_t gfp, pvma.vm_ops = NULL; pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); - page = alloc_page_vma(gfp, &pvma, 0); + page = alloc_pages_vma(gfp, 0, &pvma, 0, numa_node_id(), false); + if (page) { + __SetPageLocked(page); + __SetPageSwapBacked(page); + } /* Drop reference taken by mpol_shared_policy_lookup() */ mpol_cond_put(pvma.vm_policy); return page; } -#else /* !CONFIG_NUMA */ -#ifdef CONFIG_TMPFS -static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) -{ -} -#endif /* CONFIG_TMPFS */ - -static inline struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, - struct shmem_inode_info *info, pgoff_t index) -{ - return swapin_readahead(swap, gfp, NULL, 0); -} - -static inline struct page *shmem_alloc_page(gfp_t gfp, - struct shmem_inode_info *info, pgoff_t index) -{ - return alloc_page(gfp); -} -#endif /* CONFIG_NUMA */ - -#if !defined(CONFIG_NUMA) || !defined(CONFIG_TMPFS) -static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) -{ - return NULL; -} -#endif /* * When a page is moved from swapcache to shmem filecache (either by the @@ -1084,8 +1071,6 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, copy_highpage(newpage, oldpage); flush_dcache_page(newpage); - __SetPageLocked(newpage); - __SetPageSwapBacked(newpage); SetPageUptodate(newpage); set_page_private(newpage, swap_index); SetPageSwapCache(newpage); @@ -1155,7 +1140,7 @@ repeat: page = NULL; } - if (sgp != SGP_WRITE && sgp != SGP_FALLOC && + if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { error = -EINVAL; goto unlock; @@ -1275,9 +1260,6 @@ repeat: error = -ENOMEM; goto decused; } - - __SetPageLocked(page); - __SetPageSwapBacked(page); if (sgp == SGP_WRITE) __SetPageReferenced(page); @@ -1321,12 +1303,10 @@ clear: flush_dcache_page(page); SetPageUptodate(page); } - if (sgp == SGP_DIRTY) - set_page_dirty(page); } /* Perhaps the file has been truncated since we checked */ - if (sgp != SGP_WRITE && sgp != SGP_FALLOC && + if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { if (alloced) { ClearPageDirty(page); @@ -1633,7 +1613,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) * and even mark them dirty, so it cannot exceed the max_blocks limit. */ if (!iter_is_iovec(to)) - sgp = SGP_DIRTY; + sgp = SGP_CACHE; index = *ppos >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; @@ -1659,8 +1639,11 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) error = 0; break; } - if (page) + if (page) { + if (sgp == SGP_CACHE) + set_page_dirty(page); unlock_page(page); + } /* * We must evaluate after, since reads (unlike writes) -- cgit