diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/filemap.c | 158 | ||||
| -rw-r--r-- | mm/huge_memory.c | 57 | ||||
| -rw-r--r-- | mm/hugetlb.c | 71 | ||||
| -rw-r--r-- | mm/hugetlb_cgroup.c | 37 | ||||
| -rw-r--r-- | mm/iov_iter.c | 595 | ||||
| -rw-r--r-- | mm/ksm.c | 1 | ||||
| -rw-r--r-- | mm/memcontrol.c | 188 | ||||
| -rw-r--r-- | mm/memory-failure.c | 9 | ||||
| -rw-r--r-- | mm/mempolicy.c | 48 | ||||
| -rw-r--r-- | mm/migrate.c | 2 | ||||
| -rw-r--r-- | mm/msync.c | 3 | ||||
| -rw-r--r-- | mm/nommu.c | 2 | ||||
| -rw-r--r-- | mm/page_alloc.c | 56 | ||||
| -rw-r--r-- | mm/page_io.c | 21 | ||||
| -rw-r--r-- | mm/process_vm_access.c | 10 | ||||
| -rw-r--r-- | mm/rmap.c | 12 | ||||
| -rw-r--r-- | mm/shmem.c | 100 | ||||
| -rw-r--r-- | mm/slab.c | 90 | ||||
| -rw-r--r-- | mm/slub.c | 6 | ||||
| -rw-r--r-- | mm/vmscan.c | 2 |
20 files changed, 1050 insertions, 418 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index 7fadf1c62838..dafb06f70a09 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1665,96 +1665,42 @@ out: return written ? written : error; } -/* - * Performs necessary checks before doing a write - * @iov: io vector request - * @nr_segs: number of segments in the iovec - * @count: number of bytes to write - * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE - * - * Adjust number of segments and amount of bytes to write (nr_segs should be - * properly initialized first). Returns appropriate error code that caller - * should return or zero in case that write should be allowed. - */ -int generic_segment_checks(const struct iovec *iov, - unsigned long *nr_segs, size_t *count, int access_flags) -{ - unsigned long seg; - size_t cnt = 0; - for (seg = 0; seg < *nr_segs; seg++) { - const struct iovec *iv = &iov[seg]; - - /* - * If any segment has a negative length, or the cumulative - * length ever wraps negative then return -EINVAL. - */ - cnt += iv->iov_len; - if (unlikely((ssize_t)(cnt|iv->iov_len) < 0)) - return -EINVAL; - if (access_ok(access_flags, iv->iov_base, iv->iov_len)) - continue; - if (seg == 0) - return -EFAULT; - *nr_segs = seg; - cnt -= iv->iov_len; /* This segment is no good */ - break; - } - *count = cnt; - return 0; -} -EXPORT_SYMBOL(generic_segment_checks); - /** - * generic_file_aio_read - generic filesystem read routine + * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block - * @iov: io vector request - * @nr_segs: number of segments in the iovec - * @pos: current file position + * @iter: destination for the data read * - * This is the "read()" routine for all filesystems + * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. */ ssize_t -generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct file *filp = iocb->ki_filp; - ssize_t retval; - size_t count; + struct file *file = iocb->ki_filp; + ssize_t retval = 0; loff_t *ppos = &iocb->ki_pos; - struct iov_iter i; - - count = 0; - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; - iov_iter_init(&i, iov, nr_segs, count, 0); + loff_t pos = *ppos; /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ - if (filp->f_flags & O_DIRECT) { + if (file->f_flags & O_DIRECT) { + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); loff_t size; - struct address_space *mapping; - struct inode *inode; - mapping = filp->f_mapping; - inode = mapping->host; if (!count) goto out; /* skip atime */ size = i_size_read(inode); retval = filemap_write_and_wait_range(mapping, pos, - pos + iov_length(iov, nr_segs) - 1); + pos + count - 1); if (!retval) { - retval = mapping->a_ops->direct_IO(READ, iocb, - iov, pos, nr_segs); + struct iov_iter data = *iter; + retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos); } + if (retval > 0) { *ppos = pos + retval; - count -= retval; - /* - * If we did a short DIO read we need to skip the - * section of the iov that we've already read data into. - */ - iov_iter_advance(&i, retval); + iov_iter_advance(iter, retval); } /* @@ -1765,17 +1711,17 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, * and return. Otherwise fallthrough to buffered io for * the rest of the read. */ - if (retval < 0 || !count || *ppos >= size) { - file_accessed(filp); + if (retval < 0 || !iov_iter_count(iter) || *ppos >= size) { + file_accessed(file); goto out; } } - retval = do_generic_file_read(filp, ppos, &i, retval); + retval = do_generic_file_read(file, ppos, iter, retval); out: return retval; } -EXPORT_SYMBOL(generic_file_aio_read); +EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU /** @@ -2386,9 +2332,7 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, EXPORT_SYMBOL(pagecache_write_end); ssize_t -generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long *nr_segs, loff_t pos, - size_t count, size_t ocount) +generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -2396,11 +2340,9 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, ssize_t written; size_t write_len; pgoff_t end; + struct iov_iter data; - if (count != ocount) - *nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count); - - write_len = iov_length(iov, *nr_segs); + write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT; written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); @@ -2427,7 +2369,8 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, } } - written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs); + data = *from; + written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos); /* * Finally, try again to invalidate clean pages which might have been @@ -2444,6 +2387,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, if (written > 0) { pos += written; + iov_iter_advance(from, written); if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); @@ -2568,10 +2512,9 @@ again: EXPORT_SYMBOL(generic_perform_write); /** - * __generic_file_aio_write - write data to a file + * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) - * @iov: vector with data to write - * @nr_segs: number of segments in the vector + * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates @@ -2585,26 +2528,16 @@ EXPORT_SYMBOL(generic_perform_write); * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. */ -ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs) +ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; - size_t ocount; /* original count */ - size_t count; /* after file limit checks */ struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; ssize_t written = 0; ssize_t err; ssize_t status; - struct iov_iter from; - - ocount = 0; - err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); - if (err) - return err; - - count = ocount; + size_t count = iov_iter_count(from); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; @@ -2615,6 +2548,8 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; + iov_iter_truncate(from, count); + err = file_remove_suid(file); if (err) goto out; @@ -2623,17 +2558,13 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err) goto out; - iov_iter_init(&from, iov, nr_segs, count, 0); - /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { loff_t endbyte; - written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos, - count, ocount); + written = generic_file_direct_write(iocb, from, pos); if (written < 0 || written == count) goto out; - iov_iter_advance(&from, written); /* * direct-io write to a hole: fall through to buffered I/O @@ -2642,7 +2573,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, pos += written; count -= written; - status = generic_perform_write(file, &from, pos); + status = generic_perform_write(file, from, pos); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were @@ -2674,7 +2605,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, */ } } else { - written = generic_perform_write(file, &from, pos); + written = generic_perform_write(file, from, pos); if (likely(written >= 0)) iocb->ki_pos = pos + written; } @@ -2682,30 +2613,25 @@ out: current->backing_dev_info = NULL; return written ? written : err; } -EXPORT_SYMBOL(__generic_file_aio_write); +EXPORT_SYMBOL(__generic_file_write_iter); /** - * generic_file_aio_write - write data to a file + * generic_file_write_iter - write data to a file * @iocb: IO state structure - * @iov: vector with data to write - * @nr_segs: number of segments in the vector - * @pos: position in file where to write + * @from: iov_iter with data to write * - * This is a wrapper around __generic_file_aio_write() to be used by most + * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. */ -ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; - BUG_ON(iocb->ki_pos != pos); - mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write(iocb, iov, nr_segs); + ret = __generic_file_write_iter(iocb, from); mutex_unlock(&inode->i_mutex); if (ret > 0) { @@ -2717,7 +2643,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } return ret; } -EXPORT_SYMBOL(generic_file_aio_write); +EXPORT_SYMBOL(generic_file_write_iter); /** * try_to_release_page() - release old fs-specific metadata on a page diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e60837dc785c..33514d88fef9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -941,6 +941,37 @@ unlock: spin_unlock(ptl); } +/* + * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages + * during copy_user_huge_page()'s copy_page_rep(): in the case when + * the source page gets split and a tail freed before copy completes. + * Called under pmd_lock of checked pmd, so safe from splitting itself. + */ +static void get_user_huge_page(struct page *page) +{ + if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) { + struct page *endpage = page + HPAGE_PMD_NR; + + atomic_add(HPAGE_PMD_NR, &page->_count); + while (++page < endpage) + get_huge_page_tail(page); + } else { + get_page(page); + } +} + +static void put_user_huge_page(struct page *page) +{ + if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) { + struct page *endpage = page + HPAGE_PMD_NR; + + while (page < endpage) + put_page(page++); + } else { + put_page(page); + } +} + static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -1074,7 +1105,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, ret |= VM_FAULT_WRITE; goto out_unlock; } - get_page(page); + get_user_huge_page(page); spin_unlock(ptl); alloc: if (transparent_hugepage_enabled(vma) && @@ -1095,7 +1126,7 @@ alloc: split_huge_page(page); ret |= VM_FAULT_FALLBACK; } - put_page(page); + put_user_huge_page(page); } count_vm_event(THP_FAULT_FALLBACK); goto out; @@ -1105,7 +1136,7 @@ alloc: put_page(new_page); if (page) { split_huge_page(page); - put_page(page); + put_user_huge_page(page); } else split_huge_page_pmd(vma, address, pmd); ret |= VM_FAULT_FALLBACK; @@ -1127,7 +1158,7 @@ alloc: spin_lock(ptl); if (page) - put_page(page); + put_user_huge_page(page); if (unlikely(!pmd_same(*pmd, orig_pmd))) { spin_unlock(ptl); mem_cgroup_uncharge_page(new_page); @@ -2392,8 +2423,6 @@ static void collapse_huge_page(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; anon_vma_lock_write(vma->anon_vma); @@ -2492,8 +2521,6 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); @@ -2846,12 +2873,22 @@ void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, static void split_huge_page_address(struct mm_struct *mm, unsigned long address) { + pgd_t *pgd; + pud_t *pud; pmd_t *pmd; VM_BUG_ON(!(address & ~HPAGE_PMD_MASK)); - pmd = mm_find_pmd(mm, address); - if (!pmd) + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + return; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return; + + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) return; /* * Caller holds the mmap_sem write mode, so a huge pmd cannot diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 226910cb7c9b..2024bbd573d2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2520,6 +2520,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma, update_mmu_cache(vma, address, ptep); } +static int is_hugetlb_entry_migration(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return 0; + swp = pte_to_swp_entry(pte); + if (non_swap_entry(swp) && is_migration_entry(swp)) + return 1; + else + return 0; +} + +static int is_hugetlb_entry_hwpoisoned(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return 0; + swp = pte_to_swp_entry(pte); + if (non_swap_entry(swp) && is_hwpoison_entry(swp)) + return 1; + else + return 0; +} int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) @@ -2559,10 +2584,26 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); - if (!huge_pte_none(huge_ptep_get(src_pte))) { + entry = huge_ptep_get(src_pte); + if (huge_pte_none(entry)) { /* skip none entry */ + ; + } else if (unlikely(is_hugetlb_entry_migration(entry) || + is_hugetlb_entry_hwpoisoned(entry))) { + swp_entry_t swp_entry = pte_to_swp_entry(entry); + + if (is_write_migration_entry(swp_entry) && cow) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&swp_entry); + entry = swp_entry_to_pte(swp_entry); + set_huge_pte_at(src, addr, src_pte, entry); + } + set_huge_pte_at(dst, addr, dst_pte, entry); + } else { if (cow) huge_ptep_set_wrprotect(src, addr, src_pte); - entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); page_dup_rmap(ptepage); @@ -2578,32 +2619,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, return ret; } -static int is_hugetlb_entry_migration(pte_t pte) -{ - swp_entry_t swp; - - if (huge_pte_none(pte) || pte_present(pte)) - return 0; - swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_migration_entry(swp)) - return 1; - else - return 0; -} - -static int is_hugetlb_entry_hwpoisoned(pte_t pte) -{ - swp_entry_t swp; - - if (huge_pte_none(pte) || pte_present(pte)) - return 0; - swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_hwpoison_entry(swp)) - return 1; - else - return 0; -} - void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 595d7fd795e1..493f758445e7 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -52,7 +52,7 @@ static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) static inline struct hugetlb_cgroup * parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg) { - return hugetlb_cgroup_from_css(css_parent(&h_cg->css)); + return hugetlb_cgroup_from_css(h_cg->css.parent); } static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) @@ -181,7 +181,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); - if (!css_tryget(&h_cg->css)) { + if (!css_tryget_online(&h_cg->css)) { rcu_read_unlock(); goto again; } @@ -253,15 +253,16 @@ static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, return res_counter_read_u64(&h_cg->hugepage[idx], name); } -static int hugetlb_cgroup_write(struct cgroup_subsys_state *css, - struct cftype *cft, char *buffer) +static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { int idx, name, ret; unsigned long long val; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); - idx = MEMFILE_IDX(cft->private); - name = MEMFILE_ATTR(cft->private); + buf = strstrip(buf); + idx = MEMFILE_IDX(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_LIMIT: @@ -271,7 +272,7 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css, break; } /* This function does all necessary parse...reuse it */ - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; ret = res_counter_set_limit(&h_cg->hugepage[idx], val); @@ -280,17 +281,17 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css, ret = -EINVAL; break; } - return ret; + return ret ?: nbytes; } -static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css, - unsigned int event) +static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { int idx, name, ret = 0; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); - idx = MEMFILE_IDX(event); - name = MEMFILE_ATTR(event); + idx = MEMFILE_IDX(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_MAX_USAGE: @@ -303,7 +304,7 @@ static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css, ret = -EINVAL; break; } - return ret; + return ret ?: nbytes; } static char *mem_fmt(char *buf, int size, unsigned long hsize) @@ -331,7 +332,7 @@ static void __init __hugetlb_cgroup_file_init(int idx) snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); cft->read_u64 = hugetlb_cgroup_read_u64; - cft->write_string = hugetlb_cgroup_write; + cft->write = hugetlb_cgroup_write; /* Add the usage file */ cft = &h->cgroup_files[1]; @@ -343,14 +344,14 @@ static void __init __hugetlb_cgroup_file_init(int idx) cft = &h->cgroup_files[2]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); - cft->trigger = hugetlb_cgroup_reset; + cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; /* Add the failcntfile */ cft = &h->cgroup_files[3]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); - cft->trigger = hugetlb_cgroup_reset; + cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; /* NULL terminate the last cft */ diff --git a/mm/iov_iter.c b/mm/iov_iter.c index 10e46cd721de..7b5dbd1517b5 100644 --- a/mm/iov_iter.c +++ b/mm/iov_iter.c @@ -1,8 +1,10 @@ #include <linux/export.h> #include <linux/uio.h> #include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> -size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, +static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t skip, copy, left, wanted; @@ -72,13 +74,97 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, } kunmap(page); done: + if (skip == iov->iov_len) { + iov++; + skip = 0; + } + i->count -= wanted - bytes; + i->nr_segs -= iov - i->iov; + i->iov = iov; + i->iov_offset = skip; + return wanted - bytes; +} + +static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, left, wanted; + const struct iovec *iov; + char __user *buf; + void *kaddr, *to; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + iov = i->iov; + skip = i->iov_offset; + buf = iov->iov_base + skip; + copy = min(bytes, iov->iov_len - skip); + + if (!fault_in_pages_readable(buf, copy)) { + kaddr = kmap_atomic(page); + to = kaddr + offset; + + /* first chunk, usually the only one */ + left = __copy_from_user_inatomic(to, buf, copy); + copy -= left; + skip += copy; + to += copy; + bytes -= copy; + + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_from_user_inatomic(to, buf, copy); + copy -= left; + skip = copy; + to += copy; + bytes -= copy; + } + if (likely(!bytes)) { + kunmap_atomic(kaddr); + goto done; + } + offset = to - kaddr; + buf += copy; + kunmap_atomic(kaddr); + copy = min(bytes, iov->iov_len - skip); + } + /* Too bad - revert to non-atomic kmap */ + kaddr = kmap(page); + to = kaddr + offset; + left = __copy_from_user(to, buf, copy); + copy -= left; + skip += copy; + to += copy; + bytes -= copy; + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_from_user(to, buf, copy); + copy -= left; + skip = copy; + to += copy; + bytes -= copy; + } + kunmap(page); +done: + if (skip == iov->iov_len) { + iov++; + skip = 0; + } i->count -= wanted - bytes; i->nr_segs -= iov - i->iov; i->iov = iov; i->iov_offset = skip; return wanted - bytes; } -EXPORT_SYMBOL(copy_page_to_iter); static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) @@ -107,7 +193,7 @@ static size_t __iovec_copy_from_user_inatomic(char *vaddr, * were successfully copied. If a fault is encountered then return the number of * bytes which were copied. */ -size_t iov_iter_copy_from_user_atomic(struct page *page, +static size_t copy_from_user_atomic_iovec(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes) { char *kaddr; @@ -127,36 +213,8 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, return copied; } -EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); - -/* - * This has the same sideeffects and return value as - * iov_iter_copy_from_user_atomic(). - * The difference is that it attempts to resolve faults. - * Page must not be locked. - */ -size_t iov_iter_copy_from_user(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - kaddr = kmap(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap(page); - return copied; -} -EXPORT_SYMBOL(iov_iter_copy_from_user); -void iov_iter_advance(struct iov_iter *i, size_t bytes) +static void advance_iovec(struct iov_iter *i, size_t bytes) { BUG_ON(i->count < bytes); @@ -191,7 +249,6 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes) i->nr_segs = nr_segs; } } -EXPORT_SYMBOL(iov_iter_advance); /* * Fault in the first iovec of the given iov_iter, to a maximum length @@ -204,21 +261,483 @@ EXPORT_SYMBOL(iov_iter_advance); */ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { - char __user *buf = i->iov->iov_base + i->iov_offset; - bytes = min(bytes, i->iov->iov_len - i->iov_offset); - return fault_in_pages_readable(buf, bytes); + if (!(i->type & ITER_BVEC)) { + char __user *buf = i->iov->iov_base + i->iov_offset; + bytes = min(bytes, i->iov->iov_len - i->iov_offset); + return fault_in_pages_readable(buf, bytes); + } + return 0; } EXPORT_SYMBOL(iov_iter_fault_in_readable); +static unsigned long alignment_iovec(const struct iov_iter *i) +{ + const struct iovec *iov = i->iov; + unsigned long res; + size_t size = i->count; + size_t n; + + if (!size) + return 0; + + res = (unsigned long)iov->iov_base + i->iov_offset; + n = iov->iov_len - i->iov_offset; + if (n >= size) + return res | size; + size -= n; + res |= n; + while (size > (++iov)->iov_len) { + res |= (unsigned long)iov->iov_base | iov->iov_len; + size -= iov->iov_len; + } + res |= (unsigned long)iov->iov_base | size; + return res; +} + +void iov_iter_init(struct iov_iter *i, int direction, + const struct iovec *iov, unsigned long nr_segs, + size_t count) +{ + /* It will get better. Eventually... */ + if (segment_eq(get_fs(), KERNEL_DS)) + direction |= ITER_KVEC; + i->type = direction; + i->iov = iov; + i->nr_segs = nr_segs; + i->iov_offset = 0; + i->count = count; +} +EXPORT_SYMBOL(iov_iter_init); + +static ssize_t get_pages_iovec(struct iov_iter *i, + struct page **pages, size_t maxsize, + size_t *start) +{ + size_t offset = i->iov_offset; + const struct iovec *iov = i->iov; + size_t len; + unsigned long addr; + int n; + int res; + + len = iov->iov_len - offset; + if (len > i->count) + len = i->count; + if (len > maxsize) + len = maxsize; + addr = (unsigned long)iov->iov_base + offset; + len += *start = addr & (PAGE_SIZE - 1); + addr &= ~(PAGE_SIZE - 1); + n = (len + PAGE_SIZE - 1) / PAGE_SIZE; + res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); + if (unlikely(res < 0)) + return res; + return (res == n ? len : res * PAGE_SIZE) - *start; +} + +static ssize_t get_pages_alloc_iovec(struct iov_iter *i, + struct page ***pages, size_t maxsize, + size_t *start) +{ + size_t offset = i->iov_offset; + const struct iovec *iov = i->iov; + size_t len; + unsigned long addr; + void *p; + int n; + int res; + + len = iov->iov_len - offset; + if (len > i->count) + len = i->count; + if (len > maxsize) + len = maxsize; + addr = (unsigned long)iov->iov_base + offset; + len += *start = addr & (PAGE_SIZE - 1); + addr &= ~(PAGE_SIZE - 1); + n = (len + PAGE_SIZE - 1) / PAGE_SIZE; + + p = kmalloc(n * sizeof(struct page *), GFP_KERNEL); + if (!p) + p = vmalloc(n * sizeof(struct page *)); + if (!p) + return -ENOMEM; + + res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); + if (unlikely(res < 0)) { + kvfree(p); + return res; + } + *pages = p; + return (res == n ? len : res * PAGE_SIZE) - *start; +} + +static int iov_iter_npages_iovec(const struct iov_iter *i, int maxpages) +{ + size_t offset = i->iov_offset; + size_t size = i->count; + const struct iovec *iov = i->iov; + int npages = 0; + int n; + + for (n = 0; size && n < i->nr_segs; n++, iov++) { + unsigned long addr = (unsigned long)iov->iov_base + offset; + size_t len = iov->iov_len - offset; + offset = 0; + if (unlikely(!len)) /* empty segment */ + continue; + if (len > size) + len = size; + npages += (addr + len + PAGE_SIZE - 1) / PAGE_SIZE + - addr / PAGE_SIZE; + if (npages >= maxpages) /* don't bother going further */ + return maxpages; + size -= len; + offset = 0; + } + return min(npages, maxpages); +} + +static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) +{ + char *from = kmap_atomic(page); + memcpy(to, from + offset, len); + kunmap_atomic(from); +} + +static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t len) +{ + char *to = kmap_atomic(page); + memcpy(to + offset, from, len); + kunmap_atomic(to); +} + +static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, wanted; + const struct bio_vec *bvec; + void *kaddr, *from; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + bvec = i->bvec; + skip = i->iov_offset; + copy = min_t(size_t, bytes, bvec->bv_len - skip); + + kaddr = kmap_atomic(page); + from = kaddr + offset; + memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy); + skip += copy; + from += copy; + bytes -= copy; + while (bytes) { + bvec++; + copy = min(bytes, (size_t)bvec->bv_len); + memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, copy); + skip = copy; + from += copy; + bytes -= copy; + } + kunmap_atomic(kaddr); + if (skip == bvec->bv_len) { + bvec++; + skip = 0; + } + i->count -= wanted - bytes; + i->nr_segs -= bvec - i->bvec; + i->bvec = bvec; + i->iov_offset = skip; + return wanted - bytes; +} + +static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, wanted; + const struct bio_vec *bvec; + void *kaddr, *to; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + bvec = i->bvec; + skip = i->iov_offset; + + kaddr = kmap_atomic(page); + + to = kaddr + offset; + + copy = min(bytes, bvec->bv_len - skip); + + memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy); + + to += copy; + skip += copy; + bytes -= copy; + + while (bytes) { + bvec++; + copy = min(bytes, (size_t)bvec->bv_len); + memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, copy); + skip = copy; + to += copy; + bytes -= copy; + } + kunmap_atomic(kaddr); + if (skip == bvec->bv_len) { + bvec++; + skip = 0; + } + i->count -= wanted; + i->nr_segs -= bvec - i->bvec; + i->bvec = bvec; + i->iov_offset = skip; + return wanted; +} + +static size_t copy_from_user_bvec(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t left; + const struct bio_vec *bvec; + size_t base = i->iov_offset; + + kaddr = kmap_atomic(page); + for (left = bytes, bvec = i->bvec; left; bvec++, base = 0) { + size_t copy = min(left, bvec->bv_len - base); + if (!bvec->bv_len) + continue; + memcpy_from_page(kaddr + offset, bvec->bv_page, + bvec->bv_offset + base, copy); + offset += copy; + left -= copy; + } + kunmap_atomic(kaddr); + return bytes; +} + +static void advance_bvec(struct iov_iter *i, size_t bytes) +{ + BUG_ON(i->count < bytes); + + if (likely(i->nr_segs == 1)) { + i->iov_offset += bytes; + i->count -= bytes; + } else { + const struct bio_vec *bvec = i->bvec; + size_t base = i->iov_offset; + unsigned long nr_segs = i->nr_segs; + + /* + * The !iov->iov_len check ensures we skip over unlikely + * zero-length segments (without overruning the iovec). + */ + while (bytes || unlikely(i->count && !bvec->bv_len)) { + int copy; + + copy = min(bytes, bvec->bv_len - base); + BUG_ON(!i->count || i->count < copy); + i->count -= copy; + bytes -= copy; + base += copy; + if (bvec->bv_len == base) { + bvec++; + nr_segs--; + base = 0; + } + } + i->bvec = bvec; + i->iov_offset = base; + i->nr_segs = nr_segs; + } +} + +static unsigned long alignment_bvec(const struct iov_iter *i) +{ + const struct bio_vec *bvec = i->bvec; + unsigned long res; + size_t size = i->count; + size_t n; + + if (!size) + return 0; + + res = bvec->bv_offset + i->iov_offset; + n = bvec->bv_len - i->iov_offset; + if (n >= size) + return res | size; + size -= n; + res |= n; + while (size > (++bvec)->bv_len) { + res |= bvec->bv_offset | bvec->bv_len; + size -= bvec->bv_len; + } + res |= bvec->bv_offset | size; + return res; +} + +static ssize_t get_pages_bvec(struct iov_iter *i, + struct page **pages, size_t maxsize, + size_t *start) +{ + const struct bio_vec *bvec = i->bvec; + size_t len = bvec->bv_len - i->iov_offset; + if (len > i->count) + len = i->count; + if (len > maxsize) + len = maxsize; + *start = bvec->bv_offset + i->iov_offset; + + get_page(*pages = bvec->bv_page); + + return len; +} + +static ssize_t get_pages_alloc_bvec(struct iov_iter *i, + struct page ***pages, size_t maxsize, + size_t *start) +{ + const struct bio_vec *bvec = i->bvec; + size_t len = bvec->bv_len - i->iov_offset; + if (len > i->count) + len = i->count; + if (len > maxsize) + len = maxsize; + *start = bvec->bv_offset + i->iov_offset; + + *pages = kmalloc(sizeof(struct page *), GFP_KERNEL); + if (!*pages) + return -ENOMEM; + + get_page(**pages = bvec->bv_page); + + return len; +} + +static int iov_iter_npages_bvec(const struct iov_iter *i, int maxpages) +{ + size_t offset = i->iov_offset; + size_t size = i->count; + const struct bio_vec *bvec = i->bvec; + int npages = 0; + int n; + + for (n = 0; size && n < i->nr_segs; n++, bvec++) { + size_t len = bvec->bv_len - offset; + offset = 0; + if (unlikely(!len)) /* empty segment */ + continue; + if (len > size) + len = size; + npages++; + if (npages >= maxpages) /* don't bother going further */ + return maxpages; + size -= len; + offset = 0; + } + return min(npages, maxpages); +} + +size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + if (i->type & ITER_BVEC) + return copy_page_to_iter_bvec(page, offset, bytes, i); + else + return copy_page_to_iter_iovec(page, offset, bytes, i); +} +EXPORT_SYMBOL(copy_page_to_iter); + +size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + if (i->type & ITER_BVEC) + return copy_page_from_iter_bvec(page, offset, bytes, i); + else + return copy_page_from_iter_iovec(page, offset, bytes, i); +} +EXPORT_SYMBOL(copy_page_from_iter); + +size_t iov_iter_copy_from_user_atomic(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + if (i->type & ITER_BVEC) + return copy_from_user_bvec(page, i, offset, bytes); + else + return copy_from_user_atomic_iovec(page, i, offset, bytes); +} +EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); + +void iov_iter_advance(struct iov_iter *i, size_t size) +{ + if (i->type & ITER_BVEC) + advance_bvec(i, size); + else + advance_iovec(i, size); +} +EXPORT_SYMBOL(iov_iter_advance); + /* * Return the count of just the current iov_iter segment. */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { - const struct iovec *iov = i->iov; if (i->nr_segs == 1) return i->count; + else if (i->type & ITER_BVEC) + return min(i->count, i->iov->iov_len - i->iov_offset); else - return min(i->count, iov->iov_len - i->iov_offset); + return min(i->count, i->bvec->bv_len - i->iov_offset); } EXPORT_SYMBOL(iov_iter_single_seg_count); + +unsigned long iov_iter_alignment(const struct iov_iter *i) +{ + if (i->type & ITER_BVEC) + return alignment_bvec(i); + else + return alignment_iovec(i); +} +EXPORT_SYMBOL(iov_iter_alignment); + +ssize_t iov_iter_get_pages(struct iov_iter *i, + struct page **pages, size_t maxsize, + size_t *start) +{ + if (i->type & ITER_BVEC) + return get_pages_bvec(i, pages, maxsize, start); + else + return get_pages_iovec(i, pages, maxsize, start); +} +EXPORT_SYMBOL(iov_iter_get_pages); + +ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, + struct page ***pages, size_t maxsize, + size_t *start) +{ + if (i->type & ITER_BVEC) + return get_pages_alloc_bvec(i, pages, maxsize, start); + else + return get_pages_alloc_iovec(i, pages, maxsize, start); +} +EXPORT_SYMBOL(iov_iter_get_pages_alloc); + +int iov_iter_npages(const struct iov_iter *i, int maxpages) +{ + if (i->type & ITER_BVEC) + return iov_iter_npages_bvec(i, maxpages); + else + return iov_iter_npages_iovec(i, maxpages); +} +EXPORT_SYMBOL(iov_iter_npages); @@ -945,7 +945,6 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; - BUG_ON(pmd_trans_huge(*pmd)); mmun_start = addr; mmun_end = addr + PAGE_SIZE; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a9559b91603c..a2c7bcb0e6eb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -526,18 +526,14 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { - /* - * The ID of the root cgroup is 0, but memcg treat 0 as an - * invalid ID, so we return (cgroup_id + 1). - */ - return memcg->css.cgroup->id + 1; + return memcg->css.id; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { struct cgroup_subsys_state *css; - css = css_from_id(id - 1, &memory_cgrp_subsys); + css = css_from_id(id, &memory_cgrp_subsys); return mem_cgroup_from_css(css); } @@ -570,7 +566,8 @@ void sock_update_memcg(struct sock *sk) memcg = mem_cgroup_from_task(current); cg_proto = sk->sk_prot->proto_cgroup(memcg); if (!mem_cgroup_is_root(memcg) && - memcg_proto_active(cg_proto) && css_tryget(&memcg->css)) { + memcg_proto_active(cg_proto) && + css_tryget_online(&memcg->css)) { sk->sk_cgrp = cg_proto; } rcu_read_unlock(); @@ -831,7 +828,7 @@ retry: */ __mem_cgroup_remove_exceeded(mz, mctz); if (!res_counter_soft_limit_excess(&mz->memcg->res) || - !css_tryget(&mz->memcg->css)) + !css_tryget_online(&mz->memcg->css)) goto retry; done: return mz; @@ -1073,7 +1070,7 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) if (unlikely(!memcg)) memcg = root_mem_cgroup; } - } while (!css_tryget(&memcg->css)); + } while (!css_tryget_online(&memcg->css)); rcu_read_unlock(); return memcg; } @@ -1110,7 +1107,8 @@ skip_node: */ if (next_css) { if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) + ((next_css->flags & CSS_ONLINE) && + css_tryget_online(next_css))) return mem_cgroup_from_css(next_css); prev_css = next_css; @@ -1156,7 +1154,7 @@ mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter, * would be returned all the time. */ if (position && position != root && - !css_tryget(&position->css)) + !css_tryget_online(&position->css)) position = NULL; } return position; @@ -1533,7 +1531,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* root ? */ - if (mem_cgroup_disabled() || !css_parent(&memcg->css)) + if (mem_cgroup_disabled() || !memcg->css.parent) return vm_swappiness; return memcg->swappiness; @@ -2769,9 +2767,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg, /* * A helper function to get mem_cgroup from ID. must be called under - * rcu_read_lock(). The caller is responsible for calling css_tryget if - * the mem_cgroup is used for charging. (dropping refcnt from swap can be - * called against removed memcg.) + * rcu_read_lock(). The caller is responsible for calling + * css_tryget_online() if the mem_cgroup is used for charging. (dropping + * refcnt from swap can be called against removed memcg.) */ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) { @@ -2794,14 +2792,14 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { memcg = pc->mem_cgroup; - if (memcg && !css_tryget(&memcg->css)) + if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; } else if (PageSwapCache(page)) { ent.val = page_private(page); id = lookup_swap_cgroup_id(ent); rcu_read_lock(); memcg = mem_cgroup_lookup(id); - if (memcg && !css_tryget(&memcg->css)) + if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; rcu_read_unlock(); } @@ -3365,7 +3363,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, } /* The corresponding put will be done in the workqueue. */ - if (!css_tryget(&memcg->css)) + if (!css_tryget_online(&memcg->css)) goto out; rcu_read_unlock(); @@ -4125,8 +4123,8 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent) memcg = mem_cgroup_lookup(id); if (memcg) { /* - * We uncharge this because swap is freed. - * This memcg can be obsolete one. We avoid calling css_tryget + * We uncharge this because swap is freed. This memcg can + * be obsolete one. We avoid calling css_tryget_online(). */ if (!mem_cgroup_is_root(memcg)) res_counter_uncharge(&memcg->memsw, PAGE_SIZE); @@ -4711,18 +4709,28 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) } while (usage > 0); } +/* + * Test whether @memcg has children, dead or alive. Note that this + * function doesn't care whether @memcg has use_hierarchy enabled and + * returns %true if there are child csses according to the cgroup + * hierarchy. Testing use_hierarchy is the caller's responsiblity. + */ static inline bool memcg_has_children(struct mem_cgroup *memcg) { - lockdep_assert_held(&memcg_create_mutex); + bool ret; + /* - * The lock does not prevent addition or deletion to the list - * of children, but it prevents a new child from being - * initialized based on this parent in css_online(), so it's - * enough to decide whether hierarchically inherited - * attributes can still be changed or not. + * The lock does not prevent addition or deletion of children, but + * it prevents a new child from being initialized based on this + * parent in css_online(), so it's enough to decide whether + * hierarchically inherited attributes can still be changed or not. */ - return memcg->use_hierarchy && - !list_empty(&memcg->css.cgroup->children); + lockdep_assert_held(&memcg_create_mutex); + + rcu_read_lock(); + ret = css_next_child(NULL, &memcg->css); + rcu_read_unlock(); + return ret; } /* @@ -4734,11 +4742,6 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg) static int mem_cgroup_force_empty(struct mem_cgroup *memcg) { int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct cgroup *cgrp = memcg->css.cgroup; - - /* returns EBUSY if there is a task or if we come here twice. */ - if (cgroup_has_tasks(cgrp) || !list_empty(&cgrp->children)) - return -EBUSY; /* we call try-to-free pages for make this cgroup empty */ lru_add_drain_all(); @@ -4758,20 +4761,19 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) } } - lru_add_drain(); - mem_cgroup_reparent_charges(memcg); return 0; } -static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css, - unsigned int event) +static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); if (mem_cgroup_is_root(memcg)) return -EINVAL; - return mem_cgroup_force_empty(memcg); + return mem_cgroup_force_empty(memcg) ?: nbytes; } static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, @@ -4785,7 +4787,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, { int retval = 0; struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css)); + struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent); mutex_lock(&memcg_create_mutex); @@ -4802,7 +4804,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, */ if ((!parent_memcg || !parent_memcg->use_hierarchy) && (val == 1 || val == 0)) { - if (list_empty(&memcg->css.cgroup->children)) + if (!memcg_has_children(memcg)) memcg->use_hierarchy = val; else retval = -EBUSY; @@ -4919,7 +4921,8 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, * of course permitted. */ mutex_lock(&memcg_create_mutex); - if (cgroup_has_tasks(memcg->css.cgroup) || memcg_has_children(memcg)) + if (cgroup_has_tasks(memcg->css.cgroup) || + (memcg->use_hierarchy && memcg_has_children(memcg))) err = -EBUSY; mutex_unlock(&memcg_create_mutex); if (err) @@ -5021,17 +5024,18 @@ static int memcg_update_kmem_limit(struct mem_cgroup *memcg, * The user of this function is... * RES_LIMIT. */ -static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, - char *buffer) +static ssize_t mem_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); enum res_type type; int name; unsigned long long val; int ret; - type = MEMFILE_TYPE(cft->private); - name = MEMFILE_ATTR(cft->private); + buf = strstrip(buf); + type = MEMFILE_TYPE(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_LIMIT: @@ -5040,7 +5044,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, break; } /* This function does all necessary parse...reuse it */ - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; if (type == _MEM) @@ -5053,7 +5057,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, return -EINVAL; break; case RES_SOFT_LIMIT: - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; /* @@ -5070,7 +5074,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, ret = -EINVAL; /* should be BUG() ? */ break; } - return ret; + return ret ?: nbytes; } static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, @@ -5083,8 +5087,8 @@ static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, if (!memcg->use_hierarchy) goto out; - while (css_parent(&memcg->css)) { - memcg = mem_cgroup_from_css(css_parent(&memcg->css)); + while (memcg->css.parent) { + memcg = mem_cgroup_from_css(memcg->css.parent); if (!memcg->use_hierarchy) break; tmp = res_counter_read_u64(&memcg->res, RES_LIMIT); @@ -5097,14 +5101,15 @@ out: *memsw_limit = min_memsw_limit; } -static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) +static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); int name; enum res_type type; - type = MEMFILE_TYPE(event); - name = MEMFILE_ATTR(event); + type = MEMFILE_TYPE(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_MAX_USAGE: @@ -5129,7 +5134,7 @@ static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) break; } - return 0; + return nbytes; } static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, @@ -5322,7 +5327,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, if (val > 100) return -EINVAL; - if (css_parent(css)) + if (css->parent) memcg->swappiness = val; else vm_swappiness = val; @@ -5659,7 +5664,7 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, struct mem_cgroup *memcg = mem_cgroup_from_css(css); /* cannot set to root cgroup and only 0 and 1 are allowed */ - if (!css_parent(css) || !((val == 0) || (val == 1))) + if (!css->parent || !((val == 0) || (val == 1))) return -EINVAL; memcg->oom_kill_disable = val; @@ -5705,10 +5710,10 @@ static void kmem_cgroup_css_offline(struct mem_cgroup *memcg) * which is then paired with css_put during uncharge resp. here. * * Although this might sound strange as this path is called from - * css_offline() when the referencemight have dropped down to 0 - * and shouldn't be incremented anymore (css_tryget would fail) - * we do not have other options because of the kmem allocations - * lifetime. + * css_offline() when the referencemight have dropped down to 0 and + * shouldn't be incremented anymore (css_tryget_online() would + * fail) we do not have other options because of the kmem + * allocations lifetime. */ css_get(&memcg->css); @@ -5827,9 +5832,10 @@ static void memcg_event_ptable_queue_proc(struct file *file, * Input must be in format '<event_fd> <control_fd> <args>'. * Interpretation of args is defined by control file implementation. */ -static int memcg_write_event_control(struct cgroup_subsys_state *css, - struct cftype *cft, char *buffer) +static ssize_t memcg_write_event_control(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { + struct cgroup_subsys_state *css = of_css(of); struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_event *event; struct cgroup_subsys_state *cfile_css; @@ -5840,15 +5846,17 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, char *endp; int ret; - efd = simple_strtoul(buffer, &endp, 10); + buf = strstrip(buf); + + efd = simple_strtoul(buf, &endp, 10); if (*endp != ' ') return -EINVAL; - buffer = endp + 1; + buf = endp + 1; - cfd = simple_strtoul(buffer, &endp, 10); + cfd = simple_strtoul(buf, &endp, 10); if ((*endp != ' ') && (*endp != '\0')) return -EINVAL; - buffer = endp + 1; + buf = endp + 1; event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) @@ -5916,8 +5924,8 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_from_dir(cfile.file->f_dentry->d_parent, - &memory_cgrp_subsys); + cfile_css = css_tryget_online_from_dir(cfile.file->f_dentry->d_parent, + &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) goto out_put_cfile; @@ -5926,7 +5934,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, goto out_put_cfile; } - ret = event->register_event(memcg, event->eventfd, buffer); + ret = event->register_event(memcg, event->eventfd, buf); if (ret) goto out_put_css; @@ -5939,7 +5947,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, fdput(cfile); fdput(efile); - return 0; + return nbytes; out_put_css: css_put(css); @@ -5964,25 +5972,25 @@ static struct cftype mem_cgroup_files[] = { { .name = "max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "soft_limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { @@ -5991,7 +5999,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "force_empty", - .trigger = mem_cgroup_force_empty_write, + .write = mem_cgroup_force_empty_write, }, { .name = "use_hierarchy", @@ -6001,7 +6009,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "cgroup.event_control", /* XXX: for compat */ - .write_string = memcg_write_event_control, + .write = memcg_write_event_control, .flags = CFTYPE_NO_PREFIX, .mode = S_IWUGO, }, @@ -6034,7 +6042,7 @@ static struct cftype mem_cgroup_files[] = { { .name = "kmem.limit_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { @@ -6045,13 +6053,13 @@ static struct cftype mem_cgroup_files[] = { { .name = "kmem.failcnt", .private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, #ifdef CONFIG_SLABINFO @@ -6074,19 +6082,19 @@ static struct cftype memsw_cgroup_files[] = { { .name = "memsw.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.limit_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.failcnt", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { }, /* terminate */ @@ -6264,9 +6272,9 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); + struct mem_cgroup *parent = mem_cgroup_from_css(css->parent); - if (css->cgroup->id > MEM_CGROUP_ID_MAX) + if (css->id > MEM_CGROUP_ID_MAX) return -ENOSPC; if (!parent) @@ -6361,7 +6369,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) /* * XXX: css_offline() would be where we should reparent all * memory to prepare the cgroup for destruction. However, - * memcg does not do css_tryget() and res_counter charging + * memcg does not do css_tryget_online() and res_counter charging * under the same RCU lock region, which means that charging * could race with offlining. Offlining only happens to * cgroups with no tasks in them but charges can show up @@ -6375,9 +6383,9 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) * lookup_swap_cgroup_id() * rcu_read_lock() * mem_cgroup_lookup() - * css_tryget() + * css_tryget_online() * rcu_read_unlock() - * disable css_tryget() + * disable css_tryget_online() * call_rcu() * offline_css() * reparent_charges() diff --git a/mm/memory-failure.c b/mm/memory-failure.c index cd8989c1027e..c6399e328931 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -895,7 +895,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, struct page *hpage = *hpagep; struct page *ppage; - if (PageReserved(p) || PageSlab(p)) + if (PageReserved(p) || PageSlab(p) || !PageLRU(p)) return SWAP_SUCCESS; /* @@ -1159,9 +1159,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags) action_result(pfn, "free buddy, 2nd try", DELAYED); return 0; } - action_result(pfn, "non LRU", IGNORED); - put_page(p); - return -EBUSY; } } @@ -1194,6 +1191,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags) return 0; } + if (!PageHuge(p) && !PageTransTail(p) && !PageLRU(p)) + goto identify_page_state; + /* * For error on the tail page, we should set PG_hwpoison * on the head page to show that the hugepage is hwpoisoned @@ -1243,6 +1243,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) goto out; } +identify_page_state: res = -EBUSY; /* * The first check uses the current page flags which may not have any diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 284974230459..8f5330d74f47 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -656,19 +656,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, * @nodes and @flags,) it's isolated and queued to the pagelist which is * passed via @private.) */ -static struct vm_area_struct * +static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) { - int err; - struct vm_area_struct *first, *vma, *prev; - + int err = 0; + struct vm_area_struct *vma, *prev; - first = find_vma(mm, start); - if (!first) - return ERR_PTR(-EFAULT); + vma = find_vma(mm, start); + if (!vma) + return -EFAULT; prev = NULL; - for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) { + for (; vma && vma->vm_start < end; vma = vma->vm_next) { unsigned long endvma = vma->vm_end; if (endvma > end) @@ -678,9 +677,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, if (!(flags & MPOL_MF_DISCONTIG_OK)) { if (!vma->vm_next && vma->vm_end < end) - return ERR_PTR(-EFAULT); + return -EFAULT; if (prev && prev->vm_end < vma->vm_start) - return ERR_PTR(-EFAULT); + return -EFAULT; } if (flags & MPOL_MF_LAZY) { @@ -694,15 +693,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, err = queue_pages_pgd_range(vma, start, endvma, nodes, flags, private); - if (err) { - first = ERR_PTR(err); + if (err) break; - } } next: prev = vma; } - return first; + return err; } /* @@ -1156,16 +1153,17 @@ out: /* * Allocate a new page for page migration based on vma policy. - * Start assuming that page is mapped by vma pointed to by @private. + * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { - struct vm_area_struct *vma = (struct vm_area_struct *)private; + struct vm_area_struct *vma; unsigned long uninitialized_var(address); + vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) @@ -1195,7 +1193,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, return -ENOSYS; } -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { return NULL; } @@ -1205,7 +1203,6 @@ static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { - struct vm_area_struct *vma; struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; @@ -1271,11 +1268,9 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - vma = queue_pages_range(mm, start, end, nmask, + err = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); - - err = PTR_ERR(vma); /* maybe ... */ - if (!IS_ERR(vma)) + if (!err) err = mbind_range(mm, start, end, new); if (!err) { @@ -1283,9 +1278,8 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_vma_page, - NULL, (unsigned long)vma, - MIGRATE_SYNC, MR_MEMPOLICY_MBIND); + nr_failed = migrate_pages(&pagelist, new_page, NULL, + start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); } @@ -2145,7 +2139,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) } else *new = *old; - rcu_read_lock(); if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); if (new->flags & MPOL_F_REBINDING) @@ -2153,7 +2146,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) else mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE); } - rcu_read_unlock(); atomic_set(&new->refcnt, 1); return new; } diff --git a/mm/migrate.c b/mm/migrate.c index 63f0cd559999..9e0beaa91845 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -120,8 +120,6 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; - if (pmd_trans_huge(*pmd)) - goto out; ptep = pte_offset_map(pmd, addr); diff --git a/mm/msync.c b/mm/msync.c index a5c673669ca6..992a1673d488 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -78,7 +78,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) goto out_unlock; } file = vma->vm_file; - fstart = start + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + fstart = (start - vma->vm_start) + + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); fend = fstart + (min(end, vma->vm_end) - start) - 1; start = vma->vm_end; if ((flags & MS_SYNC) && file && diff --git a/mm/nommu.c b/mm/nommu.c index b78e3a8f5ee7..4a852f6c5709 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -786,7 +786,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) for (i = 0; i < VMACACHE_SIZE; i++) { /* if the vma is cached, invalidate the entire cache */ if (curr->vmacache[i] == vma) { - vmacache_invalidate(curr->mm); + vmacache_invalidate(mm); break; } } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4f59fa29eda8..0ea758b898fd 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -69,6 +69,7 @@ /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); +#define MIN_PERCPU_PAGELIST_FRACTION (8) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); @@ -815,9 +816,21 @@ void __init init_cma_reserved_pageblock(struct page *page) set_page_count(p, 0); } while (++p, --i); - set_page_refcounted(page); set_pageblock_migratetype(page, MIGRATE_CMA); - __free_pages(page, pageblock_order); + + if (pageblock_order >= MAX_ORDER) { + i = pageblock_nr_pages; + p = page; + do { + set_page_refcounted(p); + __free_pages(p, MAX_ORDER - 1); + p += MAX_ORDER_NR_PAGES; + } while (i -= MAX_ORDER_NR_PAGES); + } else { + set_page_refcounted(page); + __free_pages(page, pageblock_order); + } + adjust_managed_page_count(page, pageblock_nr_pages); } #endif @@ -4145,7 +4158,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) #endif -static int __meminit zone_batchsize(struct zone *zone) +static int zone_batchsize(struct zone *zone) { #ifdef CONFIG_MMU int batch; @@ -4261,8 +4274,8 @@ static void pageset_set_high(struct per_cpu_pageset *p, pageset_update(&p->pcp, high, batch); } -static void __meminit pageset_set_high_and_batch(struct zone *zone, - struct per_cpu_pageset *pcp) +static void pageset_set_high_and_batch(struct zone *zone, + struct per_cpu_pageset *pcp) { if (percpu_pagelist_fraction) pageset_set_high(pcp, @@ -5881,23 +5894,38 @@ int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - unsigned int cpu; + int old_percpu_pagelist_fraction; int ret; + mutex_lock(&pcp_batch_high_lock); + old_percpu_pagelist_fraction = percpu_pagelist_fraction; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || (ret < 0)) - return ret; + if (!write || ret < 0) + goto out; + + /* Sanity checking to avoid pcp imbalance */ + if (percpu_pagelist_fraction && + percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { + percpu_pagelist_fraction = old_percpu_pagelist_fraction; + ret = -EINVAL; + goto out; + } + + /* No change? */ + if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + goto out; - mutex_lock(&pcp_batch_high_lock); for_each_populated_zone(zone) { - unsigned long high; - high = zone->managed_pages / percpu_pagelist_fraction; + unsigned int cpu; + for_each_possible_cpu(cpu) - pageset_set_high(per_cpu_ptr(zone->pageset, cpu), - high); + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); } +out: mutex_unlock(&pcp_batch_high_lock); - return 0; + return ret; } int hashdist = HASHDIST_DEFAULT; diff --git a/mm/page_io.c b/mm/page_io.c index 58b50d2901fe..955db8b0d497 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -264,10 +264,18 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, struct kiocb kiocb; struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; - struct iovec iov = { - .iov_base = kmap(page), - .iov_len = PAGE_SIZE, + struct bio_vec bv = { + .bv_page = page, + .bv_len = PAGE_SIZE, + .bv_offset = 0 }; + struct iov_iter from = { + .type = ITER_BVEC | WRITE, + .count = PAGE_SIZE, + .iov_offset = 0, + .nr_segs = 1, + }; + from.bvec = &bv; /* older gcc versions are broken */ init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); @@ -275,10 +283,9 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, set_page_writeback(page); unlock_page(page); - ret = mapping->a_ops->direct_IO(KERNEL_WRITE, - &kiocb, &iov, - kiocb.ki_pos, 1); - kunmap(page); + ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE, + &kiocb, &from, + kiocb.ki_pos); if (ret == PAGE_SIZE) { count_vm_event(PSWPOUT); ret = 0; diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 8505c9262b35..5077afcd9e11 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -46,11 +46,7 @@ static int process_vm_rw_pages(struct page **pages, copy = len; if (vm_write) { - if (copy > iov_iter_count(iter)) - copy = iov_iter_count(iter); - copied = iov_iter_copy_from_user(page, iter, - offset, copy); - iov_iter_advance(iter, copied); + copied = copy_page_from_iter(page, offset, copy, iter); set_page_dirty_lock(page); } else { copied = copy_page_to_iter(page, offset, copy, iter); @@ -278,7 +274,7 @@ static ssize_t process_vm_rw(pid_t pid, if (rc <= 0) goto free_iovecs; - iov_iter_init(&iter, iov_l, liovcnt, rc, 0); + iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc); rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); @@ -341,7 +337,7 @@ compat_process_vm_rw(compat_pid_t pid, &iov_l); if (rc <= 0) goto free_iovecs; - iov_iter_init(&iter, iov_l, liovcnt, rc, 0); + iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc); rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); diff --git a/mm/rmap.c b/mm/rmap.c index bf05fc872ae8..b7e94ebbd09e 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -569,6 +569,7 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) pgd_t *pgd; pud_t *pud; pmd_t *pmd = NULL; + pmd_t pmde; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) @@ -579,7 +580,13 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) goto out; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) + /* + * Some THP functions use the sequence pmdp_clear_flush(), set_pmd_at() + * without holding anon_vma lock for write. So when looking for a + * genuine pmde (in which to find pte), test present and !THP together. + */ + pmde = ACCESS_ONCE(*pmd); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: return pmd; @@ -615,9 +622,6 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm, if (!pmd) return NULL; - if (pmd_trans_huge(*pmd)) - return NULL; - pte = pte_offset_map(pmd, address); /* Make a quick check before getting the lock */ if (!sync && !pte_present(*pte)) { diff --git a/mm/shmem.c b/mm/shmem.c index 5402481c28d1..1140f49b6ded 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -80,11 +80,12 @@ static struct vfsmount *shm_mnt; #define SHORT_SYMLINK_LEN 128 /* - * shmem_fallocate and shmem_writepage communicate via inode->i_private - * (with i_mutex making sure that it has only one user at a time): - * we would prefer not to enlarge the shmem inode just for that. + * shmem_fallocate communicates with shmem_fault or shmem_writepage via + * inode->i_private (with i_mutex making sure that it has only one user at + * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { + int mode; /* FALLOC_FL mode currently operating */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ @@ -759,6 +760,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && + !shmem_falloc->mode && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; @@ -1027,6 +1029,9 @@ repeat: goto failed; } + if (page && sgp == SGP_WRITE) + mark_page_accessed(page); + /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) @@ -1108,6 +1113,9 @@ repeat: shmem_recalc_inode(inode); spin_unlock(&info->lock); + if (sgp == SGP_WRITE) + mark_page_accessed(page); + delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); @@ -1134,6 +1142,9 @@ repeat: __SetPageSwapBacked(page); __set_page_locked(page); + if (sgp == SGP_WRITE) + init_page_accessed(page); + error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); if (error) @@ -1233,6 +1244,44 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) int error; int ret = VM_FAULT_LOCKED; + /* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_mutex. So refrain from + * faulting pages into the hole while it's being punched, and + * wait on i_mutex to be released if vmf->flags permits. + */ + if (unlikely(inode->i_private)) { + struct shmem_falloc *shmem_falloc; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (!shmem_falloc || + shmem_falloc->mode != FALLOC_FL_PUNCH_HOLE || + vmf->pgoff < shmem_falloc->start || + vmf->pgoff >= shmem_falloc->next) + shmem_falloc = NULL; + spin_unlock(&inode->i_lock); + /* + * i_lock has protected us from taking shmem_falloc seriously + * once return from shmem_fallocate() went back up that stack. + * i_lock does not serialize with i_mutex at all, but it does + * not matter if sometimes we wait unnecessarily, or sometimes + * miss out on waiting: we just need to make those cases rare. + */ + if (shmem_falloc) { + if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && + !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { + up_read(&vma->vm_mm->mmap_sem); + mutex_lock(&inode->i_mutex); + mutex_unlock(&inode->i_mutex); + return VM_FAULT_RETRY; + } + /* cond_resched? Leave that to GUP or return to user */ + return VM_FAULT_NOPAGE; + } + } + error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); @@ -1372,13 +1421,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - int ret; struct inode *inode = mapping->host; pgoff_t index = pos >> PAGE_CACHE_SHIFT; - ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); - if (ret == 0 && *pagep) - init_page_accessed(*pagep); - return ret; + return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); } static int @@ -1406,8 +1451,7 @@ shmem_write_end(struct file *file, struct address_space *mapping, return copied; } -static ssize_t shmem_file_aio_read(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, loff_t pos) +static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); @@ -1416,15 +1460,8 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb, unsigned long offset; enum sgp_type sgp = SGP_READ; int error = 0; - ssize_t retval; - size_t count; + ssize_t retval = 0; loff_t *ppos = &iocb->ki_pos; - struct iov_iter iter; - - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; - iov_iter_init(&iter, iov, nr_segs, count, 0); /* * Might this read be for a stacking filesystem? Then when reading @@ -1500,14 +1537,14 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb, * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ - ret = copy_page_to_iter(page, offset, nr, &iter); + ret = copy_page_to_iter(page, offset, nr, to); retval += ret; offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; page_cache_release(page); - if (!iov_iter_count(&iter)) + if (!iov_iter_count(to)) break; if (ret < nr) { error = -EFAULT; @@ -1732,20 +1769,31 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, pgoff_t start, index, end; int error; + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + mutex_lock(&inode->i_mutex); + shmem_falloc.mode = mode & ~FALLOC_FL_KEEP_SIZE; + if (mode & FALLOC_FL_PUNCH_HOLE) { struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; + shmem_falloc.start = unmap_start >> PAGE_SHIFT; + shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); + if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); shmem_truncate_range(inode, offset, offset + len - 1); /* No need to unmap again: hole-punching leaves COWed pages */ error = 0; - goto out; + goto undone; } /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ @@ -2629,13 +2677,13 @@ static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = shmem_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = shmem_file_read_iter, + .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = shmem_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif }; diff --git a/mm/slab.c b/mm/slab.c index 9ca3b87edabc..3070b929a1bf 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -386,6 +386,39 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #endif +#define OBJECT_FREE (0) +#define OBJECT_ACTIVE (1) + +#ifdef CONFIG_DEBUG_SLAB_LEAK + +static void set_obj_status(struct page *page, int idx, int val) +{ + int freelist_size; + char *status; + struct kmem_cache *cachep = page->slab_cache; + + freelist_size = cachep->num * sizeof(freelist_idx_t); + status = (char *)page->freelist + freelist_size; + status[idx] = val; +} + +static inline unsigned int get_obj_status(struct page *page, int idx) +{ + int freelist_size; + char *status; + struct kmem_cache *cachep = page->slab_cache; + + freelist_size = cachep->num * sizeof(freelist_idx_t); + status = (char *)page->freelist + freelist_size; + + return status[idx]; +} + +#else +static inline void set_obj_status(struct page *page, int idx, int val) {} + +#endif + /* * Do not go above this order unless 0 objects fit into the slab or * overridden on the command line. @@ -576,12 +609,30 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) return cachep->array[smp_processor_id()]; } +static size_t calculate_freelist_size(int nr_objs, size_t align) +{ + size_t freelist_size; + + freelist_size = nr_objs * sizeof(freelist_idx_t); + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + freelist_size += nr_objs * sizeof(char); + + if (align) + freelist_size = ALIGN(freelist_size, align); + + return freelist_size; +} + static int calculate_nr_objs(size_t slab_size, size_t buffer_size, size_t idx_size, size_t align) { int nr_objs; + size_t remained_size; size_t freelist_size; + int extra_space = 0; + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + extra_space = sizeof(char); /* * Ignore padding for the initial guess. The padding * is at most @align-1 bytes, and @buffer_size is at @@ -590,14 +641,15 @@ static int calculate_nr_objs(size_t slab_size, size_t buffer_size, * into the memory allocation when taking the padding * into account. */ - nr_objs = slab_size / (buffer_size + idx_size); + nr_objs = slab_size / (buffer_size + idx_size + extra_space); /* * This calculated number will be either the right * amount, or one greater than what we want. */ - freelist_size = slab_size - nr_objs * buffer_size; - if (freelist_size < ALIGN(nr_objs * idx_size, align)) + remained_size = slab_size - nr_objs * buffer_size; + freelist_size = calculate_freelist_size(nr_objs, align); + if (remained_size < freelist_size) nr_objs--; return nr_objs; @@ -635,7 +687,7 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size, } else { nr_objs = calculate_nr_objs(slab_size, buffer_size, sizeof(freelist_idx_t), align); - mgmt_size = ALIGN(nr_objs * sizeof(freelist_idx_t), align); + mgmt_size = calculate_freelist_size(nr_objs, align); } *num = nr_objs; *left_over = slab_size - nr_objs*buffer_size - mgmt_size; @@ -2041,13 +2093,16 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, break; if (flags & CFLGS_OFF_SLAB) { + size_t freelist_size_per_obj = sizeof(freelist_idx_t); /* * Max number of objs-per-slab for caches which * use off-slab slabs. Needed to avoid a possible * looping condition in cache_grow(). */ + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + freelist_size_per_obj += sizeof(char); offslab_limit = size; - offslab_limit /= sizeof(freelist_idx_t); + offslab_limit /= freelist_size_per_obj; if (num > offslab_limit) break; @@ -2294,8 +2349,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) if (!cachep->num) return -E2BIG; - freelist_size = - ALIGN(cachep->num * sizeof(freelist_idx_t), cachep->align); + freelist_size = calculate_freelist_size(cachep->num, cachep->align); /* * If the slab has been placed off-slab, and we have enough space then @@ -2308,7 +2362,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) if (flags & CFLGS_OFF_SLAB) { /* really off slab. No need for manual alignment */ - freelist_size = cachep->num * sizeof(freelist_idx_t); + freelist_size = calculate_freelist_size(cachep->num, 0); #ifdef CONFIG_PAGE_POISONING /* If we're going to use the generic kernel_map_pages() @@ -2612,6 +2666,7 @@ static void cache_init_objs(struct kmem_cache *cachep, if (cachep->ctor) cachep->ctor(objp); #endif + set_obj_status(page, i, OBJECT_FREE); set_free_obj(page, i, i); } } @@ -2820,6 +2875,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, BUG_ON(objnr >= cachep->num); BUG_ON(objp != index_to_obj(cachep, page, objnr)); + set_obj_status(page, objnr, OBJECT_FREE); if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { @@ -2953,6 +3009,8 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, gfp_t flags, void *objp, unsigned long caller) { + struct page *page; + if (!objp) return objp; if (cachep->flags & SLAB_POISON) { @@ -2983,6 +3041,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, *dbg_redzone1(cachep, objp) = RED_ACTIVE; *dbg_redzone2(cachep, objp) = RED_ACTIVE; } + + page = virt_to_head_page(objp); + set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE); objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) cachep->ctor(objp); @@ -4219,21 +4280,12 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c, struct page *page) { void *p; - int i, j; + int i; if (n[0] == n[1]) return; for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) { - bool active = true; - - for (j = page->active; j < c->num; j++) { - /* Skip freed item */ - if (get_free_obj(page, j) == i) { - active = false; - break; - } - } - if (!active) + if (get_obj_status(page, i) != OBJECT_ACTIVE) continue; if (!add_caller(n, (unsigned long)*dbg_userword(c, p))) diff --git a/mm/slub.c b/mm/slub.c index b2b047327d76..73004808537e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1881,7 +1881,7 @@ redo: new.frozen = 0; - if (!new.inuse && n->nr_partial > s->min_partial) + if (!new.inuse && n->nr_partial >= s->min_partial) m = M_FREE; else if (new.freelist) { m = M_PARTIAL; @@ -1992,7 +1992,7 @@ static void unfreeze_partials(struct kmem_cache *s, new.freelist, new.counters, "unfreezing slab")); - if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) { + if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) { page->next = discard_page; discard_page = page; } else { @@ -2620,7 +2620,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, return; } - if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) + if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) goto slab_empty; /* diff --git a/mm/vmscan.c b/mm/vmscan.c index e01ded365440..0f16ffe8eb67 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -464,7 +464,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * stalls if we need to run get_block(). We could test * PagePrivate for that. * - * If this process is currently in __generic_file_aio_write() against + * If this process is currently in __generic_file_write_iter() against * this page's queue, we can perform writeback even if that * will block. * |