diff options
Diffstat (limited to 'fs')
| -rw-r--r-- | fs/Kconfig | 3 | ||||
| -rw-r--r-- | fs/block_dev.c | 15 | ||||
| -rw-r--r-- | fs/cifs/file.c | 8 | ||||
| -rw-r--r-- | fs/dax.c | 301 | ||||
| -rw-r--r-- | fs/fs-writeback.c | 2 | ||||
| -rw-r--r-- | fs/hugetlbfs/inode.c | 143 | ||||
| -rw-r--r-- | fs/proc/page.c | 4 | ||||
| -rw-r--r-- | fs/proc/task_mmu.c | 55 | ||||
| -rw-r--r-- | fs/stat.c | 2 |
9 files changed, 324 insertions, 209 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 2bb1ef86c411..9adee0d7536e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -50,7 +50,8 @@ config FS_DAX_PMD bool default FS_DAX depends on FS_DAX - depends on BROKEN + depends on ZONE_DEVICE + depends on TRANSPARENT_HUGEPAGE endif # BLOCK diff --git a/fs/block_dev.c b/fs/block_dev.c index 81c0705558be..530145b607c4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -455,10 +455,7 @@ EXPORT_SYMBOL_GPL(bdev_write_page); /** * bdev_direct_access() - Get the address for directly-accessibly memory * @bdev: The device containing the memory - * @sector: The offset within the device - * @addr: Where to put the address of the memory - * @pfn: The Page Frame Number for the memory - * @size: The number of bytes requested + * @dax: control and output parameters for ->direct_access * * If a block device is made up of directly addressable memory, this function * will tell the caller the PFN and the address of the memory. The address @@ -469,10 +466,10 @@ EXPORT_SYMBOL_GPL(bdev_write_page); * Return: negative errno if an error occurs, otherwise the number of bytes * accessible at this address. */ -long bdev_direct_access(struct block_device *bdev, sector_t sector, - void __pmem **addr, unsigned long *pfn, long size) +long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) { - long avail; + sector_t sector = dax->sector; + long avail, size = dax->size; const struct block_device_operations *ops = bdev->bd_disk->fops; /* @@ -491,9 +488,11 @@ long bdev_direct_access(struct block_device *bdev, sector_t sector, sector += get_start_sect(bdev); if (sector % (PAGE_SIZE / 512)) return -EINVAL; - avail = ops->direct_access(bdev, sector, addr, pfn); + avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn); if (!avail) return -ERANGE; + if (avail > 0 && avail & ~PAGE_MASK) + return -ENXIO; return min(avail, size); } EXPORT_SYMBOL_GPL(bdev_direct_access); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0068e82217c3..0a2752b79e72 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3391,13 +3391,13 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, * should have access to this page, we're safe to simply set * PG_locked without checking it first. */ - __set_page_locked(page); + __SetPageLocked(page); rc = add_to_page_cache_locked(page, mapping, page->index, gfp); /* give up if we can't stick it in the cache */ if (rc) { - __clear_page_locked(page); + __ClearPageLocked(page); return rc; } @@ -3418,9 +3418,9 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, if (*bytes + PAGE_CACHE_SIZE > rsize) break; - __set_page_locked(page); + __SetPageLocked(page); if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { - __clear_page_locked(page); + __ClearPageLocked(page); break; } list_move_tail(&page->lru, tmplist); @@ -28,54 +28,68 @@ #include <linux/sched.h> #include <linux/uio.h> #include <linux/vmstat.h> +#include <linux/pfn_t.h> +#include <linux/sizes.h> + +static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax) +{ + struct request_queue *q = bdev->bd_queue; + long rc = -EIO; + + dax->addr = (void __pmem *) ERR_PTR(-EIO); + if (blk_queue_enter(q, true) != 0) + return rc; + + rc = bdev_direct_access(bdev, dax); + if (rc < 0) { + dax->addr = (void __pmem *) ERR_PTR(rc); + blk_queue_exit(q); + return rc; + } + return rc; +} + +static void dax_unmap_atomic(struct block_device *bdev, + const struct blk_dax_ctl *dax) +{ + if (IS_ERR(dax->addr)) + return; + blk_queue_exit(bdev->bd_queue); +} /* * dax_clear_blocks() is called from within transaction context from XFS, * and hence this means the stack from this point must follow GFP_NOFS * semantics for all operations. */ -int dax_clear_blocks(struct inode *inode, sector_t block, long size) +int dax_clear_blocks(struct inode *inode, sector_t block, long _size) { struct block_device *bdev = inode->i_sb->s_bdev; - sector_t sector = block << (inode->i_blkbits - 9); + struct blk_dax_ctl dax = { + .sector = block << (inode->i_blkbits - 9), + .size = _size, + }; might_sleep(); do { - void __pmem *addr; - unsigned long pfn; - long count; + long count, sz; - count = bdev_direct_access(bdev, sector, &addr, &pfn, size); + count = dax_map_atomic(bdev, &dax); if (count < 0) return count; - BUG_ON(size < count); - while (count > 0) { - unsigned pgsz = PAGE_SIZE - offset_in_page(addr); - if (pgsz > count) - pgsz = count; - clear_pmem(addr, pgsz); - addr += pgsz; - size -= pgsz; - count -= pgsz; - BUG_ON(pgsz & 511); - sector += pgsz / 512; - cond_resched(); - } - } while (size); + sz = min_t(long, count, SZ_128K); + clear_pmem(dax.addr, sz); + dax.size -= sz; + dax.sector += sz / 512; + dax_unmap_atomic(bdev, &dax); + cond_resched(); + } while (dax.size); wmb_pmem(); return 0; } EXPORT_SYMBOL_GPL(dax_clear_blocks); -static long dax_get_addr(struct buffer_head *bh, void __pmem **addr, - unsigned blkbits) -{ - unsigned long pfn; - sector_t sector = bh->b_blocknr << (blkbits - 9); - return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size); -} - /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */ static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first, loff_t pos, loff_t end) @@ -105,19 +119,29 @@ static bool buffer_size_valid(struct buffer_head *bh) return bh->b_state != 0; } + +static sector_t to_sector(const struct buffer_head *bh, + const struct inode *inode) +{ + sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); + + return sector; +} + static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, loff_t start, loff_t end, get_block_t get_block, struct buffer_head *bh) { - ssize_t retval = 0; - loff_t pos = start; - loff_t max = start; - loff_t bh_max = start; - void __pmem *addr; - bool hole = false; - bool need_wmb = false; - - if (iov_iter_rw(iter) != WRITE) + loff_t pos = start, max = start, bh_max = start; + bool hole = false, need_wmb = false; + struct block_device *bdev = NULL; + int rw = iov_iter_rw(iter), rc; + long map_len = 0; + struct blk_dax_ctl dax = { + .addr = (void __pmem *) ERR_PTR(-EIO), + }; + + if (rw == READ) end = min(end, i_size_read(inode)); while (pos < end) { @@ -132,13 +156,13 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, if (pos == bh_max) { bh->b_size = PAGE_ALIGN(end - pos); bh->b_state = 0; - retval = get_block(inode, block, bh, - iov_iter_rw(iter) == WRITE); - if (retval) + rc = get_block(inode, block, bh, rw == WRITE); + if (rc) break; if (!buffer_size_valid(bh)) bh->b_size = 1 << blkbits; bh_max = pos - first + bh->b_size; + bdev = bh->b_bdev; } else { unsigned done = bh->b_size - (bh_max - (pos - first)); @@ -146,47 +170,53 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, bh->b_size -= done; } - hole = iov_iter_rw(iter) != WRITE && !buffer_written(bh); + hole = rw == READ && !buffer_written(bh); if (hole) { - addr = NULL; size = bh->b_size - first; } else { - retval = dax_get_addr(bh, &addr, blkbits); - if (retval < 0) + dax_unmap_atomic(bdev, &dax); + dax.sector = to_sector(bh, inode); + dax.size = bh->b_size; + map_len = dax_map_atomic(bdev, &dax); + if (map_len < 0) { + rc = map_len; break; + } if (buffer_unwritten(bh) || buffer_new(bh)) { - dax_new_buf(addr, retval, first, pos, - end); + dax_new_buf(dax.addr, map_len, first, + pos, end); need_wmb = true; } - addr += first; - size = retval - first; + dax.addr += first; + size = map_len - first; } max = min(pos + size, end); } if (iov_iter_rw(iter) == WRITE) { - len = copy_from_iter_pmem(addr, max - pos, iter); + len = copy_from_iter_pmem(dax.addr, max - pos, iter); need_wmb = true; } else if (!hole) - len = copy_to_iter((void __force *)addr, max - pos, + len = copy_to_iter((void __force *) dax.addr, max - pos, iter); else len = iov_iter_zero(max - pos, iter); if (!len) { - retval = -EFAULT; + rc = -EFAULT; break; } pos += len; - addr += len; + if (!IS_ERR(dax.addr)) + dax.addr += len; } if (need_wmb) wmb_pmem(); + dax_unmap_atomic(bdev, &dax); - return (pos == start) ? retval : pos - start; + return (pos == start) ? rc : pos - start; } /** @@ -275,28 +305,35 @@ static int dax_load_hole(struct address_space *mapping, struct page *page, return VM_FAULT_LOCKED; } -static int copy_user_bh(struct page *to, struct buffer_head *bh, - unsigned blkbits, unsigned long vaddr) +static int copy_user_bh(struct page *to, struct inode *inode, + struct buffer_head *bh, unsigned long vaddr) { - void __pmem *vfrom; + struct blk_dax_ctl dax = { + .sector = to_sector(bh, inode), + .size = bh->b_size, + }; + struct block_device *bdev = bh->b_bdev; void *vto; - if (dax_get_addr(bh, &vfrom, blkbits) < 0) - return -EIO; + if (dax_map_atomic(bdev, &dax) < 0) + return PTR_ERR(dax.addr); vto = kmap_atomic(to); - copy_user_page(vto, (void __force *)vfrom, vaddr, to); + copy_user_page(vto, (void __force *)dax.addr, vaddr, to); kunmap_atomic(vto); + dax_unmap_atomic(bdev, &dax); return 0; } static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, struct vm_area_struct *vma, struct vm_fault *vmf) { - struct address_space *mapping = inode->i_mapping; - sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); unsigned long vaddr = (unsigned long)vmf->virtual_address; - void __pmem *addr; - unsigned long pfn; + struct address_space *mapping = inode->i_mapping; + struct block_device *bdev = bh->b_bdev; + struct blk_dax_ctl dax = { + .sector = to_sector(bh, inode), + .size = bh->b_size, + }; pgoff_t size; int error; @@ -315,20 +352,18 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, goto out; } - error = bdev_direct_access(bh->b_bdev, sector, &addr, &pfn, bh->b_size); - if (error < 0) - goto out; - if (error < PAGE_SIZE) { - error = -EIO; + if (dax_map_atomic(bdev, &dax) < 0) { + error = PTR_ERR(dax.addr); goto out; } if (buffer_unwritten(bh) || buffer_new(bh)) { - clear_pmem(addr, PAGE_SIZE); + clear_pmem(dax.addr, PAGE_SIZE); wmb_pmem(); } + dax_unmap_atomic(bdev, &dax); - error = vm_insert_mixed(vma, vaddr, pfn); + error = vm_insert_mixed(vma, vaddr, dax.pfn); out: i_mmap_unlock_read(mapping); @@ -422,7 +457,7 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (vmf->cow_page) { struct page *new_page = vmf->cow_page; if (buffer_written(&bh)) - error = copy_user_bh(new_page, &bh, blkbits, vaddr); + error = copy_user_bh(new_page, inode, &bh, vaddr); else clear_user_highpage(new_page, vaddr); if (error) @@ -523,6 +558,24 @@ EXPORT_SYMBOL_GPL(dax_fault); */ #define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) +static void __dax_dbg(struct buffer_head *bh, unsigned long address, + const char *reason, const char *fn) +{ + if (bh) { + char bname[BDEVNAME_SIZE]; + bdevname(bh->b_bdev, bname); + pr_debug("%s: %s addr: %lx dev %s state %lx start %lld " + "length %zd fallback: %s\n", fn, current->comm, + address, bname, bh->b_state, (u64)bh->b_blocknr, + bh->b_size, reason); + } else { + pr_debug("%s: %s addr: %lx fallback: %s\n", fn, + current->comm, address, reason); + } +} + +#define dax_pmd_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pmd") + int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, get_block_t get_block, dax_iodone_t complete_unwritten) @@ -534,41 +587,49 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, unsigned blkbits = inode->i_blkbits; unsigned long pmd_addr = address & PMD_MASK; bool write = flags & FAULT_FLAG_WRITE; - long length; - void __pmem *kaddr; + struct block_device *bdev; pgoff_t size, pgoff; - sector_t block, sector; - unsigned long pfn; + sector_t block; int result = 0; - /* dax pmd mappings are broken wrt gup and fork */ + /* dax pmd mappings require pfn_t_devmap() */ if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) return VM_FAULT_FALLBACK; /* Fall back to PTEs if we're going to COW */ - if (write && !(vma->vm_flags & VM_SHARED)) + if (write && !(vma->vm_flags & VM_SHARED)) { + split_huge_pmd(vma, pmd, address); + dax_pmd_dbg(NULL, address, "cow write"); return VM_FAULT_FALLBACK; + } /* If the PMD would extend outside the VMA */ - if (pmd_addr < vma->vm_start) + if (pmd_addr < vma->vm_start) { + dax_pmd_dbg(NULL, address, "vma start unaligned"); return VM_FAULT_FALLBACK; - if ((pmd_addr + PMD_SIZE) > vma->vm_end) + } + if ((pmd_addr + PMD_SIZE) > vma->vm_end) { + dax_pmd_dbg(NULL, address, "vma end unaligned"); return VM_FAULT_FALLBACK; + } pgoff = linear_page_index(vma, pmd_addr); size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (pgoff >= size) return VM_FAULT_SIGBUS; /* If the PMD would cover blocks out of the file */ - if ((pgoff | PG_PMD_COLOUR) >= size) + if ((pgoff | PG_PMD_COLOUR) >= size) { + dax_pmd_dbg(NULL, address, + "offset + huge page size > file size"); return VM_FAULT_FALLBACK; + } memset(&bh, 0, sizeof(bh)); block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; - length = get_block(inode, block, &bh, write); - if (length) + if (get_block(inode, block, &bh, write) != 0) return VM_FAULT_SIGBUS; + bdev = bh.b_bdev; i_mmap_lock_read(mapping); /* @@ -576,8 +637,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, * just fall back to PTEs. Calling get_block 512 times in a loop * would be silly. */ - if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) + if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) { + dax_pmd_dbg(&bh, address, "allocated block too small"); goto fallback; + } /* * If we allocated new storage, make sure no process has any @@ -600,57 +663,82 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, result = VM_FAULT_SIGBUS; goto out; } - if ((pgoff | PG_PMD_COLOUR) >= size) + if ((pgoff | PG_PMD_COLOUR) >= size) { + dax_pmd_dbg(&bh, address, "pgoff unaligned"); goto fallback; + } if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) { spinlock_t *ptl; pmd_t entry; struct page *zero_page = get_huge_zero_page(); - if (unlikely(!zero_page)) + if (unlikely(!zero_page)) { + dax_pmd_dbg(&bh, address, "no zero page"); goto fallback; + } ptl = pmd_lock(vma->vm_mm, pmd); if (!pmd_none(*pmd)) { spin_unlock(ptl); + dax_pmd_dbg(&bh, address, "pmd already present"); goto fallback; } + dev_dbg(part_to_dev(bdev->bd_part), + "%s: %s addr: %lx pfn: <zero> sect: %llx\n", + __func__, current->comm, address, + (unsigned long long) to_sector(&bh, inode)); + entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry); result = VM_FAULT_NOPAGE; spin_unlock(ptl); } else { - sector = bh.b_blocknr << (blkbits - 9); - length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn, - bh.b_size); + struct blk_dax_ctl dax = { + .sector = to_sector(&bh, inode), + .size = PMD_SIZE, + }; + long length = dax_map_atomic(bdev, &dax); + if (length < 0) { result = VM_FAULT_SIGBUS; goto out; } - if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) + if (length < PMD_SIZE) { + dax_pmd_dbg(&bh, address, "dax-length too small"); + dax_unmap_atomic(bdev, &dax); goto fallback; + } + if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) { + dax_pmd_dbg(&bh, address, "pfn unaligned"); + dax_unmap_atomic(bdev, &dax); + goto fallback; + } - /* - * TODO: teach vmf_insert_pfn_pmd() to support - * 'pte_special' for pmds - */ - if (pfn_valid(pfn)) + if (!pfn_t_devmap(dax.pfn)) { + dax_unmap_atomic(bdev, &dax); + dax_pmd_dbg(&bh, address, "pfn not in memmap"); goto fallback; + } if (buffer_unwritten(&bh) || buffer_new(&bh)) { - int i; - for (i = 0; i < PTRS_PER_PMD; i++) - clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); + clear_pmem(dax.addr, PMD_SIZE); wmb_pmem(); count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); result |= VM_FAULT_MAJOR; } - - result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write); + dax_unmap_atomic(bdev, &dax); + + dev_dbg(part_to_dev(bdev->bd_part), + "%s: %s addr: %lx pfn: %lx sect: %llx\n", + __func__, current->comm, address, + pfn_t_to_pfn(dax.pfn), + (unsigned long long) dax.sector); + result |= vmf_insert_pfn_pmd(vma, address, pmd, + dax.pfn, write); } out: @@ -752,12 +840,17 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length, if (err < 0) return err; if (buffer_written(&bh)) { - void __pmem *addr; - err = dax_get_addr(&bh, &addr, inode->i_blkbits); - if (err < 0) - return err; - clear_pmem(addr + offset, length); + struct block_device *bdev = bh.b_bdev; + struct blk_dax_ctl dax = { + .sector = to_sector(&bh, inode), + .size = PAGE_CACHE_SIZE, + }; + + if (dax_map_atomic(bdev, &dax) < 0) + return PTR_ERR(dax.addr); + clear_pmem(dax.addr + offset, length); wmb_pmem(); + dax_unmap_atomic(bdev, &dax); } return 0; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 023f6a1f23cd..6915c950e6e8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -677,9 +677,7 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page, if (!wbc->wb) return; - rcu_read_lock(); id = mem_cgroup_css_from_page(page)->id; - rcu_read_unlock(); if (id == wbc->wb_id) { wbc->wb_bytes += bytes; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 47789292a582..8bbf7f3e2a27 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -324,11 +324,48 @@ static void remove_huge_page(struct page *page) delete_from_page_cache(page); } +static void +hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) +{ + struct vm_area_struct *vma; + + /* + * end == 0 indicates that the entire range after + * start should be unmapped. + */ + vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) { + unsigned long v_offset; + unsigned long v_end; + + /* + * Can the expression below overflow on 32-bit arches? + * No, because the interval tree returns us only those vmas + * which overlap the truncated area starting at pgoff, + * and no vma on a 32-bit arch can span beyond the 4GB. + */ + if (vma->vm_pgoff < start) + v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT; + else + v_offset = 0; + + if (!end) + v_end = vma->vm_end; + else { + v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + + vma->vm_start; + if (v_end > vma->vm_end) + v_end = vma->vm_end; + } + + unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end, + NULL); + } +} /* * remove_inode_hugepages handles two distinct cases: truncation and hole * punch. There are subtle differences in operation for each case. - + * * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv @@ -379,6 +416,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; + bool rsv_on_error; u32 hash; /* @@ -395,37 +433,43 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, mapping, next, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); - lock_page(page); - if (likely(!page_mapped(page))) { - bool rsv_on_error = !PagePrivate(page); - /* - * We must free the huge page and remove - * from page cache (remove_huge_page) BEFORE - * removing the region/reserve map - * (hugetlb_unreserve_pages). In rare out - * of memory conditions, removal of the - * region/reserve map could fail. Before - * free'ing the page, note PagePrivate which - * is used in case of error. - */ - remove_huge_page(page); - freed++; - if (!truncate_op) { - if (unlikely(hugetlb_unreserve_pages( - inode, next, - next + 1, 1))) - hugetlb_fix_reserve_counts( - inode, rsv_on_error); - } - } else { - /* - * If page is mapped, it was faulted in after - * being unmapped. It indicates a race between - * hole punch and page fault. Do nothing in - * this case. Getting here in a truncate - * operation is a bug. - */ + /* + * If page is mapped, it was faulted in after being + * unmapped in caller. Unmap (again) now after taking + * the fault mutex. The mutex will prevent faults + * until we finish removing the page. + * + * This race can only happen in the hole punch case. + * Getting here in a truncate operation is a bug. + */ + if (unlikely(page_mapped(page))) { BUG_ON(truncate_op); + + i_mmap_lock_write(mapping); + hugetlb_vmdelete_list(&mapping->i_mmap, + next * pages_per_huge_page(h), + (next + 1) * pages_per_huge_page(h)); + i_mmap_unlock_write(mapping); + } + + lock_page(page); + /* + * We must free the huge page and remove from page + * cache (remove_huge_page) BEFORE removing the + * region/reserve map (hugetlb_unreserve_pages). In + * rare out of memory conditions, removal of the + * region/reserve map could fail. Before free'ing + * the page, note PagePrivate which is used in case + * of error. + */ + rsv_on_error = !PagePrivate(page); + remove_huge_page(page); + freed++; + if (!truncate_op) { + if (unlikely(hugetlb_unreserve_pages(inode, + next, next + 1, 1))) + hugetlb_fix_reserve_counts(inode, + rsv_on_error); } unlock_page(page); @@ -452,41 +496,6 @@ static void hugetlbfs_evict_inode(struct inode *inode) clear_inode(inode); } -static inline void -hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) -{ - struct vm_area_struct *vma; - - /* - * end == 0 indicates that the entire range after - * start should be unmapped. - */ - vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) { - unsigned long v_offset; - - /* - * Can the expression below overflow on 32-bit arches? - * No, because the interval tree returns us only those vmas - * which overlap the truncated area starting at pgoff, - * and no vma on a 32-bit arch can span beyond the 4GB. - */ - if (vma->vm_pgoff < start) - v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT; - else - v_offset = 0; - - if (end) { - end = ((end - start) << PAGE_SHIFT) + - vma->vm_start + v_offset; - if (end > vma->vm_end) - end = vma->vm_end; - } else - end = vma->vm_end; - - unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL); - } -} - static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) { pgoff_t pgoff; @@ -708,7 +717,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, /* * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never * be taken from reclaim -- unlike regular filesystems. This needs an - * annotation because huge_pmd_share() does an allocation under + * annotation because huge_pmd_share() does an allocation under hugetlb's * i_mmap_rwsem. */ static struct lock_class_key hugetlbfs_i_mmap_rwsem_key; diff --git a/fs/proc/page.c b/fs/proc/page.c index 93484034a03d..b2855eea5405 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -103,9 +103,9 @@ u64 stable_page_flags(struct page *page) * pseudo flags for the well known (anonymous) memory mapped pages * * Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the - * simple test in page_mapped() is not enough. + * simple test in page_mapcount() is not enough. */ - if (!PageSlab(page) && page_mapped(page)) + if (!PageSlab(page) && page_mapcount(page)) u |= 1 << KPF_MMAP; if (PageAnon(page)) u |= 1 << KPF_ANON; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index a353b4c6e86e..65a1b6c69c11 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -466,9 +466,10 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - unsigned long size, bool young, bool dirty) + bool compound, bool young, bool dirty) { - int mapcount; + int i, nr = compound ? HPAGE_PMD_NR : 1; + unsigned long size = nr * PAGE_SIZE; if (PageAnon(page)) mss->anonymous += size; @@ -477,23 +478,37 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, /* Accumulate the size in pages that have been accessed. */ if (young || page_is_young(page) || PageReferenced(page)) mss->referenced += size; - mapcount = page_mapcount(page); - if (mapcount >= 2) { - u64 pss_delta; - if (dirty || PageDirty(page)) - mss->shared_dirty += size; - else - mss->shared_clean += size; - pss_delta = (u64)size << PSS_SHIFT; - do_div(pss_delta, mapcount); - mss->pss += pss_delta; - } else { + /* + * page_count(page) == 1 guarantees the page is mapped exactly once. + * If any subpage of the compound page mapped with PTE it would elevate + * page_count(). + */ + if (page_count(page) == 1) { if (dirty || PageDirty(page)) mss->private_dirty += size; else mss->private_clean += size; mss->pss += (u64)size << PSS_SHIFT; + return; + } + + for (i = 0; i < nr; i++, page++) { + int mapcount = page_mapcount(page); + + if (mapcount >= 2) { + if (dirty || PageDirty(page)) + mss->shared_dirty += PAGE_SIZE; + else + mss->shared_clean += PAGE_SIZE; + mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; + } else { + if (dirty || PageDirty(page)) + mss->private_dirty += PAGE_SIZE; + else + mss->private_clean += PAGE_SIZE; + mss->pss += PAGE_SIZE << PSS_SHIFT; + } } } @@ -554,7 +569,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte)); + + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte)); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -570,8 +586,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, if (IS_ERR_OR_NULL(page)) return; mss->anonymous_thp += HPAGE_PMD_SIZE; - smaps_account(mss, page, HPAGE_PMD_SIZE, - pmd_young(*pmd), pmd_dirty(*pmd)); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd)); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -587,7 +602,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { smaps_pmd_entry(pmd, addr, walk); spin_unlock(ptl); return 0; @@ -898,7 +913,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, spinlock_t *ptl; struct page *page; - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { if (cp->type == CLEAR_REFS_SOFT_DIRTY) { clear_soft_dirty_pmd(vma, addr, pmd); goto out; @@ -1172,7 +1187,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, int err = 0; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmdp, vma, &ptl)) { u64 flags = 0, frame = 0; pmd_t pmd = *pmdp; @@ -1504,7 +1519,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, pte_t *orig_pte; pte_t *pte; - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { pte_t huge_pte = *(pte_t *)pmd; struct page *page; diff --git a/fs/stat.c b/fs/stat.c index d4a61d8dc021..bc045c7994e1 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -219,7 +219,7 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat # define choose_32_64(a,b) b #endif -#define valid_dev(x) choose_32_64(old_valid_dev,new_valid_dev)(x) +#define valid_dev(x) choose_32_64(old_valid_dev(x),true) #define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) #ifndef INIT_STRUCT_STAT_PADDING |