1 files changed, 197 insertions, 104 deletions

diff --git a/fs/dax.c b/fs/dax.c
index 43671b68220e..7af879759064 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -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;