1 files changed, 103 insertions, 68 deletions

diff --git a/fs/dax.c b/fs/dax.c
index c45598b912e1..de622d4282a6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -27,6 +27,7 @@
 #include <linux/pagevec.h>
 #include <linux/pmem.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uio.h>
 #include <linux/vmstat.h>
 #include <linux/pfn_t.h>
@@ -35,6 +36,9 @@
 #include <linux/iomap.h>
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/fs_dax.h>
+
 /* We choose 4096 entries - same as per-zone page wait tables */
 #define DAX_WAIT_TABLE_BITS 12
 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)
@@ -922,12 +926,11 @@ static int dax_insert_mapping(struct address_space *mapping,
 
 /**
  * dax_pfn_mkwrite - handle first write to DAX page
- * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  */
-int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int dax_pfn_mkwrite(struct vm_fault *vmf)
 {
-	struct file *file = vma->vm_file;
+	struct file *file = vmf->vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	void *entry, **slot;
 	pgoff_t index = vmf->pgoff;
@@ -1079,15 +1082,19 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
  */
 ssize_t
 dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
-		struct iomap_ops *ops)
+		const struct iomap_ops *ops)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = mapping->host;
 	loff_t pos = iocb->ki_pos, ret = 0, done = 0;
 	unsigned flags = 0;
 
-	if (iov_iter_rw(iter) == WRITE)
+	if (iov_iter_rw(iter) == WRITE) {
+		lockdep_assert_held_exclusive(&inode->i_rwsem);
 		flags |= IOMAP_WRITE;
+	} else {
+		lockdep_assert_held(&inode->i_rwsem);
+	}
 
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
@@ -1112,20 +1119,10 @@ static int dax_fault_return(int error)
 	return VM_FAULT_SIGBUS;
 }
 
-/**
- * dax_iomap_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @ops: iomap ops passed from the file system
- *
- * When a page fault occurs, filesystems may call this helper in their fault
- * or mkwrite handler for DAX files. Assumes the caller has done all the
- * necessary locking for the page fault to proceed successfully.
- */
-int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-			struct iomap_ops *ops)
+static int dax_iomap_pte_fault(struct vm_fault *vmf,
+			       const struct iomap_ops *ops)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	struct inode *inode = mapping->host;
 	unsigned long vaddr = vmf->address;
 	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
@@ -1198,11 +1195,11 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	case IOMAP_MAPPED:
 		if (iomap.flags & IOMAP_F_NEW) {
 			count_vm_event(PGMAJFAULT);
-			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
 			major = VM_FAULT_MAJOR;
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, sector,
-				PAGE_SIZE, &entry, vma, vmf);
+				PAGE_SIZE, &entry, vmf->vma, vmf);
 		/* -EBUSY is fine, somebody else faulted on the same PTE */
 		if (error == -EBUSY)
 			error = 0;
@@ -1240,7 +1237,6 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	}
 	return vmf_ret;
 }
-EXPORT_SYMBOL_GPL(dax_iomap_fault);
 
 #ifdef CONFIG_FS_DAX_PMD
 /*
@@ -1249,21 +1245,21 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault);
  */
 #define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
 
-static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
-		struct vm_fault *vmf, unsigned long address,
-		struct iomap *iomap, loff_t pos, bool write, void **entryp)
+static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap,
+		loff_t pos, void **entryp)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	struct block_device *bdev = iomap->bdev;
+	struct inode *inode = mapping->host;
 	struct blk_dax_ctl dax = {
 		.sector = dax_iomap_sector(iomap, pos),
 		.size = PMD_SIZE,
 	};
 	long length = dax_map_atomic(bdev, &dax);
-	void *ret;
+	void *ret = NULL;
 
 	if (length < 0) /* dax_map_atomic() failed */
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 	if (length < PMD_SIZE)
 		goto unmap_fallback;
 	if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR)
@@ -1276,67 +1272,87 @@ static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
 	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, dax.sector,
 			RADIX_DAX_PMD);
 	if (IS_ERR(ret))
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 	*entryp = ret;
 
-	return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write);
+	trace_dax_pmd_insert_mapping(inode, vmf, length, dax.pfn, ret);
+	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
+			dax.pfn, vmf->flags & FAULT_FLAG_WRITE);
 
  unmap_fallback:
 	dax_unmap_atomic(bdev, &dax);
+fallback:
+	trace_dax_pmd_insert_mapping_fallback(inode, vmf, length,
+			dax.pfn, ret);
 	return VM_FAULT_FALLBACK;
 }
 
-static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
-		struct vm_fault *vmf, unsigned long address,
-		struct iomap *iomap, void **entryp)
+static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
+		void **entryp)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	unsigned long pmd_addr = address & PMD_MASK;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	struct inode *inode = mapping->host;
 	struct page *zero_page;
+	void *ret = NULL;
 	spinlock_t *ptl;
 	pmd_t pmd_entry;
-	void *ret;
 
-	zero_page = mm_get_huge_zero_page(vma->vm_mm);
+	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
 
 	if (unlikely(!zero_page))
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 
 	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0,
 			RADIX_DAX_PMD | RADIX_DAX_HZP);
 	if (IS_ERR(ret))
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 	*entryp = ret;
 
-	ptl = pmd_lock(vma->vm_mm, pmd);
-	if (!pmd_none(*pmd)) {
+	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
+	if (!pmd_none(*(vmf->pmd))) {
 		spin_unlock(ptl);
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 	}
 
-	pmd_entry = mk_pmd(zero_page, vma->vm_page_prot);
+	pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
 	pmd_entry = pmd_mkhuge(pmd_entry);
-	set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry);
+	set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
 	spin_unlock(ptl);
+	trace_dax_pmd_load_hole(inode, vmf, zero_page, ret);
 	return VM_FAULT_NOPAGE;
+
+fallback:
+	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret);
+	return VM_FAULT_FALLBACK;
 }
 
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops)
+static int dax_iomap_pmd_fault(struct vm_fault *vmf,
+			       const struct iomap_ops *ops)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping = vma->vm_file->f_mapping;
-	unsigned long pmd_addr = address & PMD_MASK;
-	bool write = flags & FAULT_FLAG_WRITE;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
 	struct inode *inode = mapping->host;
 	int result = VM_FAULT_FALLBACK;
 	struct iomap iomap = { 0 };
 	pgoff_t max_pgoff, pgoff;
-	struct vm_fault vmf;
 	void *entry;
 	loff_t pos;
 	int error;
 
+	/*
+	 * Check whether offset isn't beyond end of file now. Caller is
+	 * supposed to hold locks serializing us with truncate / punch hole so
+	 * this is a reliable test.
+	 */
+	pgoff = linear_page_index(vma, pmd_addr);
+	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
+
+	trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
+
 	/* Fall back to PTEs if we're going to COW */
 	if (write && !(vma->vm_flags & VM_SHARED))
 		goto fallback;
@@ -1347,16 +1363,10 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
 		goto fallback;
 
-	/*
-	 * Check whether offset isn't beyond end of file now. Caller is
-	 * supposed to hold locks serializing us with truncate / punch hole so
-	 * this is a reliable test.
-	 */
-	pgoff = linear_page_index(vma, pmd_addr);
-	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
-
-	if (pgoff > max_pgoff)
-		return VM_FAULT_SIGBUS;
+	if (pgoff > max_pgoff) {
+		result = VM_FAULT_SIGBUS;
+		goto out;
+	}
 
 	/* If the PMD would extend beyond the file size */
 	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
@@ -1385,21 +1395,15 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if (IS_ERR(entry))
 		goto finish_iomap;
 
-	vmf.pgoff = pgoff;
-	vmf.flags = flags;
-	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
-
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
-		result = dax_pmd_insert_mapping(vma, pmd, &vmf, address,
-				&iomap, pos, write, &entry);
+		result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry);
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
 			goto unlock_entry;
-		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
-				&entry);
+		result = dax_pmd_load_hole(vmf, &iomap, &entry);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1425,10 +1429,41 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	}
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
-		split_huge_pmd(vma, pmd, address);
+		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		count_vm_event(THP_FAULT_FALLBACK);
 	}
+out:
+	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
 	return result;
 }
-EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
+#else
+static int dax_iomap_pmd_fault(struct vm_fault *vmf,
+			       const struct iomap_ops *ops)
+{
+	return VM_FAULT_FALLBACK;
+}
 #endif /* CONFIG_FS_DAX_PMD */
+
+/**
+ * dax_iomap_fault - handle a page fault on a DAX file
+ * @vmf: The description of the fault
+ * @ops: iomap ops passed from the file system
+ *
+ * When a page fault occurs, filesystems may call this helper in
+ * their fault handler for DAX files. dax_iomap_fault() assumes the caller
+ * has done all the necessary locking for page fault to proceed
+ * successfully.
+ */
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+		    const struct iomap_ops *ops)
+{
+	switch (pe_size) {
+	case PE_SIZE_PTE:
+		return dax_iomap_pte_fault(vmf, ops);
+	case PE_SIZE_PMD:
+		return dax_iomap_pmd_fault(vmf, ops);
+	default:
+		return VM_FAULT_FALLBACK;
+	}
+}
+EXPORT_SYMBOL_GPL(dax_iomap_fault);