[PATCH v4 0/7] DAX tracepoints, mm argument simplification

[PATCH v4 0/7] DAX tracepoints, mm argument simplification

[Ross Zwisler]

Andrew,

This contains both my DAX tracepoint code and Dave Jiang's MM argument
simplifications.  Dave's code was written with my tracepoint code as a
baseline, so it seemed simplest to keep them together in a single series.

This series is based on the v4.10-rc3-mmots-2017-01-09-17-08 snapshot.  A
working tree can be found here:

https://git.kernel.org/cgit/linux/kernel/git/zwisler/linux.git/log/?h=mmots_dax_tracepoint

Changes from the previous versions of these patches:
 - Combined Dave's code and mine into a single series.
 - Resolved some minor merge conflics in Dave's patches so they could be
   applied to the latest mmots snapshot.
 - Added Reviewed-by and Acked-by tags to patches as appropriate.

My goal for this series is to get it merged for v4.11.

Thanks,
- Ross

Dave Jiang (2):
  mm, dax: make pmd_fault() and friends to be the same as fault()
  mm, dax: move pmd_fault() to take only vmf parameter

Ross Zwisler (5):
  tracing: add __print_flags_u64()
  dax: add tracepoint infrastructure, PMD tracing
  dax: update MAINTAINERS entries for FS DAX
  dax: add tracepoints to dax_pmd_load_hole()
  dax: add tracepoints to dax_pmd_insert_mapping()

 MAINTAINERS                   |   5 +-
 drivers/dax/dax.c             |  26 ++++---
 fs/dax.c                      | 114 ++++++++++++++++--------------
 fs/ext4/file.c                |  13 ++--
 fs/xfs/xfs_file.c             |  15 ++--
 include/linux/dax.h           |   6 +-
 include/linux/mm.h            |  28 +++++++-
 include/linux/pfn_t.h         |   6 ++
 include/linux/trace_events.h  |   4 ++
 include/trace/events/fs_dax.h | 156 ++++++++++++++++++++++++++++++++++++++++++
 include/trace/trace_events.h  |  11 +++
 kernel/trace/trace_output.c   |  38 ++++++++++
 mm/memory.c                   |  11 ++-
 13 files changed, 338 insertions(+), 95 deletions(-)
 create mode 100644 include/trace/events/fs_dax.h

-- 
2.7.4

[PATCH v4 1/7] tracing: add __print_flags_u64()

[Ross Zwisler]

Add __print_flags_u64() and the helper trace_print_flags_seq_u64() in the
same spirit as __print_symbolic_u64() and trace_print_symbols_seq_u64().
These functions allow us to print symbols associated with flags that are 64
bits wide even on 32 bit machines.

These will be used by the DAX code so that we can print the flags set in a
pfn_t such as PFN_SG_CHAIN, PFN_SG_LAST, PFN_DEV and PFN_MAP.

Without this new function I was getting errors like the following when
compiling for i386:

./include/linux/pfn_t.h:13:22: warning: large integer implicitly truncated
to unsigned type [-Woverflow]
 #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
  ^

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/trace_events.h |  4 ++++
 include/trace/trace_events.h | 11 +++++++++++
 kernel/trace/trace_output.c  | 38 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 53 insertions(+)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index be00761..db2c3ba 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -23,6 +23,10 @@ const char *trace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 				    const struct trace_print_flags *symbol_array);
 
 #if BITS_PER_LONG == 32
+const char *trace_print_flags_seq_u64(struct trace_seq *p, const char *delim,
+		      unsigned long long flags,
+		      const struct trace_print_flags_u64 *flag_array);
+
 const char *trace_print_symbols_seq_u64(struct trace_seq *p,
 					unsigned long long val,
 					const struct trace_print_flags_u64
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 467e12f..c6e9f72 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -283,8 +283,16 @@ TRACE_MAKE_SYSTEM_STR();
 		trace_print_symbols_seq(p, value, symbols);		\
 	})
 
+#undef __print_flags_u64
 #undef __print_symbolic_u64
 #if BITS_PER_LONG == 32
+#define __print_flags_u64(flag, delim, flag_array...)			\
+	({								\
+		static const struct trace_print_flags_u64 __flags[] =	\
+			{ flag_array, { -1, NULL } };			\
+		trace_print_flags_seq_u64(p, delim, flag, __flags);	\
+	})
+
 #define __print_symbolic_u64(value, symbol_array...)			\
 	({								\
 		static const struct trace_print_flags_u64 symbols[] =	\
@@ -292,6 +300,9 @@ TRACE_MAKE_SYSTEM_STR();
 		trace_print_symbols_seq_u64(p, value, symbols);	\
 	})
 #else
+#define __print_flags_u64(flag, delim, flag_array...)			\
+			__print_flags(flag, delim, flag_array)
+
 #define __print_symbolic_u64(value, symbol_array...)			\
 			__print_symbolic(value, symbol_array)
 #endif
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 5d33a73..5204485 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -124,6 +124,44 @@ EXPORT_SYMBOL(trace_print_symbols_seq);
 
 #if BITS_PER_LONG == 32
 const char *
+trace_print_flags_seq_u64(struct trace_seq *p, const char *delim,
+		      unsigned long long flags,
+		      const struct trace_print_flags_u64 *flag_array)
+{
+	unsigned long long mask;
+	const char *str;
+	const char *ret = trace_seq_buffer_ptr(p);
+	int i, first = 1;
+
+	for (i = 0;  flag_array[i].name && flags; i++) {
+
+		mask = flag_array[i].mask;
+		if ((flags & mask) != mask)
+			continue;
+
+		str = flag_array[i].name;
+		flags &= ~mask;
+		if (!first && delim)
+			trace_seq_puts(p, delim);
+		else
+			first = 0;
+		trace_seq_puts(p, str);
+	}
+
+	/* check for left over flags */
+	if (flags) {
+		if (!first && delim)
+			trace_seq_puts(p, delim);
+		trace_seq_printf(p, "0x%llx", flags);
+	}
+
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(trace_print_flags_seq_u64);
+
+const char *
 trace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
 			 const struct trace_print_flags_u64 *symbol_array)
 {
-- 
2.7.4

[PATCH v4 2/7] dax: add tracepoint infrastructure, PMD tracing

[Ross Zwisler]

Tracepoints are the standard way to capture debugging and tracing
information in many parts of the kernel, including the XFS and ext4
filesystems.  Create a tracepoint header for FS DAX and add the first DAX
tracepoints to the PMD fault handler.  This allows the tracing for DAX to
be done in the same way as the filesystem tracing so that developers can
look at them together and get a coherent idea of what the system is doing.

I added both an entry and exit tracepoint because future patches will add
tracepoints to child functions of dax_iomap_pmd_fault() like
dax_pmd_load_hole() and dax_pmd_insert_mapping(). We want those messages to
be wrapped by the parent function tracepoints so the code flow is more
easily understood.  Having entry and exit tracepoints for faults also
allows us to easily see what filesystems functions were called during the
fault.  These filesystem functions get executed via iomap_begin() and
iomap_end() calls, for example, and will have their own tracepoints.

For PMD faults we primarily want to understand the type of mapping, the
fault flags, the faulting address and whether it fell back to 4k faults.
If it fell back to 4k faults the tracepoints should let us understand why.

I named the new tracepoint header file "fs_dax.h" to allow for device DAX
to have its own separate tracing header in the same directory at some
point.

Here is an example output for these events from a successful PMD fault:

big-1441  [005] ....    32.582758: xfs_filemap_pmd_fault: dev 259:0 ino
0x1003

big-1441  [005] ....    32.582776: dax_pmd_fault: dev 259:0 ino 0x1003
shared WRITE|ALLOW_RETRY|KILLABLE|USER address 0x10505000 vm_start
0x10200000 vm_end 0x10700000 pgoff 0x200 max_pgoff 0x1400

big-1441  [005] ....    32.583292: dax_pmd_fault_done: dev 259:0 ino 0x1003
shared WRITE|ALLOW_RETRY|KILLABLE|USER address 0x10505000 vm_start
0x10200000 vm_end 0x10700000 pgoff 0x200 max_pgoff 0x1400 NOPAGE

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
---
 fs/dax.c                      | 30 ++++++++++++-------
 include/linux/mm.h            | 25 ++++++++++++++++
 include/trace/events/fs_dax.h | 68 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 113 insertions(+), 10 deletions(-)
 create mode 100644 include/trace/events/fs_dax.h

diff --git a/fs/dax.c b/fs/dax.c
index ddcddfe..b719ecf 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -35,6 +35,9 @@
 #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)
@@ -1333,6 +1336,16 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	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, vma, address, flags, pgoff, max_pgoff, 0);
+
 	/* Fall back to PTEs if we're going to COW */
 	if (write && !(vma->vm_flags & VM_SHARED))
 		goto fallback;
@@ -1343,16 +1356,10 @@ 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)
@@ -1424,6 +1431,9 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		split_huge_pmd(vma, pmd, address);
 		count_vm_event(THP_FAULT_FALLBACK);
 	}
+out:
+	trace_dax_pmd_fault_done(inode, vma, address, flags, pgoff, max_pgoff,
+			result);
 	return result;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d22fc0d..aaf4c96 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -281,6 +281,17 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_REMOTE	0x80	/* faulting for non current tsk/mm */
 #define FAULT_FLAG_INSTRUCTION  0x100	/* The fault was during an instruction fetch */
 
+#define FAULT_FLAG_TRACE \
+	{ FAULT_FLAG_WRITE,		"WRITE" }, \
+	{ FAULT_FLAG_MKWRITE,		"MKWRITE" }, \
+	{ FAULT_FLAG_ALLOW_RETRY,	"ALLOW_RETRY" }, \
+	{ FAULT_FLAG_RETRY_NOWAIT,	"RETRY_NOWAIT" }, \
+	{ FAULT_FLAG_KILLABLE,		"KILLABLE" }, \
+	{ FAULT_FLAG_TRIED,		"TRIED" }, \
+	{ FAULT_FLAG_USER,		"USER" }, \
+	{ FAULT_FLAG_REMOTE,		"REMOTE" }, \
+	{ FAULT_FLAG_INSTRUCTION,	"INSTRUCTION" }
+
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
@@ -1107,6 +1118,20 @@ static inline void clear_page_pfmemalloc(struct page *page)
 			 VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
 			 VM_FAULT_FALLBACK)
 
+#define VM_FAULT_RESULT_TRACE \
+	{ VM_FAULT_OOM,			"OOM" }, \
+	{ VM_FAULT_SIGBUS,		"SIGBUS" }, \
+	{ VM_FAULT_MAJOR,		"MAJOR" }, \
+	{ VM_FAULT_WRITE,		"WRITE" }, \
+	{ VM_FAULT_HWPOISON,		"HWPOISON" }, \
+	{ VM_FAULT_HWPOISON_LARGE,	"HWPOISON_LARGE" }, \
+	{ VM_FAULT_SIGSEGV,		"SIGSEGV" }, \
+	{ VM_FAULT_NOPAGE,		"NOPAGE" }, \
+	{ VM_FAULT_LOCKED,		"LOCKED" }, \
+	{ VM_FAULT_RETRY,		"RETRY" }, \
+	{ VM_FAULT_FALLBACK,		"FALLBACK" }, \
+	{ VM_FAULT_DONE_COW,		"DONE_COW" }
+
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
 #define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf)
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
new file mode 100644
index 0000000..58b0b56
--- /dev/null
+++ b/include/trace/events/fs_dax.h
@@ -0,0 +1,68 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM fs_dax
+
+#if !defined(_TRACE_FS_DAX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FS_DAX_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(dax_pmd_fault_class,
+	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
+		unsigned long address, unsigned int flags, pgoff_t pgoff,
+		pgoff_t max_pgoff, int result),
+	TP_ARGS(inode, vma, address, flags, pgoff, max_pgoff, result),
+	TP_STRUCT__entry(
+		__field(unsigned long, ino)
+		__field(unsigned long, vm_start)
+		__field(unsigned long, vm_end)
+		__field(unsigned long, vm_flags)
+		__field(unsigned long, address)
+		__field(pgoff_t, pgoff)
+		__field(pgoff_t, max_pgoff)
+		__field(dev_t, dev)
+		__field(unsigned int, flags)
+		__field(int, result)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->vm_start = vma->vm_start;
+		__entry->vm_end = vma->vm_end;
+		__entry->vm_flags = vma->vm_flags;
+		__entry->address = address;
+		__entry->flags = flags;
+		__entry->pgoff = pgoff;
+		__entry->max_pgoff = max_pgoff;
+		__entry->result = result;
+	),
+	TP_printk("dev %d:%d ino %#lx %s %s address %#lx vm_start "
+			"%#lx vm_end %#lx pgoff %#lx max_pgoff %#lx %s",
+		MAJOR(__entry->dev),
+		MINOR(__entry->dev),
+		__entry->ino,
+		__entry->vm_flags & VM_SHARED ? "shared" : "private",
+		__print_flags(__entry->flags, "|", FAULT_FLAG_TRACE),
+		__entry->address,
+		__entry->vm_start,
+		__entry->vm_end,
+		__entry->pgoff,
+		__entry->max_pgoff,
+		__print_flags(__entry->result, "|", VM_FAULT_RESULT_TRACE)
+	)
+)
+
+#define DEFINE_PMD_FAULT_EVENT(name) \
+DEFINE_EVENT(dax_pmd_fault_class, name, \
+	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
+		unsigned long address, unsigned int flags, pgoff_t pgoff, \
+		pgoff_t max_pgoff, int result), \
+	TP_ARGS(inode, vma, address, flags, pgoff, max_pgoff, result))
+
+DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
+DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
+
+
+#endif /* _TRACE_FS_DAX_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
2.7.4

[PATCH v4 3/7] dax: update MAINTAINERS entries for FS DAX

[Ross Zwisler]

Add the new include/trace/events/fs_dax.h tracepoint header, the existing
include/linux/dax.h header, update Matthew's email address and add myself
as a maintainer for filesystem DAX.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 MAINTAINERS | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c13a4f6..9fb35d7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3909,10 +3909,13 @@ S:	Maintained
 F:	drivers/i2c/busses/i2c-diolan-u2c.c
 
 DIRECT ACCESS (DAX)
-M:	Matthew Wilcox <willy@linux.intel.com>
+M:	Matthew Wilcox <mawilcox@microsoft.com>
+M:	Ross Zwisler <ross.zwisler@linux.intel.com>
 L:	linux-fsdevel@vger.kernel.org
 S:	Supported
 F:	fs/dax.c
+F:	include/linux/dax.h
+F:	include/trace/events/fs_dax.h
 
 DIRECTORY NOTIFICATION (DNOTIFY)
 M:	Eric Paris <eparis@parisplace.org>
-- 
2.7.4

[PATCH v4 4/7] dax: add tracepoints to dax_pmd_load_hole()

[Ross Zwisler]

Add tracepoints to dax_pmd_load_hole(), following the same logging
conventions as the tracepoints in dax_iomap_pmd_fault().

Here is an example PMD fault showing the new tracepoints:

read_big-1478  [004] ....   238.242188: xfs_filemap_pmd_fault: dev 259:0
ino 0x1003

read_big-1478  [004] ....   238.242191: dax_pmd_fault: dev 259:0 ino 0x1003
shared ALLOW_RETRY|KILLABLE|USER address 0x10400000 vm_start 0x10200000
vm_end 0x10600000 pgoff 0x200 max_pgoff 0x1400

read_big-1478  [004] ....   238.242390: dax_pmd_load_hole: dev 259:0 ino
0x1003 shared address 0x10400000 zero_page ffffea0002c20000 radix_entry
0x1e

read_big-1478  [004] ....   238.242392: dax_pmd_fault_done: dev 259:0 ino
0x1003 shared ALLOW_RETRY|KILLABLE|USER address 0x10400000 vm_start
0x10200000 vm_end 0x10600000 pgoff 0x200 max_pgoff 0x1400 NOPAGE

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
---
 fs/dax.c                      | 14 ++++++++++----
 include/trace/events/fs_dax.h | 42 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+), 4 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index b719ecf..199a7e7 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1291,33 +1291,39 @@ static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	unsigned long pmd_addr = 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);
 
 	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)) {
 		spin_unlock(ptl);
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 	}
 
 	pmd_entry = mk_pmd(zero_page, vma->vm_page_prot);
 	pmd_entry = pmd_mkhuge(pmd_entry);
 	set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry);
 	spin_unlock(ptl);
+	trace_dax_pmd_load_hole(inode, vma, address, zero_page, ret);
 	return VM_FAULT_NOPAGE;
+
+fallback:
+	trace_dax_pmd_load_hole_fallback(inode, vma, address, zero_page, ret);
+	return VM_FAULT_FALLBACK;
 }
 
 int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index 58b0b56..43f1263 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -61,6 +61,48 @@ DEFINE_EVENT(dax_pmd_fault_class, name, \
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
 
+DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
+	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
+		unsigned long address, struct page *zero_page,
+		void *radix_entry),
+	TP_ARGS(inode, vma, address, zero_page, radix_entry),
+	TP_STRUCT__entry(
+		__field(unsigned long, ino)
+		__field(unsigned long, vm_flags)
+		__field(unsigned long, address)
+		__field(struct page *, zero_page)
+		__field(void *, radix_entry)
+		__field(dev_t, dev)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->vm_flags = vma->vm_flags;
+		__entry->address = address;
+		__entry->zero_page = zero_page;
+		__entry->radix_entry = radix_entry;
+	),
+	TP_printk("dev %d:%d ino %#lx %s address %#lx zero_page %p "
+			"radix_entry %#lx",
+		MAJOR(__entry->dev),
+		MINOR(__entry->dev),
+		__entry->ino,
+		__entry->vm_flags & VM_SHARED ? "shared" : "private",
+		__entry->address,
+		__entry->zero_page,
+		(unsigned long)__entry->radix_entry
+	)
+)
+
+#define DEFINE_PMD_LOAD_HOLE_EVENT(name) \
+DEFINE_EVENT(dax_pmd_load_hole_class, name, \
+	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
+		unsigned long address, struct page *zero_page, \
+		void *radix_entry), \
+	TP_ARGS(inode, vma, address, zero_page, radix_entry))
+
+DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole);
+DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
 
 #endif /* _TRACE_FS_DAX_H */
 
-- 
2.7.4

[PATCH v4 5/7] dax: add tracepoints to dax_pmd_insert_mapping()

[Ross Zwisler]

Add tracepoints to dax_pmd_insert_mapping(), following the same logging
conventions as the tracepoints in dax_iomap_pmd_fault().

Here is an example PMD fault showing the new tracepoints:

big-1504  [001] ....   326.960743: xfs_filemap_pmd_fault: dev 259:0 ino
0x1003

big-1504  [001] ....   326.960753: dax_pmd_fault: dev 259:0 ino 0x1003
shared WRITE|ALLOW_RETRY|KILLABLE|USER address 0x10505000 vm_start
0x10200000 vm_end 0x10700000 pgoff 0x200 max_pgoff 0x1400

big-1504  [001] ....   326.960981: dax_pmd_insert_mapping: dev 259:0 ino
0x1003 shared write address 0x10505000 length 0x200000 pfn 0x100600 DEV|MAP
radix_entry 0xc000e

big-1504  [001] ....   326.960986: dax_pmd_fault_done: dev 259:0 ino 0x1003
shared WRITE|ALLOW_RETRY|KILLABLE|USER address 0x10505000 vm_start
0x10200000 vm_end 0x10700000 pgoff 0x200 max_pgoff 0x1400 NOPAGE

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
---
 fs/dax.c                      | 12 +++++++---
 include/linux/pfn_t.h         |  6 +++++
 include/trace/events/fs_dax.h | 51 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 66 insertions(+), 3 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 199a7e7..4671530 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1254,15 +1254,16 @@ static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	struct address_space *mapping = 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)
@@ -1275,13 +1276,18 @@ 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;
 
+	trace_dax_pmd_insert_mapping(inode, vma, address, write, length,
+			dax.pfn, ret);
 	return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write);
 
  unmap_fallback:
 	dax_unmap_atomic(bdev, &dax);
+fallback:
+	trace_dax_pmd_insert_mapping_fallback(inode, vma, address, write,
+			length, dax.pfn, ret);
 	return VM_FAULT_FALLBACK;
 }
 
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index a3d90b9..033fc7b 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -15,6 +15,12 @@
 #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
 #define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
 
+#define PFN_FLAGS_TRACE \
+	{ PFN_SG_CHAIN,	"SG_CHAIN" }, \
+	{ PFN_SG_LAST,	"SG_LAST" }, \
+	{ PFN_DEV,	"DEV" }, \
+	{ PFN_MAP,	"MAP" }
+
 static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
 {
 	pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index 43f1263..c3b0aae 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -104,6 +104,57 @@ DEFINE_EVENT(dax_pmd_load_hole_class, name, \
 DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole);
 DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
 
+DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
+	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
+		unsigned long address, int write, long length, pfn_t pfn,
+		void *radix_entry),
+	TP_ARGS(inode, vma, address, write, length, pfn, radix_entry),
+	TP_STRUCT__entry(
+		__field(unsigned long, ino)
+		__field(unsigned long, vm_flags)
+		__field(unsigned long, address)
+		__field(long, length)
+		__field(u64, pfn_val)
+		__field(void *, radix_entry)
+		__field(dev_t, dev)
+		__field(int, write)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->vm_flags = vma->vm_flags;
+		__entry->address = address;
+		__entry->write = write;
+		__entry->length = length;
+		__entry->pfn_val = pfn.val;
+		__entry->radix_entry = radix_entry;
+	),
+	TP_printk("dev %d:%d ino %#lx %s %s address %#lx length %#lx "
+			"pfn %#llx %s radix_entry %#lx",
+		MAJOR(__entry->dev),
+		MINOR(__entry->dev),
+		__entry->ino,
+		__entry->vm_flags & VM_SHARED ? "shared" : "private",
+		__entry->write ? "write" : "read",
+		__entry->address,
+		__entry->length,
+		__entry->pfn_val & ~PFN_FLAGS_MASK,
+		__print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|",
+			PFN_FLAGS_TRACE),
+		(unsigned long)__entry->radix_entry
+	)
+)
+
+#define DEFINE_PMD_INSERT_MAPPING_EVENT(name) \
+DEFINE_EVENT(dax_pmd_insert_mapping_class, name, \
+	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
+		unsigned long address, int write, long length, pfn_t pfn, \
+		void *radix_entry), \
+	TP_ARGS(inode, vma, address, write, length, pfn, radix_entry))
+
+DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping);
+DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping_fallback);
+
 #endif /* _TRACE_FS_DAX_H */
 
 /* This part must be outside protection */
-- 
2.7.4

[PATCH v4 6/7] mm, dax: make pmd_fault() and friends to be the same as fault()

[Ross Zwisler]

From: Dave Jiang <dave.jiang@intel.com>

Instead of passing in multiple parameters in the pmd_fault() handler,
a vmf can be passed in just like a fault() handler. This will simplify
code and remove the need for the actual pmd fault handlers to allocate a
vmf. Related functions are also modified to do the same.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 drivers/dax/dax.c             | 16 +++++++---------
 fs/dax.c                      | 42 ++++++++++++++++++------------------------
 fs/ext4/file.c                |  9 ++++-----
 fs/xfs/xfs_file.c             | 10 ++++------
 include/linux/dax.h           |  7 +++----
 include/linux/mm.h            |  3 +--
 include/trace/events/fs_dax.h | 15 +++++++--------
 mm/memory.c                   |  6 ++----
 8 files changed, 46 insertions(+), 62 deletions(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index ed758b7..a8833cc 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -473,10 +473,9 @@ static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 
 static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
-		struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd,
-		unsigned int flags)
+		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	unsigned long pmd_addr = addr & PMD_MASK;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	struct device *dev = &dax_dev->dev;
 	struct dax_region *dax_region;
 	phys_addr_t phys;
@@ -508,23 +507,22 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 
 	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pmd(vma, addr, pmd, pfn,
-			flags & FAULT_FLAG_WRITE);
+	return vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
+			vmf->flags & FAULT_FLAG_WRITE);
 }
 
-static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, unsigned int flags)
+static int dax_dev_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int rc;
 	struct file *filp = vma->vm_file;
 	struct dax_dev *dax_dev = filp->private_data;
 
 	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
-			current->comm, (flags & FAULT_FLAG_WRITE)
+			current->comm, (vmf->flags & FAULT_FLAG_WRITE)
 			? "write" : "read", vma->vm_start, vma->vm_end);
 
 	rcu_read_lock();
-	rc = __dax_dev_pmd_fault(dax_dev, vma, addr, pmd, flags);
+	rc = __dax_dev_pmd_fault(dax_dev, vma, vmf);
 	rcu_read_unlock();
 
 	return rc;
diff --git a/fs/dax.c b/fs/dax.c
index 4671530..2ef7847 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1332,18 +1332,17 @@ static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
 	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)
+int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+		struct iomap_ops *ops)
 {
 	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;
+	pgoff_t max_pgoff;
 	void *entry;
 	loff_t pos;
 	int error;
@@ -1353,10 +1352,10 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	 * supposed to hold locks serializing us with truncate / punch hole so
 	 * this is a reliable test.
 	 */
-	pgoff = linear_page_index(vma, pmd_addr);
+	vmf->pgoff = linear_page_index(vma, pmd_addr);
 	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 
-	trace_dax_pmd_fault(inode, vma, address, flags, pgoff, max_pgoff, 0);
+	trace_dax_pmd_fault(inode, vma, vmf, max_pgoff, 0);
 
 	/* Fall back to PTEs if we're going to COW */
 	if (write && !(vma->vm_flags & VM_SHARED))
@@ -1368,13 +1367,13 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
 		goto fallback;
 
-	if (pgoff > max_pgoff) {
+	if (vmf->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)
+	if ((vmf->pgoff | PG_PMD_COLOUR) > max_pgoff)
 		goto fallback;
 
 	/*
@@ -1382,7 +1381,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	 * setting up a mapping, so really we're using iomap_begin() as a way
 	 * to look up our filesystem block.
 	 */
-	pos = (loff_t)pgoff << PAGE_SHIFT;
+	pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
 		goto fallback;
@@ -1396,25 +1395,21 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	 * the tree, for instance), it will return -EEXIST and we just fall
 	 * back to 4k entries.
 	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	entry = grab_mapping_entry(mapping, vmf->pgoff, RADIX_DAX_PMD);
 	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(vma, vmf->pmd, vmf,
+				vmf->address, &iomap, pos, write, &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(vma, vmf->pmd, vmf, vmf->address,
+				&iomap, &entry);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1422,7 +1417,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	}
 
  unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PMD_SIZE;
@@ -1440,12 +1435,11 @@ 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, vma, address, flags, pgoff, max_pgoff,
-			result);
+	trace_dax_pmd_fault_done(inode, vma, vmf, max_pgoff, result);
 	return result;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d663d3d..10b64ba 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -275,21 +275,20 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return result;
 }
 
-static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
+static int
+ext4_dax_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int result;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
-	bool write = flags & FAULT_FLAG_WRITE;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
 	}
 	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
-				     &ext4_iomap_ops);
+	result = dax_iomap_pmd_fault(vma, vmf, &ext4_iomap_ops);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	if (write)
 		sb_end_pagefault(sb);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 0f77519..332e194 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1432,9 +1432,7 @@ xfs_filemap_fault(
 STATIC int
 xfs_filemap_pmd_fault(
 	struct vm_area_struct	*vma,
-	unsigned long		addr,
-	pmd_t			*pmd,
-	unsigned int		flags)
+	struct vm_fault		*vmf)
 {
 	struct inode		*inode = file_inode(vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
@@ -1445,16 +1443,16 @@ xfs_filemap_pmd_fault(
 
 	trace_xfs_filemap_pmd_fault(ip);
 
-	if (flags & FAULT_FLAG_WRITE) {
+	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
 		file_update_time(vma->vm_file);
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops);
+	ret = dax_iomap_pmd_fault(vma, vmf, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
-	if (flags & FAULT_FLAG_WRITE)
+	if (vmf->flags & FAULT_FLAG_WRITE)
 		sb_end_pagefault(inode->i_sb);
 
 	return ret;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 24ad711..a829fee 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -71,16 +71,15 @@ static inline unsigned int dax_radix_order(void *entry)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops);
+int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+		struct iomap_ops *ops);
 #else
 static inline unsigned int dax_radix_order(void *entry)
 {
 	return 0;
 }
 static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
-		unsigned long address, pmd_t *pmd, unsigned int flags,
-		struct iomap_ops *ops)
+		struct vm_fault *vmf, struct iomap_ops *ops)
 {
 	return VM_FAULT_FALLBACK;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index aaf4c96..1c96128 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -347,8 +347,7 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
-	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
-						pmd_t *, unsigned int flags);
+	int (*pmd_fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
 	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index c3b0aae..a98665b 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -8,9 +8,8 @@
 
 DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
-		unsigned long address, unsigned int flags, pgoff_t pgoff,
-		pgoff_t max_pgoff, int result),
-	TP_ARGS(inode, vma, address, flags, pgoff, max_pgoff, result),
+		struct vm_fault *vmf, pgoff_t max_pgoff, int result),
+	TP_ARGS(inode, vma, vmf, max_pgoff, result),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_start)
@@ -29,9 +28,9 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 		__entry->vm_start = vma->vm_start;
 		__entry->vm_end = vma->vm_end;
 		__entry->vm_flags = vma->vm_flags;
-		__entry->address = address;
-		__entry->flags = flags;
-		__entry->pgoff = pgoff;
+		__entry->address = vmf->address;
+		__entry->flags = vmf->flags;
+		__entry->pgoff = vmf->pgoff;
 		__entry->max_pgoff = max_pgoff;
 		__entry->result = result;
 	),
@@ -54,9 +53,9 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 #define DEFINE_PMD_FAULT_EVENT(name) \
 DEFINE_EVENT(dax_pmd_fault_class, name, \
 	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
-		unsigned long address, unsigned int flags, pgoff_t pgoff, \
+		struct vm_fault *vmf, \
 		pgoff_t max_pgoff, int result), \
-	TP_ARGS(inode, vma, address, flags, pgoff, max_pgoff, result))
+	TP_ARGS(inode, vma, vmf, max_pgoff, result))
 
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
diff --git a/mm/memory.c b/mm/memory.c
index 03691d6..e648c62 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3475,8 +3475,7 @@ static int create_huge_pmd(struct vm_fault *vmf)
 	if (vma_is_anonymous(vma))
 		return do_huge_pmd_anonymous_page(vmf);
 	if (vma->vm_ops->pmd_fault)
-		return vma->vm_ops->pmd_fault(vma, vmf->address, vmf->pmd,
-				vmf->flags);
+		return vma->vm_ops->pmd_fault(vma, vmf);
 	return VM_FAULT_FALLBACK;
 }
 
@@ -3485,8 +3484,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
 	if (vmf->vma->vm_ops->pmd_fault)
-		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf->address,
-						   vmf->pmd, vmf->flags);
+		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf);
 
 	/* COW handled on pte level: split pmd */
 	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
-- 
2.7.4

[PATCH v4 7/7] mm, dax: move pmd_fault() to take only vmf parameter

[Ross Zwisler]

From: Dave Jiang <dave.jiang@intel.com>

pmd_fault() and related functions really only need the vmf parameter since
the additional parameters are all included in the vmf struct. Removing
additional parameter and simplify pmd_fault() and friends.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 drivers/dax/dax.c             | 18 +++++++--------
 fs/dax.c                      | 54 ++++++++++++++++++++-----------------------
 fs/ext4/file.c                |  8 +++----
 fs/xfs/xfs_file.c             |  7 +++---
 include/linux/dax.h           |  7 +++---
 include/linux/mm.h            |  2 +-
 include/trace/events/fs_dax.h | 54 ++++++++++++++++++++-----------------------
 mm/memory.c                   |  9 ++++----
 8 files changed, 74 insertions(+), 85 deletions(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index a8833cc..18e9875 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -472,8 +472,7 @@ static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return rc;
 }
 
-static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
-		struct vm_area_struct *vma, struct vm_fault *vmf)
+static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 {
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	struct device *dev = &dax_dev->dev;
@@ -482,7 +481,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 	pgoff_t pgoff;
 	pfn_t pfn;
 
-	if (check_vma(dax_dev, vma, __func__))
+	if (check_vma(dax_dev, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
 
 	dax_region = dax_dev->region;
@@ -497,7 +496,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 		return VM_FAULT_SIGBUS;
 	}
 
-	pgoff = linear_page_index(vma, pmd_addr);
+	pgoff = linear_page_index(vmf->vma, pmd_addr);
 	phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
 	if (phys == -1) {
 		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
@@ -507,22 +506,23 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 
 	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
+	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, pfn,
 			vmf->flags & FAULT_FLAG_WRITE);
 }
 
-static int dax_dev_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int dax_dev_pmd_fault(struct vm_fault *vmf)
 {
 	int rc;
-	struct file *filp = vma->vm_file;
+	struct file *filp = vmf->vma->vm_file;
 	struct dax_dev *dax_dev = filp->private_data;
 
 	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
 			current->comm, (vmf->flags & FAULT_FLAG_WRITE)
-			? "write" : "read", vma->vm_start, vma->vm_end);
+			? "write" : "read",
+			vmf->vma->vm_start, vmf->vma->vm_end);
 
 	rcu_read_lock();
-	rc = __dax_dev_pmd_fault(dax_dev, vma, vmf);
+	rc = __dax_dev_pmd_fault(dax_dev, vmf);
 	rcu_read_unlock();
 
 	return rc;
diff --git a/fs/dax.c b/fs/dax.c
index 2ef7847..7095602 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1248,11 +1248,10 @@ 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 = {
@@ -1279,31 +1278,30 @@ static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
 		goto fallback;
 	*entryp = ret;
 
-	trace_dax_pmd_insert_mapping(inode, vma, address, write, length,
-			dax.pfn, 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, vma, address, write,
-			length, dax.pfn, ret);
+	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;
 
-	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))
 		goto fallback;
@@ -1314,27 +1312,27 @@ static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
 		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);
 		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, vma, address, zero_page, ret);
+	trace_dax_pmd_load_hole(inode, vmf, zero_page, ret);
 	return VM_FAULT_NOPAGE;
 
 fallback:
-	trace_dax_pmd_load_hole_fallback(inode, vma, address, zero_page, ret);
+	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, struct vm_fault *vmf,
-		struct iomap_ops *ops)
+int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -1355,7 +1353,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	vmf->pgoff = linear_page_index(vma, pmd_addr);
 	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 
-	trace_dax_pmd_fault(inode, vma, vmf, max_pgoff, 0);
+	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))
@@ -1401,15 +1399,13 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
-		result = dax_pmd_insert_mapping(vma, vmf->pmd, vmf,
-				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, vmf->pmd, vmf, vmf->address,
-				&iomap, &entry);
+		result = dax_pmd_load_hole(vmf, &iomap, &entry);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1439,7 +1435,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		count_vm_event(THP_FAULT_FALLBACK);
 	}
 out:
-	trace_dax_pmd_fault_done(inode, vma, vmf, max_pgoff, result);
+	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
 	return result;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 10b64ba..75dc3dd 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -276,19 +276,19 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 
 static int
-ext4_dax_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+ext4_dax_pmd_fault(struct vm_fault *vmf)
 {
 	int result;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	if (write) {
 		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
+		file_update_time(vmf->vma->vm_file);
 	}
 	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_pmd_fault(vma, vmf, &ext4_iomap_ops);
+	result = dax_iomap_pmd_fault(vmf, &ext4_iomap_ops);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	if (write)
 		sb_end_pagefault(sb);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 332e194..02f9093 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1431,10 +1431,9 @@ xfs_filemap_fault(
  */
 STATIC int
 xfs_filemap_pmd_fault(
-	struct vm_area_struct	*vma,
 	struct vm_fault		*vmf)
 {
-	struct inode		*inode = file_inode(vma->vm_file);
+	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			ret;
 
@@ -1445,11 +1444,11 @@ xfs_filemap_pmd_fault(
 
 	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
+		file_update_time(vmf->vma->vm_file);
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_iomap_pmd_fault(vma, vmf, &xfs_iomap_ops);
+	ret = dax_iomap_pmd_fault(vmf, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (vmf->flags & FAULT_FLAG_WRITE)
diff --git a/include/linux/dax.h b/include/linux/dax.h
index a829fee..c1bd6ab 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -71,15 +71,14 @@ static inline unsigned int dax_radix_order(void *entry)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-		struct iomap_ops *ops);
+int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops);
 #else
 static inline unsigned int dax_radix_order(void *entry)
 {
 	return 0;
 }
-static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
-		struct vm_fault *vmf, struct iomap_ops *ops)
+static inline int dax_iomap_pmd_fault(struct vm_fault *vmf,
+		struct iomap_ops *ops)
 {
 	return VM_FAULT_FALLBACK;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1c96128..e9012ba 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -347,7 +347,7 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
-	int (*pmd_fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	int (*pmd_fault)(struct vm_fault *vmf);
 	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index a98665b..c566ddc 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -7,9 +7,9 @@
 #include <linux/tracepoint.h>
 
 DECLARE_EVENT_CLASS(dax_pmd_fault_class,
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
-		struct vm_fault *vmf, pgoff_t max_pgoff, int result),
-	TP_ARGS(inode, vma, vmf, max_pgoff, result),
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		pgoff_t max_pgoff, int result),
+	TP_ARGS(inode, vmf, max_pgoff, result),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_start)
@@ -25,9 +25,9 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 	TP_fast_assign(
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
-		__entry->vm_start = vma->vm_start;
-		__entry->vm_end = vma->vm_end;
-		__entry->vm_flags = vma->vm_flags;
+		__entry->vm_start = vmf->vma->vm_start;
+		__entry->vm_end = vmf->vma->vm_end;
+		__entry->vm_flags = vmf->vma->vm_flags;
 		__entry->address = vmf->address;
 		__entry->flags = vmf->flags;
 		__entry->pgoff = vmf->pgoff;
@@ -52,19 +52,18 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 
 #define DEFINE_PMD_FAULT_EVENT(name) \
 DEFINE_EVENT(dax_pmd_fault_class, name, \
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
-		struct vm_fault *vmf, \
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
 		pgoff_t max_pgoff, int result), \
-	TP_ARGS(inode, vma, vmf, max_pgoff, result))
+	TP_ARGS(inode, vmf, max_pgoff, result))
 
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
 
 DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
-		unsigned long address, struct page *zero_page,
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		struct page *zero_page,
 		void *radix_entry),
-	TP_ARGS(inode, vma, address, zero_page, radix_entry),
+	TP_ARGS(inode, vmf, zero_page, radix_entry),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_flags)
@@ -76,8 +75,8 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
 	TP_fast_assign(
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
-		__entry->vm_flags = vma->vm_flags;
-		__entry->address = address;
+		__entry->vm_flags = vmf->vma->vm_flags;
+		__entry->address = vmf->address;
 		__entry->zero_page = zero_page;
 		__entry->radix_entry = radix_entry;
 	),
@@ -95,19 +94,17 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
 
 #define DEFINE_PMD_LOAD_HOLE_EVENT(name) \
 DEFINE_EVENT(dax_pmd_load_hole_class, name, \
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
-		unsigned long address, struct page *zero_page, \
-		void *radix_entry), \
-	TP_ARGS(inode, vma, address, zero_page, radix_entry))
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
+		struct page *zero_page, void *radix_entry), \
+	TP_ARGS(inode, vmf, zero_page, radix_entry))
 
 DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole);
 DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
 
 DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
-		unsigned long address, int write, long length, pfn_t pfn,
-		void *radix_entry),
-	TP_ARGS(inode, vma, address, write, length, pfn, radix_entry),
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		long length, pfn_t pfn, void *radix_entry),
+	TP_ARGS(inode, vmf, length, pfn, radix_entry),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_flags)
@@ -121,9 +118,9 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
 	TP_fast_assign(
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
-		__entry->vm_flags = vma->vm_flags;
-		__entry->address = address;
-		__entry->write = write;
+		__entry->vm_flags = vmf->vma->vm_flags;
+		__entry->address = vmf->address;
+		__entry->write = vmf->flags & FAULT_FLAG_WRITE;
 		__entry->length = length;
 		__entry->pfn_val = pfn.val;
 		__entry->radix_entry = radix_entry;
@@ -146,10 +143,9 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
 
 #define DEFINE_PMD_INSERT_MAPPING_EVENT(name) \
 DEFINE_EVENT(dax_pmd_insert_mapping_class, name, \
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
-		unsigned long address, int write, long length, pfn_t pfn, \
-		void *radix_entry), \
-	TP_ARGS(inode, vma, address, write, length, pfn, radix_entry))
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
+		long length, pfn_t pfn, void *radix_entry), \
+	TP_ARGS(inode, vmf, length, pfn, radix_entry))
 
 DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping);
 DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping_fallback);
diff --git a/mm/memory.c b/mm/memory.c
index e648c62..6012a05 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3471,11 +3471,10 @@ static int do_numa_page(struct vm_fault *vmf)
 
 static int create_huge_pmd(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = vmf->vma;
-	if (vma_is_anonymous(vma))
+	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_anonymous_page(vmf);
-	if (vma->vm_ops->pmd_fault)
-		return vma->vm_ops->pmd_fault(vma, vmf);
+	if (vmf->vma->vm_ops->pmd_fault)
+		return vmf->vma->vm_ops->pmd_fault(vmf);
 	return VM_FAULT_FALLBACK;
 }
 
@@ -3484,7 +3483,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
 	if (vmf->vma->vm_ops->pmd_fault)
-		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf);
+		return vmf->vma->vm_ops->pmd_fault(vmf);
 
 	/* COW handled on pte level: split pmd */
 	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
-- 
2.7.4