5 files changed, 389 insertions, 5 deletions

diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index c3e201025ef0..0782ff3c2273 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -622,9 +622,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp)
         if (xen_store_evtchn == 0)
                 return -ENOENT;
 
-        nonseekable_open(inode, filp);
-
-        filp->f_mode &= ~FMODE_ATOMIC_POS; /* cdev-style semantics */
+        stream_open(inode, filp);
 
         u = kzalloc(sizeof(*u), GFP_KERNEL);
         if (u == NULL)
diff --git a/fs/open.c b/fs/open.c
index f1c2f855fd43..a00350018a47 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1215,3 +1215,21 @@ int nonseekable_open(struct inode *inode, struct file *filp)
 }
 
 EXPORT_SYMBOL(nonseekable_open);
+
+/*
+ * stream_open is used by subsystems that want stream-like file descriptors.
+ * Such file descriptors are not seekable and don't have notion of position
+ * (file.f_pos is always 0). Contrary to file descriptors of other regular
+ * files, .read() and .write() can run simultaneously.
+ *
+ * stream_open never fails and is marked to return int so that it could be
+ * directly used as file_operations.open .
+ */
+int stream_open(struct inode *inode, struct file *filp)
+{
+        filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS);
+        filp->f_mode |= FMODE_STREAM;
+        return 0;
+}
+
+EXPORT_SYMBOL(stream_open);
diff --git a/fs/read_write.c b/fs/read_write.c
index 177ccc3d405a..61b43ad7608e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -560,12 +560,13 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
 
 static inline loff_t file_pos_read(struct file *file)
 {
-        return file->f_pos;
+        return file->f_mode & FMODE_STREAM ? 0 : file->f_pos;
 }
 
 static inline void file_pos_write(struct file *file, loff_t pos)
 {
-        file->f_pos = pos;
+        if ((file->f_mode & FMODE_STREAM) == 0)
+                file->f_pos = pos;
 }
 
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8b42df09b04c..dd28e7679089 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -158,6 +158,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_OPENED            ((__force fmode_t)0x80000)
 #define FMODE_CREATED           ((__force fmode_t)0x100000)
 
+/* File is stream-like */
+#define FMODE_STREAM            ((__force fmode_t)0x200000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY          ((__force fmode_t)0x4000000)
 
@@ -3074,6 +3077,7 @@ extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);
 extern loff_t no_seek_end_llseek(struct file *, loff_t, int);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
+extern int stream_open(struct inode * inode, struct file * filp);
 
 #ifdef CONFIG_BLOCK
 typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
diff --git a/scripts/coccinelle/api/stream_open.cocci b/scripts/coccinelle/api/stream_open.cocci
new file mode 100644
index 000000000000..350145da7669
--- /dev/null
+++ b/scripts/coccinelle/api/stream_open.cocci
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0
+// Author: Kirill Smelkov (kirr@nexedi.com)
+//
+// Search for stream-like files that are using nonseekable_open and convert
+// them to stream_open. A stream-like file is a file that does not use ppos in
+// its read and write. Rationale for the conversion is to avoid deadlock in
+// between read and write.
+
+virtual report
+virtual patch
+virtual explain  // explain decisions in the patch (SPFLAGS="-D explain")
+
+// stream-like reader & writer - ones that do not depend on f_pos.
+@ stream_reader @
+identifier readstream, ppos;
+identifier f, buf, len;
+type loff_t;
+@@
+  ssize_t readstream(struct file *f, char *buf, size_t len, loff_t *ppos)
+  {
+    ... when != ppos
+  }
+
+@ stream_writer @
+identifier writestream, ppos;
+identifier f, buf, len;
+type loff_t;
+@@
+  ssize_t writestream(struct file *f, const char *buf, size_t len, loff_t *ppos)
+  {
+    ... when != ppos
+  }
+
+
+// a function that blocks
+@ blocks @
+identifier block_f;
+identifier wait_event =~ "^wait_event_.*";
+@@
+  block_f(...) {
+    ... when exists
+    wait_event(...)
+    ... when exists
+  }
+
+// stream_reader that can block inside.
+//
+// XXX wait_* can be called not directly from current function (e.g. func -> f -> g -> wait())
+// XXX currently reader_blocks supports only direct and 1-level indirect cases.
+@ reader_blocks_direct @
+identifier stream_reader.readstream;
+identifier wait_event =~ "^wait_event_.*";
+@@
+  readstream(...)
+  {
+    ... when exists
+    wait_event(...)
+    ... when exists
+  }
+
+@ reader_blocks_1 @
+identifier stream_reader.readstream;
+identifier blocks.block_f;
+@@
+  readstream(...)
+  {
+    ... when exists
+    block_f(...)
+    ... when exists
+  }
+
+@ reader_blocks depends on reader_blocks_direct || reader_blocks_1 @
+identifier stream_reader.readstream;
+@@
+  readstream(...) {
+    ...
+  }
+
+
+// file_operations + whether they have _any_ .read, .write, .llseek ... at all.
+//
+// XXX add support for file_operations xxx[N] = ...     (sound/core/pcm_native.c)
+@ fops0 @
+identifier fops;
+@@
+  struct file_operations fops = {
+    ...
+  };
+
+@ has_read @
+identifier fops0.fops;
+identifier read_f;
+@@
+  struct file_operations fops = {
+    .read = read_f,
+  };
+
+@ has_read_iter @
+identifier fops0.fops;
+identifier read_iter_f;
+@@
+  struct file_operations fops = {
+    .read_iter = read_iter_f,
+  };
+
+@ has_write @
+identifier fops0.fops;
+identifier write_f;
+@@
+  struct file_operations fops = {
+    .write = write_f,
+  };
+
+@ has_write_iter @
+identifier fops0.fops;
+identifier write_iter_f;
+@@
+  struct file_operations fops = {
+    .write_iter = write_iter_f,
+  };
+
+@ has_llseek @
+identifier fops0.fops;
+identifier llseek_f;
+@@
+  struct file_operations fops = {
+    .llseek = llseek_f,
+  };
+
+@ has_no_llseek @
+identifier fops0.fops;
+@@
+  struct file_operations fops = {
+    .llseek = no_llseek,
+  };
+
+@ has_mmap @
+identifier fops0.fops;
+identifier mmap_f;
+@@
+  struct file_operations fops = {
+    .mmap = mmap_f,
+  };
+
+@ has_copy_file_range @
+identifier fops0.fops;
+identifier copy_file_range_f;
+@@
+  struct file_operations fops = {
+    .copy_file_range = copy_file_range_f,
+  };
+
+@ has_remap_file_range @
+identifier fops0.fops;
+identifier remap_file_range_f;
+@@
+  struct file_operations fops = {
+    .remap_file_range = remap_file_range_f,
+  };
+
+@ has_splice_read @
+identifier fops0.fops;
+identifier splice_read_f;
+@@
+  struct file_operations fops = {
+    .splice_read = splice_read_f,
+  };
+
+@ has_splice_write @
+identifier fops0.fops;
+identifier splice_write_f;
+@@
+  struct file_operations fops = {
+    .splice_write = splice_write_f,
+  };
+
+
+// file_operations that is candidate for stream_open conversion - it does not
+// use mmap and other methods that assume @offset access to file.
+//
+// XXX for simplicity require no .{read/write}_iter and no .splice_{read/write} for now.
+// XXX maybe_steam.fops cannot be used in other rules - it gives "bad rule maybe_stream or bad variable fops".
+@ maybe_stream depends on (!has_llseek || has_no_llseek) && !has_mmap && !has_copy_file_range && !has_remap_file_range && !has_read_iter && !has_write_iter && !has_splice_read && !has_splice_write @
+identifier fops0.fops;
+@@
+  struct file_operations fops = {
+  };
+
+
+// ---- conversions ----
+
+// XXX .open = nonseekable_open -> .open = stream_open
+// XXX .open = func -> openfunc -> nonseekable_open
+
+// read & write
+//
+// if both are used in the same file_operations together with an opener -
+// under that conditions we can use stream_open instead of nonseekable_open.
+@ fops_rw depends on maybe_stream @
+identifier fops0.fops, openfunc;
+identifier stream_reader.readstream;
+identifier stream_writer.writestream;
+@@
+  struct file_operations fops = {
+      .open  = openfunc,
+      .read  = readstream,
+      .write = writestream,
+  };
+
+@ report_rw depends on report @
+identifier fops_rw.openfunc;
+position p1;
+@@
+  openfunc(...) {
+    <...
+     nonseekable_open@p1
+    ...>
+  }
+
+@ script:python depends on report && reader_blocks @
+fops << fops0.fops;
+p << report_rw.p1;
+@@
+coccilib.report.print_report(p[0],
+  "ERROR: %s: .read() can deadlock .write(); change nonseekable_open -> stream_open to fix." % (fops,))
+
+@ script:python depends on report && !reader_blocks @
+fops << fops0.fops;
+p << report_rw.p1;
+@@
+coccilib.report.print_report(p[0],
+  "WARNING: %s: .read() and .write() have stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+
+@ explain_rw_deadlocked depends on explain && reader_blocks @
+identifier fops_rw.openfunc;
+@@
+  openfunc(...) {
+    <...
+-    nonseekable_open
++    nonseekable_open /* read & write (was deadlock) */
+    ...>
+  }
+
+
+@ explain_rw_nodeadlock depends on explain && !reader_blocks @
+identifier fops_rw.openfunc;
+@@
+  openfunc(...) {
+    <...
+-    nonseekable_open
++    nonseekable_open /* read & write (no direct deadlock) */
+    ...>
+  }
+
+@ patch_rw depends on patch @
+identifier fops_rw.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   stream_open
+    ...>
+  }
+
+
+// read, but not write
+@ fops_r depends on maybe_stream && !has_write @
+identifier fops0.fops, openfunc;
+identifier stream_reader.readstream;
+@@
+  struct file_operations fops = {
+      .open  = openfunc,
+      .read  = readstream,
+  };
+
+@ report_r depends on report @
+identifier fops_r.openfunc;
+position p1;
+@@
+  openfunc(...) {
+    <...
+    nonseekable_open@p1
+    ...>
+  }
+
+@ script:python depends on report @
+fops << fops0.fops;
+p << report_r.p1;
+@@
+coccilib.report.print_report(p[0],
+  "WARNING: %s: .read() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+@ explain_r depends on explain @
+identifier fops_r.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   nonseekable_open /* read only */
+    ...>
+  }
+
+@ patch_r depends on patch @
+identifier fops_r.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   stream_open
+    ...>
+  }
+
+
+// write, but not read
+@ fops_w depends on maybe_stream && !has_read @
+identifier fops0.fops, openfunc;
+identifier stream_writer.writestream;
+@@
+  struct file_operations fops = {
+      .open  = openfunc,
+      .write = writestream,
+  };
+
+@ report_w depends on report @
+identifier fops_w.openfunc;
+position p1;
+@@
+  openfunc(...) {
+    <...
+    nonseekable_open@p1
+    ...>
+  }
+
+@ script:python depends on report @
+fops << fops0.fops;
+p << report_w.p1;
+@@
+coccilib.report.print_report(p[0],
+  "WARNING: %s: .write() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+@ explain_w depends on explain @
+identifier fops_w.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   nonseekable_open /* write only */
+    ...>
+  }
+
+@ patch_w depends on patch @
+identifier fops_w.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   stream_open
+    ...>
+  }
+
+
+// no read, no write - don't change anything