Merge tag 'for-5.20/io_uring-2022-07-29' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:

 - As per (valid) complaint in the last merge window, fs/io_uring.c has
   grown quite large these days. io_uring isn't really tied to fs
   either, as it supports a wide variety of functionality outside of
   that.

   Move the code to io_uring/ and split it into files that either
   implement a specific request type, and split some code into helpers
   as well. The code is organized a lot better like this, and io_uring.c
   is now < 4K LOC (me).

 - Deprecate the epoll_ctl opcode. It'll still work, just trigger a
   warning once if used. If we don't get any complaints on this, and I
   don't expect any, then we can fully remove it in a future release
   (me).

 - Improve the cancel hash locking (Hao)

 - kbuf cleanups (Hao)

 - Efficiency improvements to the task_work handling (Dylan, Pavel)

 - Provided buffer improvements (Dylan)

 - Add support for recv/recvmsg multishot support. This is similar to
   the accept (or poll) support for have for multishot, where a single
   SQE can trigger everytime data is received. For applications that
   expect to do more than a few receives on an instantiated socket, this
   greatly improves efficiency (Dylan).

 - Efficiency improvements for poll handling (Pavel)

 - Poll cancelation improvements (Pavel)

 - Allow specifiying a range for direct descriptor allocations (Pavel)

 - Cleanup the cqe32 handling (Pavel)

 - Move io_uring types to greatly cleanup the tracing (Pavel)

 - Tons of great code cleanups and improvements (Pavel)

 - Add a way to do sync cancelations rather than through the sqe -> cqe
   interface, as that's a lot easier to use for some use cases (me).

 - Add support to IORING_OP_MSG_RING for sending direct descriptors to a
   different ring. This avoids the usually problematic SCM case, as we
   disallow those. (me)

 - Make the per-command alloc cache we use for apoll generic, place
   limits on it, and use it for netmsg as well (me).

 - Various cleanups (me, Michal, Gustavo, Uros)

* tag 'for-5.20/io_uring-2022-07-29' of git://git.kernel.dk/linux-block: (172 commits)
  io_uring: ensure REQ_F_ISREG is set async offload
  net: fix compat pointer in get_compat_msghdr()
  io_uring: Don't require reinitable percpu_ref
  io_uring: fix types in io_recvmsg_multishot_overflow
  io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
  io_uring: support multishot in recvmsg
  net: copy from user before calling __get_compat_msghdr
  net: copy from user before calling __copy_msghdr
  io_uring: support 0 length iov in buffer select in compat
  io_uring: fix multishot ending when not polled
  io_uring: add netmsg cache
  io_uring: impose max limit on apoll cache
  io_uring: add abstraction around apoll cache
  io_uring: move apoll cache to poll.c
  io_uring: consolidate hash_locked io-wq handling
  io_uring: clear REQ_F_HASH_LOCKED on hash removal
  io_uring: don't race double poll setting REQ_F_ASYNC_DATA
  io_uring: don't miss setting REQ_F_DOUBLE_POLL
  io_uring: disable multishot recvmsg
  io_uring: only trace one of complete or overflow
  ...

1 files changed, 88 insertions, 0 deletions

diff --git a/io_uring/filetable.h b/io_uring/filetable.h
new file mode 100644
index 000000000000..ff3a712e11bf
--- /dev/null
+++ b/io_uring/filetable.h
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_FILE_TABLE_H
+#define IOU_FILE_TABLE_H
+
+#include <linux/file.h>
+#include <linux/io_uring_types.h>
+
+/*
+ * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0
+ * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we
+ * can't safely always dereference the file when the task has exited and ring
+ * cleanup is done. If a file is tracked and part of SCM, then unix gc on
+ * process exit may reap it before __io_sqe_files_unregister() is run.
+ */
+#define FFS_NOWAIT		0x1UL
+#define FFS_ISREG		0x2UL
+#if defined(CONFIG_64BIT)
+#define FFS_SCM			0x4UL
+#else
+#define IO_URING_SCM_ALL
+#define FFS_SCM			0x0UL
+#endif
+#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG|FFS_SCM)
+
+bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files);
+void io_free_file_tables(struct io_file_table *table);
+
+int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
+			struct file *file, unsigned int file_slot);
+int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
+				unsigned int file_slot);
+int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset);
+
+int io_register_file_alloc_range(struct io_ring_ctx *ctx,
+				 struct io_uring_file_index_range __user *arg);
+
+unsigned int io_file_get_flags(struct file *file);
+
+static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
+{
+	__clear_bit(bit, table->bitmap);
+	table->alloc_hint = bit;
+}
+
+static inline void io_file_bitmap_set(struct io_file_table *table, int bit)
+{
+	WARN_ON_ONCE(test_bit(bit, table->bitmap));
+	__set_bit(bit, table->bitmap);
+	table->alloc_hint = bit + 1;
+}
+
+static inline struct io_fixed_file *
+io_fixed_file_slot(struct io_file_table *table, unsigned i)
+{
+	return &table->files[i];
+}
+
+static inline struct file *io_file_from_index(struct io_file_table *table,
+					      int index)
+{
+	struct io_fixed_file *slot = io_fixed_file_slot(table, index);
+
+	return (struct file *) (slot->file_ptr & FFS_MASK);
+}
+
+static inline void io_fixed_file_set(struct io_fixed_file *file_slot,
+				     struct file *file)
+{
+	unsigned long file_ptr = (unsigned long) file;
+
+	file_ptr |= io_file_get_flags(file);
+	file_slot->file_ptr = file_ptr;
+}
+
+static inline void io_reset_alloc_hint(struct io_ring_ctx *ctx)
+{
+	ctx->file_table.alloc_hint = ctx->file_alloc_start;
+}
+
+static inline void io_file_table_set_alloc_range(struct io_ring_ctx *ctx,
+						 unsigned off, unsigned len)
+{
+	ctx->file_alloc_start = off;
+	ctx->file_alloc_end = off + len;
+	io_reset_alloc_hint(ctx);
+}
+
+#endif