Adding Direct IO Support

Adding O_DIRECT support to ZFS to bypass the ARC for writes/reads.

O_DIRECT support in ZFS will always ensure there is coherency between
buffered and O_DIRECT IO requests. This ensures that all IO requests,
whether buffered or direct, will see the same file contents at all
times. Just as in other FS's , O_DIRECT does not imply O_SYNC. While
data is written directly to VDEV disks, metadata will not be synced
until the associated  TXG is synced.
For both O_DIRECT read and write request the offset and request sizes,
at a minimum, must be PAGE_SIZE aligned. In the event they are not,
then EINVAL is returned unless the direct property is set to always (see
below).

For O_DIRECT writes:
The request also must be block aligned (recordsize) or the write
request will take the normal (buffered) write path. In the event that
request is block aligned and a cached copy of the buffer in the ARC,
then it will be discarded from the ARC forcing all further reads to
retrieve the data from disk.

For O_DIRECT reads:
The only alignment restrictions are PAGE_SIZE alignment. In the event
that the requested data is in buffered (in the ARC) it will just be
copied from the ARC into the user buffer.

For both O_DIRECT writes and reads the O_DIRECT flag will be ignored in
the event that file contents are mmap'ed. In this case, all requests
that are at least PAGE_SIZE aligned will just fall back to the buffered
paths. If the request however is not PAGE_SIZE aligned, EINVAL will
be returned as always regardless if the file's contents are mmap'ed.

Since O_DIRECT writes go through the normal ZIO pipeline, the
following operations are supported just as with normal buffered writes:
Checksum
Compression
Encryption
Erasure Coding
There is one caveat for the data integrity of O_DIRECT writes that is
distinct for each of the OS's supported by ZFS.
FreeBSD - FreeBSD is able to place user pages under write protection so
          any data in the user buffers and written directly down to the
	  VDEV disks is guaranteed to not change. There is no concern
	  with data integrity and O_DIRECT writes.
Linux - Linux is not able to place anonymous user pages under write
        protection. Because of this, if the user decides to manipulate
	the page contents while the write operation is occurring, data
	integrity can not be guaranteed. However, there is a module
	parameter `zfs_vdev_direct_write_verify` that controls the
	if a O_DIRECT writes that can occur to a top-level VDEV before
	a checksum verify is run before the contents of the I/O buffer
        are committed to disk. In the event of a checksum verification
	failure the write will return EIO. The number of O_DIRECT write
	checksum verification errors can be observed by doing
	`zpool status -d`, which will list all verification errors that
	have occurred on a top-level VDEV. Along with `zpool status`, a
	ZED event will be issues as `dio_verify` when a checksum
	verification error occurs.

ZVOLs and dedup is not currently supported with Direct I/O.

A new dataset property `direct` has been added with the following 3
allowable values:
disabled - Accepts O_DIRECT flag, but silently ignores it and treats
	   the request as a buffered IO request.
standard - Follows the alignment restrictions  outlined above for
	   write/read IO requests when the O_DIRECT flag is used.
always   - Treats every write/read IO request as though it passed
           O_DIRECT and will do O_DIRECT if the alignment restrictions
	   are met otherwise will redirect through the ARC. This
	   property will not allow a request to fail.

There is also a module parameter zfs_dio_enabled that can be used to
force all reads and writes through the ARC. By setting this module
parameter to 0, it mimics as if the  direct dataset property is set to
disabled.

Reviewed-by: Brian Behlendorf <behlendorf@llnl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Atkinson <batkinson@lanl.gov>
Co-authored-by: Mark Maybee <mark.maybee@delphix.com>
Co-authored-by: Matt Macy <mmacy@FreeBSD.org>
Co-authored-by: Brian Behlendorf <behlendorf@llnl.gov>
Closes #10018

include/sys/dmu.h

@@ -525,6 +525,7 @@ void dmu_redact(objset_t *os, uint64_t object, uint64_t offset, uint64_t size,
 #define	WP_NOFILL	0x1
 #define	WP_DMU_SYNC	0x2
 #define	WP_SPILL	0x4
+#define	WP_DIRECT_WR	0x8
 
 void dmu_write_policy(objset_t *os, dnode_t *dn, int level, int wp,
     struct zio_prop *zp);
@@ -589,6 +590,7 @@ int dmu_buf_hold_array_by_dnode(dnode_t *dn, uint64_t offset,
     dmu_buf_t ***dbpp, uint32_t flags);
 int dmu_buf_hold_noread_by_dnode(dnode_t *dn, uint64_t offset, const void *tag,
     dmu_buf_t **dbp);
+
 /*
  * Add a reference to a dmu buffer that has already been held via
  * dmu_buf_hold() in the current context.
@@ -873,16 +875,20 @@ int dmu_free_long_object(objset_t *os, uint64_t object);
 #define	DMU_READ_PREFETCH	0 /* prefetch */
 #define	DMU_READ_NO_PREFETCH	1 /* don't prefetch */
 #define	DMU_READ_NO_DECRYPT	2 /* don't decrypt */
+#define	DMU_DIRECTIO		4 /* use Direct I/O */
+
 int dmu_read(objset_t *os, uint64_t object, uint64_t offset, uint64_t size,
-	void *buf, uint32_t flags);
+    void *buf, uint32_t flags);
 int dmu_read_by_dnode(dnode_t *dn, uint64_t offset, uint64_t size, void *buf,
     uint32_t flags);
 void dmu_write(objset_t *os, uint64_t object, uint64_t offset, uint64_t size,
-	const void *buf, dmu_tx_t *tx);
-void dmu_write_by_dnode(dnode_t *dn, uint64_t offset, uint64_t size,
     const void *buf, dmu_tx_t *tx);
+int dmu_write_by_dnode(dnode_t *dn, uint64_t offset, uint64_t size,
+    const void *buf, dmu_tx_t *tx);
+int dmu_write_by_dnode_flags(dnode_t *dn, uint64_t offset, uint64_t size,
+    const void *buf, dmu_tx_t *tx, uint32_t flags);
 void dmu_prealloc(objset_t *os, uint64_t object, uint64_t offset, uint64_t size,
-	dmu_tx_t *tx);
+    dmu_tx_t *tx);
 #ifdef _KERNEL
 int dmu_read_uio(objset_t *os, uint64_t object, zfs_uio_t *uio, uint64_t size);
 int dmu_read_uio_dbuf(dmu_buf_t *zdb, zfs_uio_t *uio, uint64_t size);