Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block layer patches:

- qcow2: Use worker threads for compression to improve performance of
  'qemu-img convert -W' and compressed backup jobs
- blklogwrites: New filter driver to log write requests to an image in
  the dm-log-writes format
- file-posix: Fix image locking during image creation
- crypto: Fix memory leak in error path
- Error out instead of silently truncating node names

# gpg: Signature made Thu 05 Jul 2018 11:24:33 BST
# gpg:                using RSA key 7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream:
  file-posix: Unlock FD after creation
  file-posix: Fix creation locking
  block/blklogwrites: Add an option for the update interval of the log superblock
  block/blklogwrites: Add an option for appending to an old log
  block/blklogwrites: Change log_sector_size from int64_t to uint64_t
  block/crypto: Fix memory leak in create error path
  block: Don't silently truncate node names
  block: Add blklogwrites
  block: Move two block permission constants to the relevant enum
  qcow2: add compress threads
  qcow2: refactor data compression
  qemu-img: allow compressed not-in-order writes

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

MAINTAINERS

@@ -2052,6 +2052,12 @@ S: Supported
 F: block/quorum.c
 L: qemu-block@nongnu.org
 
+blklogwrites
+M: Ari Sundholm <ari@tuxera.com>
+L: qemu-block@nongnu.org
+S: Supported
+F: block/blklogwrites.c
+
 blkverify
 M: Stefan Hajnoczi <stefanha@redhat.com>
 L: qemu-block@nongnu.org

block.c

@@ -1156,6 +1156,12 @@ static void bdrv_assign_node_name(BlockDriverState *bs,
         goto out;
     }
 
+    /* Make sure that the node name isn't truncated */
+    if (strlen(node_name) >= sizeof(bs->node_name)) {
+        error_setg(errp, "Node name too long");
+        goto out;
+    }
+
     /* copy node name into the bs and insert it into the graph list */
     pstrcpy(bs->node_name, sizeof(bs->node_name), node_name);
     QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs, node_list);
@@ -1948,12 +1954,6 @@ int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
     return 0;
 }
 
-#define DEFAULT_PERM_PASSTHROUGH (BLK_PERM_CONSISTENT_READ \
-                                 | BLK_PERM_WRITE \
-                                 | BLK_PERM_WRITE_UNCHANGED \
-                                 | BLK_PERM_RESIZE)
-#define DEFAULT_PERM_UNCHANGED (BLK_PERM_ALL & ~DEFAULT_PERM_PASSTHROUGH)
-
 void bdrv_filter_default_perms(BlockDriverState *bs, BdrvChild *c,
                                const BdrvChildRole *role,
                                BlockReopenQueue *reopen_queue,

block/Makefile.objs

@@ -5,6 +5,7 @@ block-obj-y += qed-check.o
 block-obj-y += vhdx.o vhdx-endian.o vhdx-log.o
 block-obj-y += quorum.o
 block-obj-y += parallels.o blkdebug.o blkverify.o blkreplay.o
+block-obj-y += blklogwrites.o
 block-obj-y += block-backend.o snapshot.o qapi.o
 block-obj-$(CONFIG_WIN32) += file-win32.o win32-aio.o
 block-obj-$(CONFIG_POSIX) += file-posix.o

block/crypto.c

@@ -551,7 +551,7 @@ static int coroutine_fn block_crypto_co_create_opts_luks(const char *filename,
     /* Create protocol layer */
     ret = bdrv_create_file(filename, opts, errp);
     if (ret < 0) {
-        return ret;
+        goto fail;
     }
 
     bs = bdrv_open(filename, NULL, NULL,

block/file-posix.c

@@ -2111,8 +2111,9 @@ static int coroutine_fn
 raw_co_create(BlockdevCreateOptions *options, Error **errp)
 {
     BlockdevCreateOptionsFile *file_opts;
+    Error *local_err = NULL;
     int fd;
-    int perm, shared;
+    uint64_t perm, shared;
     int result = 0;
 
     /* Validate options and set default values */
@@ -2148,7 +2149,7 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
     shared = BLK_PERM_ALL & ~BLK_PERM_RESIZE;
 
     /* Step one: Take locks */
-    result = raw_apply_lock_bytes(fd, perm, shared, false, errp);
+    result = raw_apply_lock_bytes(fd, perm, ~shared, false, errp);
     if (result < 0) {
         goto out_close;
     }
@@ -2156,13 +2157,13 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
     /* Step two: Check that nobody else has taken conflicting locks */
     result = raw_check_lock_bytes(fd, perm, shared, errp);
     if (result < 0) {
-        goto out_close;
+        goto out_unlock;
     }
 
     /* Clear the file by truncating it to 0 */
     result = raw_regular_truncate(NULL, fd, 0, PREALLOC_MODE_OFF, errp);
     if (result < 0) {
-        goto out_close;
+        goto out_unlock;
     }
 
     if (file_opts->nocow) {
@@ -2185,7 +2186,17 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
     result = raw_regular_truncate(NULL, fd, file_opts->size,
                                   file_opts->preallocation, errp);
     if (result < 0) {
-        goto out_close;
+        goto out_unlock;
+    }
+
+out_unlock:
+    raw_apply_lock_bytes(fd, 0, 0, true, &local_err);
+    if (local_err) {
+        /* The above call should not fail, and if it does, that does
+         * not mean the whole creation operation has failed.  So
+         * report it the user for their convenience, but do not report
+         * it to the caller. */
+        error_report_err(local_err);
     }
 
 out_close:

block/qcow2.c

@@ -23,11 +23,14 @@
  */
 
 #include "qemu/osdep.h"
+
+#define ZLIB_CONST
+#include <zlib.h>
+
 #include "block/block_int.h"
 #include "block/qdict.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
-#include <zlib.h>
 #include "qcow2.h"
 #include "qemu/error-report.h"
 #include "qapi/error.h"
@@ -41,6 +44,7 @@
 #include "qapi/qobject-input-visitor.h"
 #include "qapi/qapi-visit-block-core.h"
 #include "crypto.h"
+#include "block/thread-pool.h"
 
 /*
   Differences with QCOW:
@@ -1541,6 +1545,9 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options,
         qcow2_check_refcounts(bs, &result, 0);
     }
 #endif
+
+    qemu_co_queue_init(&s->compress_wait_queue);
+
     return ret;
 
  fail:
@@ -3650,6 +3657,104 @@ fail:
     return ret;
 }
 
+/*
+ * qcow2_compress()
+ *
+ * @dest - destination buffer, at least of @size-1 bytes
+ * @src - source buffer, @size bytes
+ *
+ * Returns: compressed size on success
+ *          -1 if compression is inefficient
+ *          -2 on any other error
+ */
+static ssize_t qcow2_compress(void *dest, const void *src, size_t size)
+{
+    ssize_t ret;
+    z_stream strm;
+
+    /* best compression, small window, no zlib header */
+    memset(&strm, 0, sizeof(strm));
+    ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION, Z_DEFLATED,
+                       -12, 9, Z_DEFAULT_STRATEGY);
+    if (ret != 0) {
+        return -2;
+    }
+
+    /* strm.next_in is not const in old zlib versions, such as those used on
+     * OpenBSD/NetBSD, so cast the const away */
+    strm.avail_in = size;
+    strm.next_in = (void *) src;
+    strm.avail_out = size - 1;
+    strm.next_out = dest;
+
+    ret = deflate(&strm, Z_FINISH);
+    if (ret == Z_STREAM_END) {
+        ret = size - 1 - strm.avail_out;
+    } else {
+        ret = (ret == Z_OK ? -1 : -2);
+    }
+
+    deflateEnd(&strm);
+
+    return ret;
+}
+
+#define MAX_COMPRESS_THREADS 4
+
+typedef struct Qcow2CompressData {
+    void *dest;
+    const void *src;
+    size_t size;
+    ssize_t ret;
+} Qcow2CompressData;
+
+static int qcow2_compress_pool_func(void *opaque)
+{
+    Qcow2CompressData *data = opaque;
+
+    data->ret = qcow2_compress(data->dest, data->src, data->size);
+
+    return 0;
+}
+
+static void qcow2_compress_complete(void *opaque, int ret)
+{
+    qemu_coroutine_enter(opaque);
+}
+
+/* See qcow2_compress definition for parameters description */
+static ssize_t qcow2_co_compress(BlockDriverState *bs,
+                                 void *dest, const void *src, size_t size)
+{
+    BDRVQcow2State *s = bs->opaque;
+    BlockAIOCB *acb;
+    ThreadPool *pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
+    Qcow2CompressData arg = {
+        .dest = dest,
+        .src = src,
+        .size = size,
+    };
+
+    while (s->nb_compress_threads >= MAX_COMPRESS_THREADS) {
+        qemu_co_queue_wait(&s->compress_wait_queue, NULL);
+    }
+
+    s->nb_compress_threads++;
+    acb = thread_pool_submit_aio(pool, qcow2_compress_pool_func, &arg,
+                                 qcow2_compress_complete,
+                                 qemu_coroutine_self());
+
+    if (!acb) {
+        s->nb_compress_threads--;
+        return -EINVAL;
+    }
+    qemu_coroutine_yield();
+    s->nb_compress_threads--;
+    qemu_co_queue_next(&s->compress_wait_queue);
+
+    return arg.ret;
+}
+
 /* XXX: put compressed sectors first, then all the cluster aligned
    tables to avoid losing bytes in alignment */
 static coroutine_fn int
@@ -3659,8 +3764,8 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
     BDRVQcow2State *s = bs->opaque;
     QEMUIOVector hd_qiov;
     struct iovec iov;
-    z_stream strm;
-    int ret, out_len;
+    int ret;
+    size_t out_len;
     uint8_t *buf, *out_buf;
     int64_t cluster_offset;
 
@@ -3694,32 +3799,11 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
 
     out_buf = g_malloc(s->cluster_size);
 
-    /* best compression, small window, no zlib header */
-    memset(&strm, 0, sizeof(strm));
-    ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION,
-                       Z_DEFLATED, -12,
-                       9, Z_DEFAULT_STRATEGY);
-    if (ret != 0) {
+    out_len = qcow2_co_compress(bs, out_buf, buf, s->cluster_size);
+    if (out_len == -2) {
         ret = -EINVAL;
         goto fail;
-    }
-
-    strm.avail_in = s->cluster_size;
-    strm.next_in = (uint8_t *)buf;
-    strm.avail_out = s->cluster_size;
-    strm.next_out = out_buf;
-
-    ret = deflate(&strm, Z_FINISH);
-    if (ret != Z_STREAM_END && ret != Z_OK) {
-        deflateEnd(&strm);
-        ret = -EINVAL;
-        goto fail;
-    }
-    out_len = strm.next_out - out_buf;
-
-    deflateEnd(&strm);
-
-    if (ret != Z_STREAM_END || out_len >= s->cluster_size) {
+    } else if (out_len == -1) {
         /* could not compress: write normal cluster */
         ret = qcow2_co_pwritev(bs, offset, bytes, qiov, 0);
         if (ret < 0) {

block/qcow2.h

@@ -326,6 +326,9 @@ typedef struct BDRVQcow2State {
      * override) */
     char *image_backing_file;
     char *image_backing_format;
+
+    CoQueue compress_wait_queue;
+    int nb_compress_threads;
 } BDRVQcow2State;
 
 typedef struct Qcow2COWRegion {

include/block/block.h

@@ -225,6 +225,13 @@ enum {
     BLK_PERM_GRAPH_MOD          = 0x10,
 
     BLK_PERM_ALL                = 0x1f,
+
+    DEFAULT_PERM_PASSTHROUGH    = BLK_PERM_CONSISTENT_READ
+                                 | BLK_PERM_WRITE
+                                 | BLK_PERM_WRITE_UNCHANGED
+                                 | BLK_PERM_RESIZE,
+
+    DEFAULT_PERM_UNCHANGED      = BLK_PERM_ALL & ~DEFAULT_PERM_PASSTHROUGH,
 };
 
 char *bdrv_perm_names(uint64_t perm);

qapi/block-core.json

@@ -2533,16 +2533,17 @@
 # @throttle: Since 2.11
 # @nvme: Since 2.12
 # @copy-on-read: Since 3.0
+# @blklogwrites: Since 3.0
 #
 # Since: 2.9
 ##
 { 'enum': 'BlockdevDriver',
-  'data': [ 'blkdebug', 'blkverify', 'bochs', 'cloop', 'copy-on-read',
-            'dmg', 'file', 'ftp', 'ftps', 'gluster', 'host_cdrom',
-            'host_device', 'http', 'https', 'iscsi', 'luks', 'nbd', 'nfs',
-            'null-aio', 'null-co', 'nvme', 'parallels', 'qcow', 'qcow2', 'qed',
-            'quorum', 'raw', 'rbd', 'replication', 'sheepdog', 'ssh',
-            'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
+  'data': [ 'blkdebug', 'blklogwrites', 'blkverify', 'bochs', 'cloop',
+            'copy-on-read', 'dmg', 'file', 'ftp', 'ftps', 'gluster',
+            'host_cdrom', 'host_device', 'http', 'https', 'iscsi', 'luks',
+            'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', 'qcow',
+            'qcow2', 'qed', 'quorum', 'raw', 'rbd', 'replication', 'sheepdog',
+            'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
 
 ##
 # @BlockdevOptionsFile:
@@ -3044,6 +3045,30 @@
             '*inject-error': ['BlkdebugInjectErrorOptions'],
             '*set-state': ['BlkdebugSetStateOptions'] } }
 
+##
+# @BlockdevOptionsBlklogwrites:
+#
+# Driver specific block device options for blklogwrites.
+#
+# @file:            block device
+#
+# @log:             block device used to log writes to @file
+#
+# @log-sector-size: sector size used in logging writes to @file, determines
+#                   granularity of offsets and sizes of writes (default: 512)
+#
+# @log-super-update-interval: interval of write requests after which the log
+#                             super block is updated to disk (default: 4096)
+#
+# Since: 3.0
+##
+{ 'struct': 'BlockdevOptionsBlklogwrites',
+  'data': { 'file': 'BlockdevRef',
+            'log': 'BlockdevRef',
+            '*log-sector-size': 'uint32',
+            '*log-append': 'bool',
+            '*log-super-update-interval': 'uint64' } }
+
 ##
 # @BlockdevOptionsBlkverify:
 #
@@ -3563,6 +3588,7 @@
   'discriminator': 'driver',
   'data': {
       'blkdebug':   'BlockdevOptionsBlkdebug',
+      'blklogwrites':'BlockdevOptionsBlklogwrites',
       'blkverify':  'BlockdevOptionsBlkverify',
       'bochs':      'BlockdevOptionsGenericFormat',
       'cloop':      'BlockdevOptionsGenericFormat',

qemu-img.c

@@ -2141,11 +2141,6 @@ static int img_convert(int argc, char **argv)
         goto fail_getopt;
     }
 
-    if (!s.wr_in_order && s.compressed) {
-        error_report("Out of order write and compress are mutually exclusive");
-        goto fail_getopt;
-    }
-
     if (tgt_image_opts && !skip_create) {
         error_report("--target-image-opts requires use of -n flag");
         goto fail_getopt;

tests/qemu-iotests/051

@@ -99,6 +99,21 @@ run_qemu -drive file="$TEST_IMG",driver=foo
 run_qemu -drive file="$TEST_IMG",driver=raw,format=qcow2
 run_qemu -drive file="$TEST_IMG",driver=qcow2,format=qcow2
 
+echo
+echo === Node names ===
+echo
+
+# Maximum length: 31 characters
+run_qemu -drive file="$TEST_IMG",node-name=x123456789012345678901234567890
+run_qemu -drive file="$TEST_IMG",node-name=x1234567890123456789012345678901
+
+# First character must be alphabetic
+# Following characters alphanumeric or -._
+run_qemu -drive file="$TEST_IMG",node-name=All-Types.of_all0wed_chars
+run_qemu -drive file="$TEST_IMG",node-name=123foo
+run_qemu -drive file="$TEST_IMG",node-name=_foo
+run_qemu -drive file="$TEST_IMG",node-name=foo#12
+
 echo
 echo === Device without drive ===
 echo

tests/qemu-iotests/051.out

@@ -47,6 +47,29 @@ Testing: -drive file=TEST_DIR/t.qcow2,driver=qcow2,format=qcow2
 QEMU_PROG: -drive file=TEST_DIR/t.qcow2,driver=qcow2,format=qcow2: Cannot specify both 'driver' and 'format'
 
 
+=== Node names ===
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=x123456789012345678901234567890
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) quit
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=x1234567890123456789012345678901
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=x1234567890123456789012345678901: Node name too long
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=All-Types.of_all0wed_chars
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) quit
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=123foo
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=123foo: Invalid node name
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=_foo
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=_foo: Invalid node name
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=foo#12
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=foo#12: Invalid node name
+
+
 === Device without drive ===
 
 Testing: -device VIRTIO_SCSI -device scsi-hd

tests/qemu-iotests/051.pc.out

@@ -47,6 +47,29 @@ Testing: -drive file=TEST_DIR/t.qcow2,driver=qcow2,format=qcow2
 QEMU_PROG: -drive file=TEST_DIR/t.qcow2,driver=qcow2,format=qcow2: Cannot specify both 'driver' and 'format'
 
 
+=== Node names ===
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=x123456789012345678901234567890
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) quit
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=x1234567890123456789012345678901
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=x1234567890123456789012345678901: Node name too long
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=All-Types.of_all0wed_chars
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) quit
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=123foo
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=123foo: Invalid node name
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=_foo
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=_foo: Invalid node name
+
+Testing: -drive file=TEST_DIR/t.qcow2,node-name=foo#12
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=foo#12: Invalid node name
+
+
 === Device without drive ===
 
 Testing: -device VIRTIO_SCSI -device scsi-hd