The following changes since commit fb68096da3d35e64c88cd610c1fa42766c58e92a: Revert "tests: use memfd in vhost-user-test" (2018-02-13 09:51:52 +0000) are available in the git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to 0a4dc980e6c935e9be745ce3ee1a4c71629ecd00: Merge remote-tracking branch 'mreitz/tags/pull-block-2018-02-13' into queue-block (2018-02-13 17:01:13 +0100) ---------------------------------------------------------------- Block layer patches ---------------------------------------------------------------- Alberto Garcia (40): qcow2: Use g_try_realloc() in qcow2_expand_zero_clusters() qcow2: Fix documentation of get_cluster_table() qcow2: Add table size field to Qcow2Cache qcow2: Remove BDS parameter from qcow2_cache_get_table_addr() qcow2: Remove BDS parameter from qcow2_cache_get_table_idx() qcow2: Remove BDS parameter from qcow2_cache_table_release() qcow2: Remove BDS parameter from qcow2_cache_entry_mark_dirty() qcow2: Remove BDS parameter from qcow2_cache_put() qcow2: Remove BDS parameter from qcow2_cache_destroy() qcow2: Remove BDS parameter from qcow2_cache_clean_unused() qcow2: Remove BDS parameter from qcow2_cache_discard() qcow2: Remove BDS parameter from qcow2_cache_is_table_offset() qcow2: Add offset_to_l1_index() qcow2: Add l2_slice_size field to BDRVQcow2State qcow2: Add offset_to_l2_slice_index() qcow2: Update l2_load() to support L2 slices qcow2: Prepare l2_allocate() for adding L2 slice support qcow2: Update l2_allocate() to support L2 slices qcow2: Refactor get_cluster_table() qcow2: Update get_cluster_table() to support L2 slices qcow2: Update qcow2_get_cluster_offset() to support L2 slices qcow2: Update qcow2_alloc_cluster_link_l2() to support L2 slices qcow2: Update handle_copied() to support L2 slices qcow2: Update handle_alloc() to support L2 slices qcow2: Update discard_single_l2() to support L2 slices qcow2: Update zero_single_l2() to support L2 slices qcow2: Prepare qcow2_update_snapshot_refcount() for adding L2 slice support qcow2: Update qcow2_update_snapshot_refcount() to support L2 slices qcow2: Read refcount before L2 table in expand_zero_clusters_in_l1() qcow2: Prepare expand_zero_clusters_in_l1() for adding L2 slice support qcow2: Update expand_zero_clusters_in_l1() to support L2 slices qcow2: Update qcow2_truncate() to support L2 slices qcow2: Rename l2_table in qcow2_alloc_compressed_cluster_offset() qcow2: Rename l2_table in count_contiguous_clusters() qcow2: Rename l2_table in count_contiguous_clusters_unallocated() qcow2: Rename l2_table in count_cow_clusters() qcow2: Allow configuring the L2 slice size iotests: Test valid values of l2-cache-entry-size iotests: Test downgrading an image using a small L2 slice size iotests: Add l2-cache-entry-size to iotest 137 Daniel P. Berrangé (1): qemu-io: fix EOF Ctrl-D handling in qemu-io readline code Fam Zheng (4): iotests: Fix CID for VMDK afl image qemu-img.texi: Clean up parameter list qemu-img: Document --force-share / -U docs: Document share-rw property more thoroughly Kevin Wolf (1): Merge remote-tracking branch 'mreitz/tags/pull-block-2018-02-13' into queue-block Max Reitz (8): iotests: Use virtio-blk in 155 gluster: Move glfs_close() to create's clean-up gluster: Pull truncation from qemu_gluster_create gluster: Query current size in do_truncate() gluster: Add preallocated truncation sheepdog: Make sd_prealloc() take a BDS sheepdog: Pass old and new size to sd_prealloc() sheepdog: Allow fully preallocated truncation Paolo Bonzini (1): block: early check for blockers on drive-mirror Vladimir Sementsov-Ogievskiy (1): block: maintain persistent disabled bitmaps qapi/block-core.json | 12 +- block/qcow2.h | 33 +- include/block/dirty-bitmap.h | 1 - block/dirty-bitmap.c | 18 - block/gluster.c | 116 +++--- block/qcow2-bitmap.c | 12 +- block/qcow2-cache.c | 80 ++-- block/qcow2-cluster.c | 519 +++++++++++++------------ block/qcow2-refcount.c | 206 +++++----- block/qcow2.c | 63 ++- block/sheepdog.c | 56 ++- blockdev.c | 15 +- qemu-io.c | 27 +- docs/qemu-block-drivers.texi | 10 + qemu-doc.texi | 7 + qemu-img.texi | 74 ++-- tests/qemu-iotests/059.out | 2 +- tests/qemu-iotests/061 | 16 + tests/qemu-iotests/061.out | 61 +++ tests/qemu-iotests/103 | 17 + tests/qemu-iotests/103.out | 3 + tests/qemu-iotests/137 | 5 + tests/qemu-iotests/137.out | 2 + tests/qemu-iotests/155 | 14 +- tests/qemu-iotests/165 | 2 +- tests/qemu-iotests/176 | 2 +- tests/qemu-iotests/sample_images/afl9.vmdk.bz2 | Bin 178 -> 618 bytes 27 files changed, 816 insertions(+), 557 deletions(-) From: Fam Zheng <famz@redhat.com> This reverts commit 76bf133c4 which updated the reference output, and fixed the reference image, because the code path we want to exercise is actually the invalid image size. The descriptor block in the image, which includes the CID to verify, has been invalid since the reference image was added. Since commit 9877860e7bd we report this error earlier than the "file too large", so 059.out mismatches. The binary change is generated along the operations of: $ bunzip2 afl9.vmdk.bz2 $ qemu-img create -f vmdk fix.vmdk 1G $ dd if=afl9.vmdk of=fix.vmdk bs=512 count=1 conv=notrunc $ mv fix.vmdk afl9.vmdk $ bzip2 afl9.vmdk Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/059.out | 2 +- tests/qemu-iotests/sample_images/afl9.vmdk.bz2 | Bin 178 -> 618 bytes 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/059.out b/tests/qemu-iotests/059.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/059.out +++ b/tests/qemu-iotests/059.out @@ -XXX,XX +XXX,XX @@ Offset Length Mapped to File 0x140000000 0x10000 0x50000 TEST_DIR/t-s003.vmdk === Testing afl image with a very large capacity === -qemu-img: Could not open 'TEST_DIR/afl9.IMGFMT': Could not open 'TEST_DIR/afl9.IMGFMT': Invalid argument +qemu-img: Can't get image size 'TEST_DIR/afl9.IMGFMT': File too large *** done diff --git a/tests/qemu-iotests/sample_images/afl9.vmdk.bz2 b/tests/qemu-iotests/sample_images/afl9.vmdk.bz2 index XXXXXXX..XXXXXXX 100644 GIT binary patch literal 618 zcmV-w0+szjT4*^jL0KkKSvgW7ssIN3|NsBH-Q9UpfAhclU70`s-*NE~5QvC~h=_=Y zh>D2n*q*=vygR634445h35k;?00h9835kMW00004$iPepVE{Bqk)uhJ^wfGLr=)3s zhM5CR88jLh7)B;cA*K)*6GmuECPU3o4NWG5O#pg>Ak#xY8Z^<M8Z>CrMt}oD38Ns$ z02n}M0LdjZ&}cLPqd+nPKmn$j0iXe(02%-d27nnJriN-uE+X&cz@Bj4BBfd|yV!NB zwqkL}nW3AI5x^jp=t%^F1pxqp)v#n#)j$zcm1xqv(!$2d*5%vF{5RPWnOV8-^tE<( zU~%&}Y0uNu*9Wt=yS^8PkC&gPueZO%IG;aD{l#sG`<Af;l1Pnwpi9I75FkQ`LLhd8 z6(9f*2s+N5=%bwp80ddrD6>m4Ho*fsHXdM<jtl*zKvRiTx7Ugy1|Nl<Ns!z;1dvhy z=`SDHh~{u|1ZodC(_lzezQ)I*Kv2z|PZ@!SJjlVzwGdx2iu#W}dI{t+T&dDWT^LPy zg3NouEM=V~7GvZQS1CXy676F6mJXWGgW!KTr+E$OspGYCjWmuwa^<Bc>_(-i7fPIW zA+~n9iy_f)g8B2RILhd%F)dZ5f?7pFLw)@;Ncl<JE}gvMrfh{elT#3gLjY6r8xY4O z)UO#pv=WYptukn<DuoMH2ip%k?V^k!rjQirK^RC<Brw>3Bz9<|!xm0F{45K+gg8#n z4FNAJ!<X|3Vq+lyV4=xZ;>AN0<K=%c4A2ruB!4rGvWm!KFrvd4PyfZ-kxmpO4pfM$ EfLnqQYXATM literal 178 zcmV;j08RfwT4*^jL0KkKS>A08g#Z9x|HJ$H)ZJi0004xF0SE*D03g5s00IDLSQelF ziVX^$pfWNUJrmRhn2k52pQ;Rs0EQC;(S%|!m`2~BZ@b++;etskRJUVl!Kt)wu7?VN zl;%JdqX2?TgsNVJP?87M*MvL1qQnBkCES&?0@MeaN-bL4;bDzxmMm|da4fuh!=#fu g@i9R@5z!av{9tA<GGr!3hi~HUNT&)C8_l7xpl%OKQ2+n{ -- 2.13.6 From: Fam Zheng <famz@redhat.com> Split options out of the "@table @var" section and create a "@table @option", then use whitespaces and blank lines consistently. Suggested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Kashyap Chamarthy <kchamart@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.texi | 66 +++++++++++++++++++++++++++++++++++------------------------ 1 file changed, 39 insertions(+), 27 deletions(-) diff --git a/qemu-img.texi b/qemu-img.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.texi +++ b/qemu-img.texi @@ -XXX,XX +XXX,XX @@ The following commands are supported: Command parameters: @table @var -@item filename - is a disk image filename - -@item --object @var{objectdef} - -is a QEMU user creatable object definition. See the @code{qemu(1)} manual -page for a description of the object properties. The most common object -type is a @code{secret}, which is used to supply passwords and/or encryption -keys. - -@item --image-opts - -Indicates that the source @var{filename} parameter is to be interpreted as a -full option string, not a plain filename. This parameter is mutually -exclusive with the @var{-f} parameter. - -@item --target-image-opts -Indicates that the @var{output_filename} parameter(s) are to be interpreted as -a full option string, not a plain filename. This parameter is mutually -exclusive with the @var{-O} parameters. It is currently required to also use -the @var{-n} parameter to skip image creation. This restriction may be relaxed -in a future release. +@item filename +is a disk image filename @item fmt is the disk image format. It is guessed automatically in most cases. See below for a description of the supported disk formats. -@item --backing-chain -will enumerate information about backing files in a disk image chain. Refer -below for further description. - @item size is the disk image size in bytes. Optional suffixes @code{k} or @code{K} (kilobyte, 1024) @code{M} (megabyte, 1024k) and @code{G} (gigabyte, 1024M) @@ -XXX,XX +XXX,XX @@ and T (terabyte, 1024G) are supported. @code{b} is ignored. is the destination disk image filename @item output_fmt - is the destination format +is the destination format + @item options is a comma separated list of format specific options in a name=value format. Use @code{-o ?} for an overview of the options supported by the used format or see the format descriptions below for details. + @item snapshot_param is param used for internal snapshot, format is 'snapshot.id=[ID],snapshot.name=[NAME]' or '[ID_OR_NAME]' + @item snapshot_id_or_name is deprecated, use snapshot_param instead +@end table + +@table @option + +@item --object @var{objectdef} +is a QEMU user creatable object definition. See the @code{qemu(1)} manual +page for a description of the object properties. The most common object +type is a @code{secret}, which is used to supply passwords and/or encryption +keys. + +@item --image-opts +Indicates that the source @var{filename} parameter is to be interpreted as a +full option string, not a plain filename. This parameter is mutually +exclusive with the @var{-f} parameter. + +@item --target-image-opts +Indicates that the @var{output_filename} parameter(s) are to be interpreted as +a full option string, not a plain filename. This parameter is mutually +exclusive with the @var{-O} parameters. It is currently required to also use +the @var{-n} parameter to skip image creation. This restriction may be relaxed +in a future release. + +@item --backing-chain +will enumerate information about backing files in a disk image chain. Refer +below for further description. + @item -c indicates that target image must be compressed (qcow format only) + @item -h with or without a command shows help and lists the supported formats + @item -p display progress bar (compare, convert and rebase commands only). If the @var{-p} option is not used for a command that supports it, the progress is reported when the process receives a @code{SIGUSR1} or @code{SIGINFO} signal. + @item -q Quiet mode - do not print any output (except errors). There's no progress bar in case both @var{-q} and @var{-p} options are used. + @item -S @var{size} indicates the consecutive number of bytes that must contain only zeros for qemu-img to create a sparse image during conversion. This value is rounded down to the nearest 512 bytes. You may use the common size suffixes like @code{k} for kilobytes. + @item -t @var{cache} specifies the cache mode that should be used with the (destination) file. See the documentation of the emulator's @code{-drive cache=...} option for allowed values. + @item -T @var{src_cache} specifies the cache mode that should be used with the source file(s). See the documentation of the emulator's @code{-drive cache=...} option for allowed values. + @end table Parameters to snapshot subcommand: -- 2.13.6 From: Fam Zheng <famz@redhat.com> Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Kashyap Chamarthy <kchamart@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.texi | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/qemu-img.texi b/qemu-img.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.texi +++ b/qemu-img.texi @@ -XXX,XX +XXX,XX @@ exclusive with the @var{-O} parameters. It is currently required to also use the @var{-n} parameter to skip image creation. This restriction may be relaxed in a future release. +@item --force-share (-U) +If specified, @code{qemu-img} will open the image in shared mode, allowing +other QEMU processes to open it in write mode. For example, this can be used to +get the image information (with 'info' subcommand) when the image is used by a +running guest. Note that this could produce inconsistent results because of +concurrent metadata changes, etc. This option is only allowed when opening +images in read-only mode. + @item --backing-chain will enumerate information about backing files in a disk image chain. Refer below for further description. -- 2.13.6 From: Fam Zheng <famz@redhat.com> Suggested-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Kashyap Chamarthy <kchamart@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- docs/qemu-block-drivers.texi | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/docs/qemu-block-drivers.texi b/docs/qemu-block-drivers.texi index XXXXXXX..XXXXXXX 100644 --- a/docs/qemu-block-drivers.texi +++ b/docs/qemu-block-drivers.texi @@ -XXX,XX +XXX,XX @@ QEMU transparently handles lock handover during shared storage migration. For shared virtual disk images between multiple VMs, the "share-rw" device option should be used. +By default, the guest has exclusive write access to its disk image. If the +guest can safely share the disk image with other writers the @code{-device +...,share-rw=on} parameter can be used. This is only safe if the guest is +running software, such as a cluster file system, that coordinates disk accesses +to avoid corruption. + +Note that share-rw=on only declares the guest's ability to share the disk. +Some QEMU features, such as image file formats, require exclusive write access +to the disk image and this is unaffected by the share-rw=on option. + Alternatively, locking can be fully disabled by "locking=off" block device option. In the command line, the option is usually in the form of "file.locking=off" as the protocol driver is normally placed as a "file" child -- 2.13.6 From: Alberto Garcia <berto@igalia.com> g_realloc() aborts the program if it fails to allocate the required amount of memory. We want to detect that scenario and return an error instead, so let's use g_try_realloc(). Signed-off-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-cluster.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_expand_zero_clusters(BlockDriverState *bs, int l1_sectors = DIV_ROUND_UP(s->snapshots[i].l1_size * sizeof(uint64_t), BDRV_SECTOR_SIZE); - l1_table = g_realloc(l1_table, l1_sectors * BDRV_SECTOR_SIZE); + uint64_t *new_l1_table = + g_try_realloc(l1_table, l1_sectors * BDRV_SECTOR_SIZE); + + if (!new_l1_table) { + ret = -ENOMEM; + goto fail; + } + + l1_table = new_l1_table; ret = bdrv_read(bs->file, s->snapshots[i].l1_table_offset / BDRV_SECTOR_SIZE, -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> Even if an op blocker is present for BLOCK_OP_TYPE_MIRROR_SOURCE, it is checked a bit late and the result is that the target is created even if drive-mirror subsequently fails. Add an early check to avoid this. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockdev.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp) return; } + /* Early check to avoid creating target */ + if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_MIRROR_SOURCE, errp)) { + return; + } + aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Only a few select machine types support floppy drives and there is actually nothing preventing us from using virtio here, so let's do it. Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/155 | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/tests/qemu-iotests/155 b/tests/qemu-iotests/155 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/155 +++ b/tests/qemu-iotests/155 @@ -XXX,XX +XXX,XX @@ class BaseClass(iotests.QMPTestCase): 'file': {'driver': 'file', 'filename': source_img}} self.vm.add_blockdev(self.qmp_to_opts(blockdev)) - self.vm.add_device('floppy,id=qdev0,drive=source') + self.vm.add_device('virtio-blk,id=qdev0,drive=source') self.vm.launch() self.assertIntactSourceBackingChain() @@ -XXX,XX +XXX,XX @@ class MirrorBaseClass(BaseClass): def testFull(self): self.runMirror('full') - node = self.findBlockNode('target', 'qdev0') + node = self.findBlockNode('target', + '/machine/peripheral/qdev0/virtio-backend') self.assertCorrectBackingImage(node, None) self.assertIntactSourceBackingChain() def testTop(self): self.runMirror('top') - node = self.findBlockNode('target', 'qdev0') + node = self.findBlockNode('target', + '/machine/peripheral/qdev0/virtio-backend') self.assertCorrectBackingImage(node, back2_img) self.assertIntactSourceBackingChain() def testNone(self): self.runMirror('none') - node = self.findBlockNode('target', 'qdev0') + node = self.findBlockNode('target', + '/machine/peripheral/qdev0/virtio-backend') self.assertCorrectBackingImage(node, source_img) self.assertIntactSourceBackingChain() @@ -XXX,XX +XXX,XX @@ class TestCommit(BaseClass): self.vm.event_wait('BLOCK_JOB_COMPLETED') - node = self.findBlockNode(None, 'qdev0') + node = self.findBlockNode(None, + '/machine/peripheral/qdev0/virtio-backend') self.assert_qmp(node, 'image' + '/backing-image' * 0 + '/filename', back1_img) self.assert_qmp(node, 'image' + '/backing-image' * 1 + '/filename', -- 2.13.6 From: "Daniel P. Berrange" <berrange@redhat.com> qemu-io puts the TTY into non-canonical mode, which means no EOF processing is done and thus getchar() will never return the EOF constant. Instead we have to query the TTY attributes to determine the configured EOF character (usually Ctrl-D / 0x4), and then explicitly check for that value. This fixes the regression that prevented Ctrl-D from triggering an exit of qemu-io that has existed since readline was first added in commit 0cf17e181798063c3824c8200ba46f25f54faa1a Author: Stefan Hajnoczi <stefanha@redhat.com> Date: Thu Nov 14 11:54:17 2013 +0100 qemu-io: use readline.c It also ensures that a newline is printed when exiting, to complete the line output by the "qemu-io> " prompt. Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-io.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/qemu-io.c b/qemu-io.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io.c +++ b/qemu-io.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include <getopt.h> #include <libgen.h> +#ifndef _WIN32 +#include <termios.h> +#endif #include "qapi/error.h" #include "qemu-io.h" @@ -XXX,XX +XXX,XX @@ static bool imageOpts; static ReadLineState *readline_state; +static int ttyEOF; + +static int get_eof_char(void) +{ +#ifdef _WIN32 + return 0x4; /* Ctrl-D */ +#else + struct termios tty; + if (tcgetattr(STDIN_FILENO, &tty) != 0) { + if (errno == ENOTTY) { + return 0x0; /* just expect read() == 0 */ + } else { + return 0x4; /* Ctrl-D */ + } + } + + return tty.c_cc[VEOF]; +#endif +} + static int close_f(BlockBackend *blk, int argc, char **argv) { blk_unref(qemuio_blk); @@ -XXX,XX +XXX,XX @@ static char *fetchline_readline(void) readline_start(readline_state, get_prompt(), 0, readline_func, &line); while (!line) { int ch = getchar(); - if (ch == EOF) { + if (ttyEOF != 0x0 && ch == ttyEOF) { + printf("\n"); break; } readline_handle_byte(readline_state, ch); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) qemuio_add_command(&close_cmd); if (isatty(STDIN_FILENO)) { + ttyEOF = get_eof_char(); readline_state = readline_init(readline_printf_func, readline_flush_func, NULL, -- 2.13.6 From: Max Reitz <mreitz@redhat.com> glfs_close() is a classical clean-up operation, as can be seen by the fact that it is executed even if the truncation before it failed. Also, moving it to clean-up makes it more clear that if it fails, we do not want it to overwrite the current ret value if that signifies an error already. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/gluster.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static int qemu_gluster_create(const char *filename, { BlockdevOptionsGluster *gconf; struct glfs *glfs; - struct glfs_fd *fd; + struct glfs_fd *fd = NULL; int ret = 0; PreallocMode prealloc; int64_t total_size = 0; @@ -XXX,XX +XXX,XX @@ static int qemu_gluster_create(const char *filename, break; } - if (glfs_close(fd) != 0) { - ret = -errno; - } out: + if (fd) { + if (glfs_close(fd) != 0 && ret == 0) { + ret = -errno; + } + } qapi_free_BlockdevOptionsGluster(gconf); glfs_clear_preopened(glfs); return ret; -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Pull out the truncation code from the qemu_cluster_create() function so we can later reuse it in qemu_gluster_truncate(). Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/gluster.c | 74 +++++++++++++++++++++++++++++++-------------------------- 1 file changed, 40 insertions(+), 34 deletions(-) diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs, } #endif +static int qemu_gluster_do_truncate(struct glfs_fd *fd, int64_t offset, + PreallocMode prealloc, Error **errp) +{ + switch (prealloc) { +#ifdef CONFIG_GLUSTERFS_FALLOCATE + case PREALLOC_MODE_FALLOC: + if (glfs_fallocate(fd, 0, 0, offset)) { + error_setg_errno(errp, errno, "Could not preallocate data"); + return -errno; + } + break; +#endif /* CONFIG_GLUSTERFS_FALLOCATE */ +#ifdef CONFIG_GLUSTERFS_ZEROFILL + case PREALLOC_MODE_FULL: + if (glfs_ftruncate(fd, offset)) { + error_setg_errno(errp, errno, "Could not resize file"); + return -errno; + } + if (glfs_zerofill(fd, 0, offset)) { + error_setg_errno(errp, errno, "Could not zerofill the new area"); + return -errno; + } + break; +#endif /* CONFIG_GLUSTERFS_ZEROFILL */ + case PREALLOC_MODE_OFF: + if (glfs_ftruncate(fd, offset)) { + error_setg_errno(errp, errno, "Could not resize file"); + return -errno; + } + break; + default: + error_setg(errp, "Unsupported preallocation mode: %s", + PreallocMode_str(prealloc)); + return -EINVAL; + } + + return 0; +} + static int qemu_gluster_create(const char *filename, QemuOpts *opts, Error **errp) { @@ -XXX,XX +XXX,XX @@ static int qemu_gluster_create(const char *filename, goto out; } - switch (prealloc) { -#ifdef CONFIG_GLUSTERFS_FALLOCATE - case PREALLOC_MODE_FALLOC: - if (glfs_fallocate(fd, 0, 0, total_size)) { - error_setg(errp, "Could not preallocate data for the new file"); - ret = -errno; - } - break; -#endif /* CONFIG_GLUSTERFS_FALLOCATE */ -#ifdef CONFIG_GLUSTERFS_ZEROFILL - case PREALLOC_MODE_FULL: - if (!glfs_ftruncate(fd, total_size)) { - if (glfs_zerofill(fd, 0, total_size)) { - error_setg(errp, "Could not zerofill the new file"); - ret = -errno; - } - } else { - error_setg(errp, "Could not resize file"); - ret = -errno; - } - break; -#endif /* CONFIG_GLUSTERFS_ZEROFILL */ - case PREALLOC_MODE_OFF: - if (glfs_ftruncate(fd, total_size) != 0) { - ret = -errno; - error_setg(errp, "Could not resize file"); - } - break; - default: - ret = -EINVAL; - error_setg(errp, "Unsupported preallocation mode: %s", - PreallocMode_str(prealloc)); - break; - } + ret = qemu_gluster_do_truncate(fd, total_size, prealloc, errp); out: if (fd) { -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Instead of expecting the current size to be 0, query it and allocate only the area [current_size, offset) if preallocation is requested. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/gluster.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs, static int qemu_gluster_do_truncate(struct glfs_fd *fd, int64_t offset, PreallocMode prealloc, Error **errp) { + int64_t current_length; + + current_length = glfs_lseek(fd, 0, SEEK_END); + if (current_length < 0) { + error_setg_errno(errp, errno, "Failed to determine current size"); + return -errno; + } + + if (current_length > offset && prealloc != PREALLOC_MODE_OFF) { + error_setg(errp, "Cannot use preallocation for shrinking files"); + return -ENOTSUP; + } + + if (current_length == offset) { + return 0; + } + switch (prealloc) { #ifdef CONFIG_GLUSTERFS_FALLOCATE case PREALLOC_MODE_FALLOC: - if (glfs_fallocate(fd, 0, 0, offset)) { + if (glfs_fallocate(fd, 0, current_length, offset - current_length)) { error_setg_errno(errp, errno, "Could not preallocate data"); return -errno; } @@ -XXX,XX +XXX,XX @@ static int qemu_gluster_do_truncate(struct glfs_fd *fd, int64_t offset, error_setg_errno(errp, errno, "Could not resize file"); return -errno; } - if (glfs_zerofill(fd, 0, offset)) { + if (glfs_zerofill(fd, current_length, offset - current_length)) { error_setg_errno(errp, errno, "Could not zerofill the new area"); return -errno; } -- 2.13.6 From: Max Reitz <mreitz@redhat.com> By using qemu_do_cluster_truncate() in qemu_cluster_truncate(), we now automatically have preallocated truncation. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/gluster.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs, static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset, PreallocMode prealloc, Error **errp) { - int ret; BDRVGlusterState *s = bs->opaque; - - if (prealloc != PREALLOC_MODE_OFF) { - error_setg(errp, "Unsupported preallocation mode '%s'", - PreallocMode_str(prealloc)); - return -ENOTSUP; - } - - ret = glfs_ftruncate(s->fd, offset); - if (ret < 0) { - ret = -errno; - error_setg_errno(errp, -ret, "Failed to truncate file"); - return ret; - } - - return 0; + return qemu_gluster_do_truncate(s->fd, offset, prealloc, errp); } static coroutine_fn int qemu_gluster_co_readv(BlockDriverState *bs, -- 2.13.6 From: Max Reitz <mreitz@redhat.com> We want to use this function in sd_truncate() later on, so taking a filename is not exactly ideal. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/sheepdog.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot, return 0; } -static int sd_prealloc(const char *filename, Error **errp) +static int sd_prealloc(BlockDriverState *bs, Error **errp) { BlockBackend *blk = NULL; - BDRVSheepdogState *base = NULL; + BDRVSheepdogState *base = bs->opaque; unsigned long buf_size; uint32_t idx, max_idx; uint32_t object_size; @@ -XXX,XX +XXX,XX @@ static int sd_prealloc(const char *filename, Error **errp) void *buf = NULL; int ret; - blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp); - if (blk == NULL) { - ret = -EIO; + blk = blk_new(BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE | BLK_PERM_RESIZE, + BLK_PERM_ALL); + + ret = blk_insert_bs(blk, bs, errp); + if (ret < 0) { goto out_with_err_set; } @@ -XXX,XX +XXX,XX @@ static int sd_prealloc(const char *filename, Error **errp) goto out; } - base = blk_bs(blk)->opaque; object_size = (UINT32_C(1) << base->inode.block_size_shift); buf_size = MIN(object_size, SD_DATA_OBJ_SIZE); buf = g_malloc0(buf_size); @@ -XXX,XX +XXX,XX @@ static int sd_create(const char *filename, QemuOpts *opts, } if (prealloc) { - ret = sd_prealloc(filename, errp); + BlockDriverState *bs; + QDict *opts; + + opts = qdict_new(); + qdict_put_str(opts, "driver", "sheepdog"); + bs = bdrv_open(filename, NULL, opts, BDRV_O_PROTOCOL | BDRV_O_RDWR, + errp); + if (!bs) { + goto out; + } + + ret = sd_prealloc(bs, errp); + + bdrv_unref(bs); } out: g_free(backing_file); -- 2.13.6 From: Max Reitz <mreitz@redhat.com> sd_prealloc() will now preallocate the area [old_size, new_size). As before, it rounds to buf_size and may thus overshoot and preallocate areas that were not requested to be preallocated. For image creation, this is no change in behavior. For truncation, this is in accordance with the documentation for preallocated truncation. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/sheepdog.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot, return 0; } -static int sd_prealloc(BlockDriverState *bs, Error **errp) +static int sd_prealloc(BlockDriverState *bs, int64_t old_size, int64_t new_size, + Error **errp) { BlockBackend *blk = NULL; BDRVSheepdogState *base = bs->opaque; unsigned long buf_size; uint32_t idx, max_idx; uint32_t object_size; - int64_t vdi_size; void *buf = NULL; int ret; @@ -XXX,XX +XXX,XX @@ static int sd_prealloc(BlockDriverState *bs, Error **errp) blk_set_allow_write_beyond_eof(blk, true); - vdi_size = blk_getlength(blk); - if (vdi_size < 0) { - ret = vdi_size; - goto out; - } - object_size = (UINT32_C(1) << base->inode.block_size_shift); buf_size = MIN(object_size, SD_DATA_OBJ_SIZE); buf = g_malloc0(buf_size); - max_idx = DIV_ROUND_UP(vdi_size, buf_size); + max_idx = DIV_ROUND_UP(new_size, buf_size); - for (idx = 0; idx < max_idx; idx++) { + for (idx = old_size / buf_size; idx < max_idx; idx++) { /* * The created image can be a cloned image, so we need to read * a data from the source image. @@ -XXX,XX +XXX,XX @@ static int sd_create(const char *filename, QemuOpts *opts, goto out; } - ret = sd_prealloc(bs, errp); + ret = sd_prealloc(bs, 0, s->inode.vdi_size, errp); bdrv_unref(bs); } -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/sheepdog.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static int sd_truncate(BlockDriverState *bs, int64_t offset, int ret, fd; unsigned int datalen; uint64_t max_vdi_size; + int64_t old_size = s->inode.vdi_size; - if (prealloc != PREALLOC_MODE_OFF) { + if (prealloc != PREALLOC_MODE_OFF && prealloc != PREALLOC_MODE_FULL) { error_setg(errp, "Unsupported preallocation mode '%s'", PreallocMode_str(prealloc)); return -ENOTSUP; } max_vdi_size = (UINT64_C(1) << s->inode.block_size_shift) * MAX_DATA_OBJS; - if (offset < s->inode.vdi_size) { + if (offset < old_size) { error_setg(errp, "shrinking is not supported"); return -EINVAL; } else if (offset > max_vdi_size) { @@ -XXX,XX +XXX,XX @@ static int sd_truncate(BlockDriverState *bs, int64_t offset, if (ret < 0) { error_setg_errno(errp, -ret, "failed to update an inode"); + return ret; } - return ret; + if (prealloc == PREALLOC_MODE_FULL) { + ret = sd_prealloc(bs, old_size, offset, errp); + if (ret < 0) { + return ret; + } + } + + return 0; } /* -- 2.13.6 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> To maintain load/store disabled bitmap there is new approach: - deprecate @autoload flag of block-dirty-bitmap-add, make it ignored - store enabled bitmaps as "auto" to qcow2 - store disabled bitmaps without "auto" flag to qcow2 - on qcow2 open load "auto" bitmaps as enabled and others as disabled (except in_use bitmaps) Also, adjust iotests 165 and 176 appropriately. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20180202160752.143796-1-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 6 +++--- block/qcow2.h | 2 +- include/block/dirty-bitmap.h | 1 - block/dirty-bitmap.c | 18 ------------------ block/qcow2-bitmap.c | 12 +++++++----- block/qcow2.c | 2 +- blockdev.c | 10 ++-------- qemu-doc.texi | 7 +++++++ tests/qemu-iotests/165 | 2 +- tests/qemu-iotests/176 | 2 +- 10 files changed, 23 insertions(+), 39 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # Qcow2 disks support persistent bitmaps. Default is false for # block-dirty-bitmap-add. (Since: 2.10) # -# @autoload: the bitmap will be automatically loaded when the image it is stored -# in is opened. This flag may only be specified for persistent -# bitmaps. Default is false for block-dirty-bitmap-add. (Since: 2.10) +# @autoload: ignored and deprecated since 2.12. +# Currently, all dirty tracking bitmaps are loaded from Qcow2 on +# open. # # Since: 2.4 ## diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ void qcow2_cache_discard(BlockDriverState *bs, Qcow2Cache *c, void *table); int qcow2_check_bitmaps_refcounts(BlockDriverState *bs, BdrvCheckResult *res, void **refcount_table, int64_t *refcount_table_size); -bool qcow2_load_autoloading_dirty_bitmaps(BlockDriverState *bs, Error **errp); +bool qcow2_load_dirty_bitmaps(BlockDriverState *bs, Error **errp); int qcow2_reopen_bitmaps_rw(BlockDriverState *bs, Error **errp); void qcow2_store_persistent_dirty_bitmaps(BlockDriverState *bs, Error **errp); int qcow2_reopen_bitmaps_ro(BlockDriverState *bs, Error **errp); diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_bitmap_deserialize_ones(BdrvDirtyBitmap *bitmap, void bdrv_dirty_bitmap_deserialize_finish(BdrvDirtyBitmap *bitmap); void bdrv_dirty_bitmap_set_readonly(BdrvDirtyBitmap *bitmap, bool value); -void bdrv_dirty_bitmap_set_autoload(BdrvDirtyBitmap *bitmap, bool autoload); void bdrv_dirty_bitmap_set_persistance(BdrvDirtyBitmap *bitmap, bool persistent); diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ struct BdrvDirtyBitmap { Such operations must fail and both the image and this bitmap must remain unchanged while this flag is set. */ - bool autoload; /* For persistent bitmaps: bitmap must be - autoloaded on image opening */ bool persistent; /* bitmap must be saved to owner disk image */ QLIST_ENTRY(BdrvDirtyBitmap) list; }; @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_bitmap_make_anon(BdrvDirtyBitmap *bitmap) g_free(bitmap->name); bitmap->name = NULL; bitmap->persistent = false; - bitmap->autoload = false; } /* Called with BQL taken. */ @@ -XXX,XX +XXX,XX @@ BdrvDirtyBitmap *bdrv_dirty_bitmap_abdicate(BlockDriverState *bs, bitmap->successor = NULL; successor->persistent = bitmap->persistent; bitmap->persistent = false; - successor->autoload = bitmap->autoload; - bitmap->autoload = false; bdrv_release_dirty_bitmap(bs, bitmap); return successor; @@ -XXX,XX +XXX,XX @@ bool bdrv_has_readonly_bitmaps(BlockDriverState *bs) } /* Called with BQL taken. */ -void bdrv_dirty_bitmap_set_autoload(BdrvDirtyBitmap *bitmap, bool autoload) -{ - qemu_mutex_lock(bitmap->mutex); - bitmap->autoload = autoload; - qemu_mutex_unlock(bitmap->mutex); -} - -bool bdrv_dirty_bitmap_get_autoload(const BdrvDirtyBitmap *bitmap) -{ - return bitmap->autoload; -} - -/* Called with BQL taken. */ void bdrv_dirty_bitmap_set_persistance(BdrvDirtyBitmap *bitmap, bool persistent) { qemu_mutex_lock(bitmap->mutex); diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-bitmap.c +++ b/block/qcow2-bitmap.c @@ -XXX,XX +XXX,XX @@ static void set_readonly_helper(gpointer bitmap, gpointer value) bdrv_dirty_bitmap_set_readonly(bitmap, (bool)value); } -/* qcow2_load_autoloading_dirty_bitmaps() +/* qcow2_load_dirty_bitmaps() * Return value is a hint for caller: true means that the Qcow2 header was * updated. (false doesn't mean that the header should be updated by the * caller, it just means that updating was not needed or the image cannot be * written to). * On failure the function returns false. */ -bool qcow2_load_autoloading_dirty_bitmaps(BlockDriverState *bs, Error **errp) +bool qcow2_load_dirty_bitmaps(BlockDriverState *bs, Error **errp) { BDRVQcow2State *s = bs->opaque; Qcow2BitmapList *bm_list; @@ -XXX,XX +XXX,XX @@ bool qcow2_load_autoloading_dirty_bitmaps(BlockDriverState *bs, Error **errp) } QSIMPLEQ_FOREACH(bm, bm_list, entry) { - if ((bm->flags & BME_FLAG_AUTO) && !(bm->flags & BME_FLAG_IN_USE)) { + if (!(bm->flags & BME_FLAG_IN_USE)) { BdrvDirtyBitmap *bitmap = load_bitmap(bs, bm, errp); if (bitmap == NULL) { goto fail; } + if (!(bm->flags & BME_FLAG_AUTO)) { + bdrv_disable_dirty_bitmap(bitmap); + } bdrv_dirty_bitmap_set_persistance(bitmap, true); - bdrv_dirty_bitmap_set_autoload(bitmap, true); bm->flags |= BME_FLAG_IN_USE; created_dirty_bitmaps = g_slist_append(created_dirty_bitmaps, bitmap); @@ -XXX,XX +XXX,XX @@ void qcow2_store_persistent_dirty_bitmaps(BlockDriverState *bs, Error **errp) bm->table.size = 0; QSIMPLEQ_INSERT_TAIL(&drop_tables, tb, entry); } - bm->flags = bdrv_dirty_bitmap_get_autoload(bitmap) ? BME_FLAG_AUTO : 0; + bm->flags = bdrv_dirty_bitmap_enabled(bitmap) ? BME_FLAG_AUTO : 0; bm->granularity_bits = ctz32(bdrv_dirty_bitmap_granularity(bitmap)); bm->dirty_bitmap = bitmap; } diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags, s->autoclear_features &= QCOW2_AUTOCLEAR_MASK; } - if (qcow2_load_autoloading_dirty_bitmaps(bs, &local_err)) { + if (qcow2_load_dirty_bitmaps(bs, &local_err)) { update_header = false; } if (local_err != NULL) { diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_block_dirty_bitmap_add(const char *node, const char *name, if (!has_persistent) { persistent = false; } - if (!has_autoload) { - autoload = false; - } - if (has_autoload && !persistent) { - error_setg(errp, "Autoload flag must be used only for persistent " - "bitmaps"); - return; + if (has_autoload) { + warn_report("Autoload option is deprecated and its value is ignored"); } if (persistent && @@ -XXX,XX +XXX,XX @@ void qmp_block_dirty_bitmap_add(const char *node, const char *name, } bdrv_dirty_bitmap_set_persistance(bitmap, persistent); - bdrv_dirty_bitmap_set_autoload(bitmap, autoload); } void qmp_block_dirty_bitmap_remove(const char *node, const char *name, diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ used and it will be removed with no replacement. The ``convert -s snapshot_id_or_name'' argument is obsoleted by the ``convert -l snapshot_param'' argument instead. +@section QEMU Machine Protocol (QMP) commands + +@subsection block-dirty-bitmap-add "autoload" parameter (since 2.12.0) + +"autoload" parameter is now ignored. All bitmaps are automatically loaded +from qcow2 images. + @section System emulator human monitor commands @subsection host_net_add (since 2.10.0) diff --git a/tests/qemu-iotests/165 b/tests/qemu-iotests/165 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/165 +++ b/tests/qemu-iotests/165 @@ -XXX,XX +XXX,XX @@ class TestPersistentDirtyBitmap(iotests.QMPTestCase): def qmpAddBitmap(self): self.vm.qmp('block-dirty-bitmap-add', node='drive0', - name='bitmap0', persistent=True, autoload=True) + name='bitmap0', persistent=True) def test_persistent(self): self.vm = self.mkVm() diff --git a/tests/qemu-iotests/176 b/tests/qemu-iotests/176 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/176 +++ b/tests/qemu-iotests/176 @@ -XXX,XX +XXX,XX @@ case $reason in "file": { "driver": "file", "filename": "$TEST_IMG" } } } { "execute": "block-dirty-bitmap-add", "arguments": { "node": "drive0", "name": "bitmap0", - "persistent": true, "autoload": true } } + "persistent": true } } { "execute": "quit" } EOF ;; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function has not been returning the offset of the L2 table since commit 3948d1d4876065160583e79533bf604481063833 Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: b498733b6706a859a03678d74ecbd26aeba129aa.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ fail: * for a given disk offset, load (and allocate if needed) * the l2 table. * - * the l2 table offset in the qcow2 file and the cluster index - * in the l2 table are given to the caller. + * the cluster index in the l2 table is given to the caller. * * Returns 0 on success, -errno in failure case */ -- 2.13.6 From: Alberto Garcia <berto@igalia.com> The table size in the qcow2 cache is currently equal to the cluster size. This doesn't allow us to use the cache memory efficiently, particularly with large cluster sizes, so we need to be able to have smaller cache tables that are independent from the cluster size. This patch adds a new field to Qcow2Cache that we can use instead of the cluster size. The current table size is still being initialized to the cluster size, so there are no semantic changes yet, but this patch will allow us to prepare the rest of the code and simplify a few function calls. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 67a1bf9e55f417005c567bead95a018dc34bc687.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cache.c | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ struct Qcow2Cache { Qcow2CachedTable *entries; struct Qcow2Cache *depends; int size; + int table_size; bool depends_on_flush; void *table_array; uint64_t lru_counter; @@ -XXX,XX +XXX,XX @@ struct Qcow2Cache { static inline void *qcow2_cache_get_table_addr(BlockDriverState *bs, Qcow2Cache *c, int table) { - BDRVQcow2State *s = bs->opaque; - return (uint8_t *) c->table_array + (size_t) table * s->cluster_size; + return (uint8_t *) c->table_array + (size_t) table * c->table_size; } static inline int qcow2_cache_get_table_idx(BlockDriverState *bs, Qcow2Cache *c, void *table) { - BDRVQcow2State *s = bs->opaque; ptrdiff_t table_offset = (uint8_t *) table - (uint8_t *) c->table_array; - int idx = table_offset / s->cluster_size; - assert(idx >= 0 && idx < c->size && table_offset % s->cluster_size == 0); + int idx = table_offset / c->table_size; + assert(idx >= 0 && idx < c->size && table_offset % c->table_size == 0); return idx; } @@ -XXX,XX +XXX,XX @@ static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c, { /* Using MADV_DONTNEED to discard memory is a Linux-specific feature */ #ifdef CONFIG_LINUX - BDRVQcow2State *s = bs->opaque; void *t = qcow2_cache_get_table_addr(bs, c, i); int align = getpagesize(); - size_t mem_size = (size_t) s->cluster_size * num_tables; + size_t mem_size = (size_t) c->table_size * num_tables; size_t offset = QEMU_ALIGN_UP((uintptr_t) t, align) - (uintptr_t) t; size_t length = QEMU_ALIGN_DOWN(mem_size - offset, align); if (mem_size > offset && length > 0) { @@ -XXX,XX +XXX,XX @@ Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables) c = g_new0(Qcow2Cache, 1); c->size = num_tables; + c->table_size = s->cluster_size; c->entries = g_try_new0(Qcow2CachedTable, num_tables); c->table_array = qemu_try_blockalign(bs->file->bs, - (size_t) num_tables * s->cluster_size); + (size_t) num_tables * c->table_size); if (!c->entries || !c->table_array) { qemu_vfree(c->table_array); @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i) if (c == s->refcount_block_cache) { ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_REFCOUNT_BLOCK, - c->entries[i].offset, s->cluster_size); + c->entries[i].offset, c->table_size); } else if (c == s->l2_table_cache) { ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_ACTIVE_L2, - c->entries[i].offset, s->cluster_size); + c->entries[i].offset, c->table_size); } else { ret = qcow2_pre_write_overlap_check(bs, 0, - c->entries[i].offset, s->cluster_size); + c->entries[i].offset, c->table_size); } if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i) } ret = bdrv_pwrite(bs->file, c->entries[i].offset, - qcow2_cache_get_table_addr(bs, c, i), s->cluster_size); + qcow2_cache_get_table_addr(bs, c, i), c->table_size); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, trace_qcow2_cache_get(qemu_coroutine_self(), c == s->l2_table_cache, offset, read_from_disk); - if (offset_into_cluster(s, offset)) { + if (!QEMU_IS_ALIGNED(offset, c->table_size)) { qcow2_signal_corruption(bs, true, -1, -1, "Cannot get entry from %s " "cache: Offset %#" PRIx64 " is unaligned", qcow2_cache_get_name(s, c), offset); @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, } /* Check if the table is already cached */ - i = lookup_index = (offset / s->cluster_size * 4) % c->size; + i = lookup_index = (offset / c->table_size * 4) % c->size; do { const Qcow2CachedTable *t = &c->entries[i]; if (t->offset == offset) { @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, ret = bdrv_pread(bs->file, offset, qcow2_cache_get_table_addr(bs, c, i), - s->cluster_size); + c->table_size); if (ret < 0) { return ret; } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was only using the BlockDriverState parameter to get the cache table size (since it was equal to the cluster size). This is no longer necessary so this parameter can be removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: e1f943a9e89e1deb876f45de1bb22419ccdb6ad3.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cache.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ struct Qcow2Cache { uint64_t cache_clean_lru_counter; }; -static inline void *qcow2_cache_get_table_addr(BlockDriverState *bs, - Qcow2Cache *c, int table) +static inline void *qcow2_cache_get_table_addr(Qcow2Cache *c, int table) { return (uint8_t *) c->table_array + (size_t) table * c->table_size; } @@ -XXX,XX +XXX,XX @@ static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c, { /* Using MADV_DONTNEED to discard memory is a Linux-specific feature */ #ifdef CONFIG_LINUX - void *t = qcow2_cache_get_table_addr(bs, c, i); + void *t = qcow2_cache_get_table_addr(c, i); int align = getpagesize(); size_t mem_size = (size_t) c->table_size * num_tables; size_t offset = QEMU_ALIGN_UP((uintptr_t) t, align) - (uintptr_t) t; @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i) } ret = bdrv_pwrite(bs->file, c->entries[i].offset, - qcow2_cache_get_table_addr(bs, c, i), c->table_size); + qcow2_cache_get_table_addr(c, i), c->table_size); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, } ret = bdrv_pread(bs->file, offset, - qcow2_cache_get_table_addr(bs, c, i), + qcow2_cache_get_table_addr(c, i), c->table_size); if (ret < 0) { return ret; @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, /* And return the right table */ found: c->entries[i].ref++; - *table = qcow2_cache_get_table_addr(bs, c, i); + *table = qcow2_cache_get_table_addr(c, i); trace_qcow2_cache_get_done(qemu_coroutine_self(), c == s->l2_table_cache, i); @@ -XXX,XX +XXX,XX @@ void *qcow2_cache_is_table_offset(BlockDriverState *bs, Qcow2Cache *c, for (i = 0; i < c->size; i++) { if (c->entries[i].offset == offset) { - return qcow2_cache_get_table_addr(bs, c, i); + return qcow2_cache_get_table_addr(c, i); } } return NULL; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was only using the BlockDriverState parameter to get the cache table size (since it was equal to the cluster size). This is no longer necessary so this parameter can be removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: da3575d47c9a181a2cfd4715e53dd84a2c651017.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cache.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ static inline void *qcow2_cache_get_table_addr(Qcow2Cache *c, int table) return (uint8_t *) c->table_array + (size_t) table * c->table_size; } -static inline int qcow2_cache_get_table_idx(BlockDriverState *bs, - Qcow2Cache *c, void *table) +static inline int qcow2_cache_get_table_idx(Qcow2Cache *c, void *table) { ptrdiff_t table_offset = (uint8_t *) table - (uint8_t *) c->table_array; int idx = table_offset / c->table_size; @@ -XXX,XX +XXX,XX @@ int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, void qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table) { - int i = qcow2_cache_get_table_idx(bs, c, *table); + int i = qcow2_cache_get_table_idx(c, *table); c->entries[i].ref--; *table = NULL; @@ -XXX,XX +XXX,XX @@ void qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table) void qcow2_cache_entry_mark_dirty(BlockDriverState *bs, Qcow2Cache *c, void *table) { - int i = qcow2_cache_get_table_idx(bs, c, table); + int i = qcow2_cache_get_table_idx(c, table); assert(c->entries[i].offset != 0); c->entries[i].dirty = true; } @@ -XXX,XX +XXX,XX @@ void *qcow2_cache_is_table_offset(BlockDriverState *bs, Qcow2Cache *c, void qcow2_cache_discard(BlockDriverState *bs, Qcow2Cache *c, void *table) { - int i = qcow2_cache_get_table_idx(bs, c, table); + int i = qcow2_cache_get_table_idx(c, table); assert(c->entries[i].ref == 0); -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was only using the BlockDriverState parameter to get the cache table size (since it was equal to the cluster size). This is no longer necessary so this parameter can be removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 7c1b262344375d52544525f85bbbf0548d5ba575.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cache.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ static inline const char *qcow2_cache_get_name(BDRVQcow2State *s, Qcow2Cache *c) } } -static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c, - int i, int num_tables) +static void qcow2_cache_table_release(Qcow2Cache *c, int i, int num_tables) { /* Using MADV_DONTNEED to discard memory is a Linux-specific feature */ #ifdef CONFIG_LINUX @@ -XXX,XX +XXX,XX @@ void qcow2_cache_clean_unused(BlockDriverState *bs, Qcow2Cache *c) } if (to_clean > 0) { - qcow2_cache_table_release(bs, c, i - to_clean, to_clean); + qcow2_cache_table_release(c, i - to_clean, to_clean); } } @@ -XXX,XX +XXX,XX @@ int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c) c->entries[i].lru_counter = 0; } - qcow2_cache_table_release(bs, c, 0, c->size); + qcow2_cache_table_release(c, 0, c->size); c->lru_counter = 0; @@ -XXX,XX +XXX,XX @@ void qcow2_cache_discard(BlockDriverState *bs, Qcow2Cache *c, void *table) c->entries[i].lru_counter = 0; c->entries[i].dirty = false; - qcow2_cache_table_release(bs, c, i, 1); + qcow2_cache_table_release(c, i, 1); } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was only using the BlockDriverState parameter to pass it to qcow2_cache_get_table_idx(). This is no longer necessary so this parameter can be removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 5c40516a91782b083c1428b7b6a41bb9e2679bfb.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 3 +-- block/qcow2-cache.c | 3 +-- block/qcow2-cluster.c | 12 ++++++------ block/qcow2-refcount.c | 14 ++++++-------- 4 files changed, 14 insertions(+), 18 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_read_snapshots(BlockDriverState *bs); Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables); int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c); -void qcow2_cache_entry_mark_dirty(BlockDriverState *bs, Qcow2Cache *c, - void *table); +void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table); int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c); int qcow2_cache_write(BlockDriverState *bs, Qcow2Cache *c); int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c, diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ void qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table) assert(c->entries[i].ref >= 0); } -void qcow2_cache_entry_mark_dirty(BlockDriverState *bs, Qcow2Cache *c, - void *table) +void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table) { int i = qcow2_cache_get_table_idx(c, table); assert(c->entries[i].offset != 0); diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table) BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_WRITE); trace_qcow2_l2_allocate_write_l2(bs, l1_index); - qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); ret = qcow2_cache_flush(bs, s->l2_table_cache); if (ret < 0) { goto fail; @@ -XXX,XX +XXX,XX @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, /* compressed clusters never have the copied flag */ BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE_COMPRESSED); - qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); l2_table[l2_index] = cpu_to_be64(cluster_offset); qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); @@ -XXX,XX +XXX,XX @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m) if (ret < 0) { goto err; } - qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); assert(l2_index + m->nb_clusters <= s->l2_size); for (i = 0; i < m->nb_clusters; i++) { @@ -XXX,XX +XXX,XX @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset, } /* First remove L2 entries */ - qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); if (!full_discard && s->qcow_version >= 3) { l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO); } else { @@ -XXX,XX +XXX,XX @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset, continue; } - qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); if (cluster_type == QCOW2_CLUSTER_COMPRESSED || unmap) { l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO); qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST); @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, if (is_active_l1) { if (l2_dirty) { - qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); qcow2_cache_depends_on_flush(s->l2_table_cache); } qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ static int alloc_refcount_block(BlockDriverState *bs, /* Now the new refcount block needs to be written to disk */ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE); - qcow2_cache_entry_mark_dirty(bs, s->refcount_block_cache, *refcount_block); + qcow2_cache_entry_mark_dirty(s->refcount_block_cache, *refcount_block); ret = qcow2_cache_flush(bs, s->refcount_block_cache); if (ret < 0) { goto fail; @@ -XXX,XX +XXX,XX @@ int64_t qcow2_refcount_area(BlockDriverState *bs, uint64_t start_offset, goto fail; } memset(refblock_data, 0, s->cluster_size); - qcow2_cache_entry_mark_dirty(bs, s->refcount_block_cache, + qcow2_cache_entry_mark_dirty(s->refcount_block_cache, refblock_data); new_table[i] = block_offset; @@ -XXX,XX +XXX,XX @@ int64_t qcow2_refcount_area(BlockDriverState *bs, uint64_t start_offset, s->set_refcount(refblock_data, j, 1); } - qcow2_cache_entry_mark_dirty(bs, s->refcount_block_cache, + qcow2_cache_entry_mark_dirty(s->refcount_block_cache, refblock_data); } @@ -XXX,XX +XXX,XX @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs, } old_table_index = table_index; - qcow2_cache_entry_mark_dirty(bs, s->refcount_block_cache, - refcount_block); + qcow2_cache_entry_mark_dirty(s->refcount_block_cache, refcount_block); /* we can update the count and save it */ block_index = cluster_index & (s->refcount_block_size - 1); @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, s->refcount_block_cache); } l2_table[j] = cpu_to_be64(entry); - qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, - l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); } } @@ -XXX,XX +XXX,XX @@ static int qcow2_discard_refcount_block(BlockDriverState *bs, } s->set_refcount(refblock, block_index, 0); - qcow2_cache_entry_mark_dirty(bs, s->refcount_block_cache, refblock); + qcow2_cache_entry_mark_dirty(s->refcount_block_cache, refblock); qcow2_cache_put(bs, s->refcount_block_cache, &refblock); -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was only using the BlockDriverState parameter to pass it to qcow2_cache_get_table_idx(). This is no longer necessary so this parameter can be removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 6f98155489054a457563da77cdad1a66ebb3e896.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 2 +- block/qcow2-cache.c | 2 +- block/qcow2-cluster.c | 28 ++++++++++++++-------------- block/qcow2-refcount.c | 30 +++++++++++++++--------------- 4 files changed, 31 insertions(+), 31 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, void **table); int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, void **table); -void qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table); +void qcow2_cache_put(Qcow2Cache *c, void **table); void *qcow2_cache_is_table_offset(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset); void qcow2_cache_discard(BlockDriverState *bs, Qcow2Cache *c, void *table); diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, return qcow2_cache_do_get(bs, c, offset, table, false); } -void qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table) +void qcow2_cache_put(Qcow2Cache *c, void **table) { int i = qcow2_cache_get_table_idx(c, *table); diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table) memcpy(l2_table, old_table, s->cluster_size); - qcow2_cache_put(bs, s->l2_table_cache, (void **) &old_table); + qcow2_cache_put(s->l2_table_cache, (void **) &old_table); } /* write the l2 table to the file */ @@ -XXX,XX +XXX,XX @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table) fail: trace_qcow2_l2_allocate_done(bs, l1_index, ret); if (l2_table != NULL) { - qcow2_cache_put(bs, s->l2_table_cache, (void**) table); + qcow2_cache_put(s->l2_table_cache, (void **) table); } s->l1_table[l1_index] = old_l2_offset; if (l2_offset > 0) { @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, abort(); } - qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); bytes_available = (int64_t)c * s->cluster_size; @@ -XXX,XX +XXX,XX @@ out: return type; fail: - qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table); + qcow2_cache_put(s->l2_table_cache, (void **)&l2_table); return ret; } @@ -XXX,XX +XXX,XX @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, * allocated. */ cluster_offset = be64_to_cpu(l2_table[l2_index]); if (cluster_offset & L2E_OFFSET_MASK) { - qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); return 0; } cluster_offset = qcow2_alloc_bytes(bs, compressed_size); if (cluster_offset < 0) { - qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); return 0; } @@ -XXX,XX +XXX,XX @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE_COMPRESSED); qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); l2_table[l2_index] = cpu_to_be64(cluster_offset); - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); return cluster_offset; } @@ -XXX,XX +XXX,XX @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m) } - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); /* * If this was a COW, we need to decrease the refcount of the old cluster. @@ -XXX,XX +XXX,XX @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset, /* Cleanup */ out: - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); /* Only return a host offset if we actually made progress. Otherwise we * would make requirements for handle_alloc() that it can't fulfill */ @@ -XXX,XX +XXX,XX @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset, keep_old_clusters = true; } - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); if (!alloc_cluster_offset) { /* Allocate, if necessary at a given offset in the image file */ @@ -XXX,XX +XXX,XX @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset, qcow2_free_any_clusters(bs, old_l2_entry, 1, type); } - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); return nb_clusters; } @@ -XXX,XX +XXX,XX @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset, } } - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); return nb_clusters; } @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); qcow2_cache_depends_on_flush(s->l2_table_cache); } - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); } else { if (l2_dirty) { ret = qcow2_pre_write_overlap_check(bs, @@ -XXX,XX +XXX,XX @@ fail: if (!is_active_l1) { qemu_vfree(l2_table); } else { - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); } } return ret; diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index, block_index = cluster_index & (s->refcount_block_size - 1); *refcount = s->get_refcount(refcount_block, block_index); - qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block); + qcow2_cache_put(s->refcount_block_cache, &refcount_block); return 0; } @@ -XXX,XX +XXX,XX @@ static int alloc_refcount_block(BlockDriverState *bs, return -EAGAIN; } - qcow2_cache_put(bs, s->refcount_block_cache, refcount_block); + qcow2_cache_put(s->refcount_block_cache, refcount_block); /* * If we come here, we need to grow the refcount table. Again, a new @@ -XXX,XX +XXX,XX @@ static int alloc_refcount_block(BlockDriverState *bs, fail: if (*refcount_block != NULL) { - qcow2_cache_put(bs, s->refcount_block_cache, refcount_block); + qcow2_cache_put(s->refcount_block_cache, refcount_block); } return ret; } @@ -XXX,XX +XXX,XX @@ int64_t qcow2_refcount_area(BlockDriverState *bs, uint64_t start_offset, refblock_data); } - qcow2_cache_put(bs, s->refcount_block_cache, &refblock_data); + qcow2_cache_put(s->refcount_block_cache, &refblock_data); } assert(block_offset == table_offset); @@ -XXX,XX +XXX,XX @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs, /* Load the refcount block and allocate it if needed */ if (table_index != old_table_index) { if (refcount_block) { - qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block); + qcow2_cache_put(s->refcount_block_cache, &refcount_block); } ret = alloc_refcount_block(bs, cluster_index, &refcount_block); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs, table = qcow2_cache_is_table_offset(bs, s->refcount_block_cache, offset); if (table != NULL) { - qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block); + qcow2_cache_put(s->refcount_block_cache, &refcount_block); qcow2_cache_discard(bs, s->refcount_block_cache, table); } @@ -XXX,XX +XXX,XX @@ fail: /* Write last changed block to disk */ if (refcount_block) { - qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block); + qcow2_cache_put(s->refcount_block_cache, &refcount_block); } /* @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, } } - qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); if (addend != 0) { ret = qcow2_update_cluster_refcount(bs, l2_offset >> @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, ret = bdrv_flush(bs); fail: if (l2_table) { - qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); } s->cache_discards = false; @@ -XXX,XX +XXX,XX @@ static int walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable, new_reftable_size, new_refblock, new_refblock_empty, allocated, errp); if (ret < 0) { - qcow2_cache_put(bs, s->refcount_block_cache, &refblock); + qcow2_cache_put(s->refcount_block_cache, &refblock); return ret; } @@ -XXX,XX +XXX,XX @@ static int walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable, if (new_refcount_bits < 64 && refcount >> new_refcount_bits) { uint64_t offset; - qcow2_cache_put(bs, s->refcount_block_cache, &refblock); + qcow2_cache_put(s->refcount_block_cache, &refblock); offset = ((reftable_index << s->refcount_block_bits) + refblock_index) << s->cluster_bits; @@ -XXX,XX +XXX,XX @@ static int walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable, new_refblock_empty = new_refblock_empty && refcount == 0; } - qcow2_cache_put(bs, s->refcount_block_cache, &refblock); + qcow2_cache_put(s->refcount_block_cache, &refblock); } else { /* No refblock means every refcount is 0 */ for (refblock_index = 0; refblock_index < s->refcount_block_size; @@ -XXX,XX +XXX,XX @@ static int qcow2_discard_refcount_block(BlockDriverState *bs, offset_to_reftable_index(s, discard_block_offs), discard_block_offs, s->get_refcount(refblock, block_index)); - qcow2_cache_put(bs, s->refcount_block_cache, &refblock); + qcow2_cache_put(s->refcount_block_cache, &refblock); return -EINVAL; } s->set_refcount(refblock, block_index, 0); qcow2_cache_entry_mark_dirty(s->refcount_block_cache, refblock); - qcow2_cache_put(bs, s->refcount_block_cache, &refblock); + qcow2_cache_put(s->refcount_block_cache, &refblock); if (cluster_index < s->free_cluster_index) { s->free_cluster_index = cluster_index; @@ -XXX,XX +XXX,XX @@ int qcow2_shrink_reftable(BlockDriverState *bs) } else { unused_block = buffer_is_zero(refblock, s->cluster_size); } - qcow2_cache_put(bs, s->refcount_block_cache, &refblock); + qcow2_cache_put(s->refcount_block_cache, &refblock); reftable_tmp[i] = unused_block ? 0 : cpu_to_be64(s->refcount_table[i]); } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was never using the BlockDriverState parameter so it can be safely removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 49c74fe8b3aead9056e61a85b145ce787d06262b.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 2 +- block/qcow2-cache.c | 2 +- block/qcow2.c | 16 ++++++++-------- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_read_snapshots(BlockDriverState *bs); /* qcow2-cache.c functions */ Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables); -int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c); +int qcow2_cache_destroy(Qcow2Cache *c); void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table); int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c); diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables) return c; } -int qcow2_cache_destroy(BlockDriverState *bs, Qcow2Cache *c) +int qcow2_cache_destroy(Qcow2Cache *c) { int i; diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static void qcow2_update_options_commit(BlockDriverState *bs, int i; if (s->l2_table_cache) { - qcow2_cache_destroy(bs, s->l2_table_cache); + qcow2_cache_destroy(s->l2_table_cache); } if (s->refcount_block_cache) { - qcow2_cache_destroy(bs, s->refcount_block_cache); + qcow2_cache_destroy(s->refcount_block_cache); } s->l2_table_cache = r->l2_table_cache; s->refcount_block_cache = r->refcount_block_cache; @@ -XXX,XX +XXX,XX @@ static void qcow2_update_options_abort(BlockDriverState *bs, Qcow2ReopenState *r) { if (r->l2_table_cache) { - qcow2_cache_destroy(bs, r->l2_table_cache); + qcow2_cache_destroy(r->l2_table_cache); } if (r->refcount_block_cache) { - qcow2_cache_destroy(bs, r->refcount_block_cache); + qcow2_cache_destroy(r->refcount_block_cache); } qapi_free_QCryptoBlockOpenOptions(r->crypto_opts); } @@ -XXX,XX +XXX,XX @@ static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags, s->l1_table = NULL; cache_clean_timer_del(bs); if (s->l2_table_cache) { - qcow2_cache_destroy(bs, s->l2_table_cache); + qcow2_cache_destroy(s->l2_table_cache); } if (s->refcount_block_cache) { - qcow2_cache_destroy(bs, s->refcount_block_cache); + qcow2_cache_destroy(s->refcount_block_cache); } qcrypto_block_free(s->crypto); qapi_free_QCryptoBlockOpenOptions(s->crypto_opts); @@ -XXX,XX +XXX,XX @@ static void qcow2_close(BlockDriverState *bs) } cache_clean_timer_del(bs); - qcow2_cache_destroy(bs, s->l2_table_cache); - qcow2_cache_destroy(bs, s->refcount_block_cache); + qcow2_cache_destroy(s->l2_table_cache); + qcow2_cache_destroy(s->refcount_block_cache); qcrypto_block_free(s->crypto); s->crypto = NULL; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was only using the BlockDriverState parameter to pass it to qcow2_cache_table_release(). This is no longer necessary so this parameter can be removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: b74f17591af52f201de0ea3a3b2dd0a81932334d.1517840876.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 2 +- block/qcow2-cache.c | 2 +- block/qcow2.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c, Qcow2Cache *dependency); void qcow2_cache_depends_on_flush(Qcow2Cache *c); -void qcow2_cache_clean_unused(BlockDriverState *bs, Qcow2Cache *c); +void qcow2_cache_clean_unused(Qcow2Cache *c); int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c); int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ static inline bool can_clean_entry(Qcow2Cache *c, int i) t->lru_counter <= c->cache_clean_lru_counter; } -void qcow2_cache_clean_unused(BlockDriverState *bs, Qcow2Cache *c) +void qcow2_cache_clean_unused(Qcow2Cache *c) { int i = 0; while (i < c->size) { diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static void cache_clean_timer_cb(void *opaque) { BlockDriverState *bs = opaque; BDRVQcow2State *s = bs->opaque; - qcow2_cache_clean_unused(bs, s->l2_table_cache); - qcow2_cache_clean_unused(bs, s->refcount_block_cache); + qcow2_cache_clean_unused(s->l2_table_cache); + qcow2_cache_clean_unused(s->refcount_block_cache); timer_mod(s->cache_clean_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + (int64_t) s->cache_clean_interval * 1000); } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was only using the BlockDriverState parameter to pass it to qcow2_cache_get_table_idx() and qcow2_cache_table_release(). This is no longer necessary so this parameter can be removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 9724f7e38e763ad3be32627c6b7fe8df9edb1476.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 2 +- block/qcow2-cache.c | 2 +- block/qcow2-refcount.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, void qcow2_cache_put(Qcow2Cache *c, void **table); void *qcow2_cache_is_table_offset(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset); -void qcow2_cache_discard(BlockDriverState *bs, Qcow2Cache *c, void *table); +void qcow2_cache_discard(Qcow2Cache *c, void *table); /* qcow2-bitmap.c functions */ int qcow2_check_bitmaps_refcounts(BlockDriverState *bs, BdrvCheckResult *res, diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ void *qcow2_cache_is_table_offset(BlockDriverState *bs, Qcow2Cache *c, return NULL; } -void qcow2_cache_discard(BlockDriverState *bs, Qcow2Cache *c, void *table) +void qcow2_cache_discard(Qcow2Cache *c, void *table) { int i = qcow2_cache_get_table_idx(c, table); diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs, offset); if (table != NULL) { qcow2_cache_put(s->refcount_block_cache, &refcount_block); - qcow2_cache_discard(bs, s->refcount_block_cache, table); + qcow2_cache_discard(s->refcount_block_cache, table); } table = qcow2_cache_is_table_offset(bs, s->l2_table_cache, offset); if (table != NULL) { - qcow2_cache_discard(bs, s->l2_table_cache, table); + qcow2_cache_discard(s->l2_table_cache, table); } if (s->discard_passthrough[type]) { @@ -XXX,XX +XXX,XX @@ static int qcow2_discard_refcount_block(BlockDriverState *bs, discard_block_offs); if (refblock) { /* discard refblock from the cache if refblock is cached */ - qcow2_cache_discard(bs, s->refcount_block_cache, refblock); + qcow2_cache_discard(s->refcount_block_cache, refblock); } update_refcount_discard(bs, discard_block_offs, s->cluster_size); -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function was only using the BlockDriverState parameter to pass it to qcow2_cache_get_table_addr(). This is no longer necessary so this parameter can be removed. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: eb0ed90affcf302e5a954bafb5931b5215483d3a.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 3 +-- block/qcow2-cache.c | 3 +-- block/qcow2-refcount.c | 6 +++--- 3 files changed, 5 insertions(+), 7 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, void **table); void qcow2_cache_put(Qcow2Cache *c, void **table); -void *qcow2_cache_is_table_offset(BlockDriverState *bs, Qcow2Cache *c, - uint64_t offset); +void *qcow2_cache_is_table_offset(Qcow2Cache *c, uint64_t offset); void qcow2_cache_discard(Qcow2Cache *c, void *table); /* qcow2-bitmap.c functions */ diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table) c->entries[i].dirty = true; } -void *qcow2_cache_is_table_offset(BlockDriverState *bs, Qcow2Cache *c, - uint64_t offset) +void *qcow2_cache_is_table_offset(Qcow2Cache *c, uint64_t offset) { int i; diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs, if (refcount == 0) { void *table; - table = qcow2_cache_is_table_offset(bs, s->refcount_block_cache, + table = qcow2_cache_is_table_offset(s->refcount_block_cache, offset); if (table != NULL) { qcow2_cache_put(s->refcount_block_cache, &refcount_block); qcow2_cache_discard(s->refcount_block_cache, table); } - table = qcow2_cache_is_table_offset(bs, s->l2_table_cache, offset); + table = qcow2_cache_is_table_offset(s->l2_table_cache, offset); if (table != NULL) { qcow2_cache_discard(s->l2_table_cache, table); } @@ -XXX,XX +XXX,XX @@ static int qcow2_discard_refcount_block(BlockDriverState *bs, s->free_cluster_index = cluster_index; } - refblock = qcow2_cache_is_table_offset(bs, s->refcount_block_cache, + refblock = qcow2_cache_is_table_offset(s->refcount_block_cache, discard_block_offs); if (refblock) { /* discard refblock from the cache if refblock is cached */ -- 2.13.6 From: Alberto Garcia <berto@igalia.com> Similar to offset_to_l2_index(), this function returns the index in the L1 table for a given guest offset. This is only used in a couple of places and it's not a particularly complex calculation, but it makes the code a bit more readable. Although in the qcow2_get_cluster_offset() case the old code was taking advantage of the l1_bits variable, we're going to get rid of the other uses of l1_bits in a later patch anyway, so it doesn't make sense to keep it just for this. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: a5f626fed526b7459a0425fad06d823d18df8522.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 5 +++++ block/qcow2-cluster.c | 4 ++-- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ static inline int64_t size_to_l1(BDRVQcow2State *s, int64_t size) return (size + (1ULL << shift) - 1) >> shift; } +static inline int offset_to_l1_index(BDRVQcow2State *s, uint64_t offset) +{ + return offset >> (s->l2_bits + s->cluster_bits); +} + static inline int offset_to_l2_index(BDRVQcow2State *s, int64_t offset) { return (offset >> s->cluster_bits) & (s->l2_size - 1); diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, /* seek to the l2 offset in the l1 table */ - l1_index = offset >> l1_bits; + l1_index = offset_to_l1_index(s, offset); if (l1_index >= s->l1_size) { type = QCOW2_CLUSTER_UNALLOCATED; goto out; @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, /* seek to the l2 offset in the l1 table */ - l1_index = offset >> (s->l2_bits + s->cluster_bits); + l1_index = offset_to_l1_index(s, offset); if (l1_index >= s->l1_size) { ret = qcow2_grow_l1_table(bs, l1_index + 1, false); if (ret < 0) { -- 2.13.6 From: Alberto Garcia <berto@igalia.com> The BDRVQcow2State structure contains an l2_size field, which stores the number of 64-bit entries in an L2 table. For efficiency reasons we want to be able to load slices instead of full L2 tables, so we need to know how many entries an L2 slice can hold. An L2 slice is the portion of an L2 table that is loaded by the qcow2 cache. At the moment that cache can only load complete tables, therefore an L2 slice has the same size as an L2 table (one cluster) and l2_size == l2_slice_size. Later we'll allow smaller slices, but until then we have to use this new l2_slice_size field to make the rest of the code ready for that. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: adb048595f9fb5dfb110c802a8b3c3be3b937f37.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 1 + block/qcow2.c | 3 +++ 2 files changed, 4 insertions(+) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ typedef struct BDRVQcow2State { int cluster_bits; int cluster_size; int cluster_sectors; + int l2_slice_size; int l2_bits; int l2_size; int l1_size; diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static void read_cache_sizes(BlockDriverState *bs, QemuOpts *opts, typedef struct Qcow2ReopenState { Qcow2Cache *l2_table_cache; Qcow2Cache *refcount_block_cache; + int l2_slice_size; /* Number of entries in a slice of the L2 table */ bool use_lazy_refcounts; int overlap_check; bool discard_passthrough[QCOW2_DISCARD_MAX]; @@ -XXX,XX +XXX,XX @@ static int qcow2_update_options_prepare(BlockDriverState *bs, } } + r->l2_slice_size = s->cluster_size / sizeof(uint64_t); r->l2_table_cache = qcow2_cache_create(bs, l2_cache_size); r->refcount_block_cache = qcow2_cache_create(bs, refcount_cache_size); if (r->l2_table_cache == NULL || r->refcount_block_cache == NULL) { @@ -XXX,XX +XXX,XX @@ static void qcow2_update_options_commit(BlockDriverState *bs, } s->l2_table_cache = r->l2_table_cache; s->refcount_block_cache = r->refcount_block_cache; + s->l2_slice_size = r->l2_slice_size; s->overlap_check = r->overlap_check; s->use_lazy_refcounts = r->use_lazy_refcounts; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> Similar to offset_to_l2_index(), this function takes a guest offset and returns the index in the L2 slice that contains its L2 entry. An L2 slice has currently the same size as an L2 table (one cluster), so both functions return the same value for now. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: a1c45c5c5a76146dd1712d8d1e7b409ad539c718.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ static inline int offset_to_l2_index(BDRVQcow2State *s, int64_t offset) return (offset >> s->cluster_bits) & (s->l2_size - 1); } +static inline int offset_to_l2_slice_index(BDRVQcow2State *s, int64_t offset) +{ + return (offset >> s->cluster_bits) & (s->l2_slice_size - 1); +} + static inline int64_t align_offset(int64_t offset, int n) { offset = (offset + n - 1) & ~(n - 1); -- 2.13.6 From: Alberto Garcia <berto@igalia.com> Each entry in the qcow2 L2 cache stores a full L2 table (which uses a complete cluster in the qcow2 image). A cluster is usually too large to be used efficiently as the size for a cache entry, so we want to decouple both values by allowing smaller cache entries. Therefore the qcow2 L2 cache will no longer return full L2 tables but slices instead. This patch updates l2_load() so it can handle L2 slices correctly. Apart from the offset of the L2 table (which we already had) we also need the guest offset in order to calculate which one of the slices we need. An L2 slice has currently the same size as an L2 table (one cluster), so for now this function will load exactly the same data as before. This patch also removes a stale comment about the return value being a pointer to the L2 table. This function returns an error code since 55c17e9821c474d5fcdebdc82ed2fc096777d611. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: b830aa1fc5b6f8e3cb331d006853fe22facca847.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, /* * l2_load * - * Loads a L2 table into memory. If the table is in the cache, the cache - * is used; otherwise the L2 table is loaded from the image file. + * @bs: The BlockDriverState + * @offset: A guest offset, used to calculate what slice of the L2 + * table to load. + * @l2_offset: Offset to the L2 table in the image file. + * @l2_slice: Location to store the pointer to the L2 slice. * - * Returns a pointer to the L2 table on success, or NULL if the read from - * the image file failed. + * Loads a L2 slice into memory (L2 slices are the parts of L2 tables + * that are loaded by the qcow2 cache). If the slice is in the cache, + * the cache is used; otherwise the L2 slice is loaded from the image + * file. */ - -static int l2_load(BlockDriverState *bs, uint64_t l2_offset, - uint64_t **l2_table) +static int l2_load(BlockDriverState *bs, uint64_t offset, + uint64_t l2_offset, uint64_t **l2_slice) { BDRVQcow2State *s = bs->opaque; + int start_of_slice = sizeof(uint64_t) * + (offset_to_l2_index(s, offset) - offset_to_l2_slice_index(s, offset)); - return qcow2_cache_get(bs, s->l2_table_cache, l2_offset, - (void **)l2_table); + return qcow2_cache_get(bs, s->l2_table_cache, l2_offset + start_of_slice, + (void **)l2_slice); } /* @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, /* load the l2 table in memory */ - ret = l2_load(bs, l2_offset, &l2_table); + ret = l2_load(bs, offset, l2_offset, &l2_table); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, if (s->l1_table[l1_index] & QCOW_OFLAG_COPIED) { /* load the l2 table in memory */ - ret = l2_load(bs, l2_offset, &l2_table); + ret = l2_load(bs, offset, l2_offset, &l2_table); if (ret < 0) { return ret; } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> Adding support for L2 slices to l2_allocate() needs (among other things) an extra loop that iterates over all slices of a new L2 table. Putting all changes in one patch would make it hard to read because all semantic changes would be mixed with pure indentation changes. To make things easier this patch simply creates a new block and changes the indentation of all lines of code inside it. Thus, all modifications in this patch are cosmetic. There are no semantic changes and no variables are renamed yet. The next patch will take care of that. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: d0d7dca8520db304524f52f49d8157595a707a35.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 53 ++++++++++++++++++++++++++++----------------------- 1 file changed, 29 insertions(+), 24 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table) /* allocate a new entry in the l2 cache */ trace_qcow2_l2_allocate_get_empty(bs, l1_index); - ret = qcow2_cache_get_empty(bs, s->l2_table_cache, l2_offset, (void**) table); - if (ret < 0) { - goto fail; - } + { + ret = qcow2_cache_get_empty(bs, s->l2_table_cache, + l2_offset, + (void **) table); + if (ret < 0) { + goto fail; + } - l2_table = *table; + l2_table = *table; - if ((old_l2_offset & L1E_OFFSET_MASK) == 0) { - /* if there was no old l2 table, clear the new table */ - memset(l2_table, 0, s->l2_size * sizeof(uint64_t)); - } else { - uint64_t* old_table; + if ((old_l2_offset & L1E_OFFSET_MASK) == 0) { + /* if there was no old l2 table, clear the new table */ + memset(l2_table, 0, s->l2_size * sizeof(uint64_t)); + } else { + uint64_t *old_table; - /* if there was an old l2 table, read it from the disk */ - BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_COW_READ); - ret = qcow2_cache_get(bs, s->l2_table_cache, - old_l2_offset & L1E_OFFSET_MASK, - (void**) &old_table); - if (ret < 0) { - goto fail; + /* if there was an old l2 table, read it from the disk */ + BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_COW_READ); + ret = qcow2_cache_get(bs, s->l2_table_cache, + old_l2_offset & L1E_OFFSET_MASK, + (void **) &old_table); + if (ret < 0) { + goto fail; + } + + memcpy(l2_table, old_table, s->cluster_size); + + qcow2_cache_put(s->l2_table_cache, (void **) &old_table); } - memcpy(l2_table, old_table, s->cluster_size); + /* write the l2 table to the file */ + BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_WRITE); - qcow2_cache_put(s->l2_table_cache, (void **) &old_table); + trace_qcow2_l2_allocate_write_l2(bs, l1_index); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); } - /* write the l2 table to the file */ - BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_WRITE); - - trace_qcow2_l2_allocate_write_l2(bs, l1_index); - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); ret = qcow2_cache_flush(bs, s->l2_table_cache); if (ret < 0) { goto fail; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This patch updates l2_allocate() to support the qcow2 cache returning L2 slices instead of full L2 tables. The old code simply gets an L2 table from the cache and initializes it with zeroes or with the contents of an existing table. With a cache that returns slices instead of tables the idea remains the same, but the code must now iterate over all the slices that are contained in an L2 table. Since now we're operating with slices the function can no longer return the newly-allocated table, so it's up to the caller to retrieve the appropriate L2 slice after calling l2_allocate() (note that with this patch the caller is still loading full L2 tables, but we'll deal with that in a separate patch). Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20fc0415bf0e011e29f6487ec86eb06a11f37445.1517840877.git.berto@igalia.com Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 56 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 34 insertions(+), 22 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index) * */ -static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table) +static int l2_allocate(BlockDriverState *bs, int l1_index) { BDRVQcow2State *s = bs->opaque; uint64_t old_l2_offset; - uint64_t *l2_table = NULL; + uint64_t *l2_slice = NULL; + unsigned slice, slice_size2, n_slices; int64_t l2_offset; int ret; @@ -XXX,XX +XXX,XX @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table) /* allocate a new entry in the l2 cache */ + slice_size2 = s->l2_slice_size * sizeof(uint64_t); + n_slices = s->cluster_size / slice_size2; + trace_qcow2_l2_allocate_get_empty(bs, l1_index); - { + for (slice = 0; slice < n_slices; slice++) { ret = qcow2_cache_get_empty(bs, s->l2_table_cache, - l2_offset, - (void **) table); + l2_offset + slice * slice_size2, + (void **) &l2_slice); if (ret < 0) { goto fail; } - l2_table = *table; - if ((old_l2_offset & L1E_OFFSET_MASK) == 0) { - /* if there was no old l2 table, clear the new table */ - memset(l2_table, 0, s->l2_size * sizeof(uint64_t)); + /* if there was no old l2 table, clear the new slice */ + memset(l2_slice, 0, slice_size2); } else { - uint64_t *old_table; + uint64_t *old_slice; + uint64_t old_l2_slice_offset = + (old_l2_offset & L1E_OFFSET_MASK) + slice * slice_size2; - /* if there was an old l2 table, read it from the disk */ + /* if there was an old l2 table, read a slice from the disk */ BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_COW_READ); - ret = qcow2_cache_get(bs, s->l2_table_cache, - old_l2_offset & L1E_OFFSET_MASK, - (void **) &old_table); + ret = qcow2_cache_get(bs, s->l2_table_cache, old_l2_slice_offset, + (void **) &old_slice); if (ret < 0) { goto fail; } - memcpy(l2_table, old_table, s->cluster_size); + memcpy(l2_slice, old_slice, slice_size2); - qcow2_cache_put(s->l2_table_cache, (void **) &old_table); + qcow2_cache_put(s->l2_table_cache, (void **) &old_slice); } - /* write the l2 table to the file */ + /* write the l2 slice to the file */ BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_WRITE); trace_qcow2_l2_allocate_write_l2(bs, l1_index); - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); } ret = qcow2_cache_flush(bs, s->l2_table_cache); @@ -XXX,XX +XXX,XX @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table) goto fail; } - *table = l2_table; trace_qcow2_l2_allocate_done(bs, l1_index, 0); return 0; fail: trace_qcow2_l2_allocate_done(bs, l1_index, ret); - if (l2_table != NULL) { - qcow2_cache_put(s->l2_table_cache, (void **) table); + if (l2_slice != NULL) { + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); } s->l1_table[l1_index] = old_l2_offset; if (l2_offset > 0) { @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, } } else { /* First allocate a new L2 table (and do COW if needed) */ - ret = l2_allocate(bs, l1_index, &l2_table); + ret = l2_allocate(bs, l1_index); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t), QCOW2_DISCARD_OTHER); } + + /* Get the offset of the newly-allocated l2 table */ + l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK; + assert(offset_into_cluster(s, l2_offset) == 0); + /* Load the l2 table in memory */ + ret = l2_load(bs, offset, l2_offset, &l2_table); + if (ret < 0) { + return ret; + } } /* find the cluster offset for the given disk offset */ -- 2.13.6 From: Alberto Garcia <berto@igalia.com> After the previous patch we're now always using l2_load() in get_cluster_table() regardless of whether a new L2 table has to be allocated or not. This patch refactors that part of the code to use one single l2_load() call. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: ce31758c4a1fadccea7a6ccb93951eb01d95fd4c.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, return -EIO; } - /* seek the l2 table of the given l2 offset */ - - if (s->l1_table[l1_index] & QCOW_OFLAG_COPIED) { - /* load the l2 table in memory */ - ret = l2_load(bs, offset, l2_offset, &l2_table); - if (ret < 0) { - return ret; - } - } else { + if (!(s->l1_table[l1_index] & QCOW_OFLAG_COPIED)) { /* First allocate a new L2 table (and do COW if needed) */ ret = l2_allocate(bs, l1_index); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, /* Get the offset of the newly-allocated l2 table */ l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK; assert(offset_into_cluster(s, l2_offset) == 0); - /* Load the l2 table in memory */ - ret = l2_load(bs, offset, l2_offset, &l2_table); - if (ret < 0) { - return ret; - } + } + + /* load the l2 table in memory */ + ret = l2_load(bs, offset, l2_offset, &l2_table); + if (ret < 0) { + return ret; } /* find the cluster offset for the given disk offset */ -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This patch updates get_cluster_table() to return L2 slices instead of full L2 tables. The code itself needs almost no changes, it only needs to call offset_to_l2_slice_index() instead of offset_to_l2_index(). This patch also renames all the relevant variables and the documentation. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 64cf064c0021ba315d3f3032da0f95db1b615f33.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ fail: * get_cluster_table * * for a given disk offset, load (and allocate if needed) - * the l2 table. + * the appropriate slice of its l2 table. * - * the cluster index in the l2 table is given to the caller. + * the cluster index in the l2 slice is given to the caller. * * Returns 0 on success, -errno in failure case */ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, - uint64_t **new_l2_table, + uint64_t **new_l2_slice, int *new_l2_index) { BDRVQcow2State *s = bs->opaque; unsigned int l2_index; uint64_t l1_index, l2_offset; - uint64_t *l2_table = NULL; + uint64_t *l2_slice = NULL; int ret; /* seek to the l2 offset in the l1 table */ @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, assert(offset_into_cluster(s, l2_offset) == 0); } - /* load the l2 table in memory */ - ret = l2_load(bs, offset, l2_offset, &l2_table); + /* load the l2 slice in memory */ + ret = l2_load(bs, offset, l2_offset, &l2_slice); if (ret < 0) { return ret; } /* find the cluster offset for the given disk offset */ - l2_index = offset_to_l2_index(s, offset); + l2_index = offset_to_l2_slice_index(s, offset); - *new_l2_table = l2_table; + *new_l2_slice = l2_slice; *new_l2_index = l2_index; return 0; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> qcow2_get_cluster_offset() checks how many contiguous bytes are available at a given offset. The returned number of bytes is limited by the amount that can be addressed without having to load more than one L2 table. Since we'll be loading L2 slices instead of full tables this patch changes the limit accordingly using the size of the L2 slice for the calculations instead of the full table size. One consequence of this is that with small L2 slices operations such as 'qemu-img map' will need to iterate in more steps because each qcow2_get_cluster_offset() call will potentially return a smaller number. However the code is already prepared for that so this doesn't break semantics. The l2_table variable is also renamed to l2_slice to reflect this, and offset_to_l2_index() is replaced with offset_to_l2_slice_index(). Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 6b602260acb33da56ed6af9611731cb7acd110eb.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, { BDRVQcow2State *s = bs->opaque; unsigned int l2_index; - uint64_t l1_index, l2_offset, *l2_table; - int l1_bits, c; + uint64_t l1_index, l2_offset, *l2_slice; + int c; unsigned int offset_in_cluster; uint64_t bytes_available, bytes_needed, nb_clusters; QCow2ClusterType type; @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, offset_in_cluster = offset_into_cluster(s, offset); bytes_needed = (uint64_t) *bytes + offset_in_cluster; - l1_bits = s->l2_bits + s->cluster_bits; - /* compute how many bytes there are between the start of the cluster - * containing offset and the end of the l1 entry */ - bytes_available = (1ULL << l1_bits) - (offset & ((1ULL << l1_bits) - 1)) - + offset_in_cluster; + * containing offset and the end of the l2 slice that contains + * the entry pointing to it */ + bytes_available = + ((uint64_t) (s->l2_slice_size - offset_to_l2_slice_index(s, offset))) + << s->cluster_bits; if (bytes_needed > bytes_available) { bytes_needed = bytes_available; @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, return -EIO; } - /* load the l2 table in memory */ + /* load the l2 slice in memory */ - ret = l2_load(bs, offset, l2_offset, &l2_table); + ret = l2_load(bs, offset, l2_offset, &l2_slice); if (ret < 0) { return ret; } /* find the cluster offset for the given disk offset */ - l2_index = offset_to_l2_index(s, offset); - *cluster_offset = be64_to_cpu(l2_table[l2_index]); + l2_index = offset_to_l2_slice_index(s, offset); + *cluster_offset = be64_to_cpu(l2_slice[l2_index]); nb_clusters = size_to_clusters(s, bytes_needed); /* bytes_needed <= *bytes + offset_in_cluster, both of which are unsigned @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, case QCOW2_CLUSTER_UNALLOCATED: /* how many empty clusters ? */ c = count_contiguous_clusters_unallocated(nb_clusters, - &l2_table[l2_index], type); + &l2_slice[l2_index], type); *cluster_offset = 0; break; case QCOW2_CLUSTER_ZERO_ALLOC: case QCOW2_CLUSTER_NORMAL: /* how many allocated clusters ? */ c = count_contiguous_clusters(nb_clusters, s->cluster_size, - &l2_table[l2_index], QCOW_OFLAG_ZERO); + &l2_slice[l2_index], QCOW_OFLAG_ZERO); *cluster_offset &= L2E_OFFSET_MASK; if (offset_into_cluster(s, *cluster_offset)) { qcow2_signal_corruption(bs, true, -1, -1, @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, abort(); } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); bytes_available = (int64_t)c * s->cluster_size; @@ -XXX,XX +XXX,XX @@ out: return type; fail: - qcow2_cache_put(s->l2_table_cache, (void **)&l2_table); + qcow2_cache_put(s->l2_table_cache, (void **)&l2_slice); return ret; } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> There's a loop in this function that iterates over the L2 entries in a table, so now we need to assert that it remains within the limits of an L2 slice. Apart from that, this function doesn't need any additional changes, so this patch simply updates the variable name from l2_table to l2_slice. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: f9846a1c2efc51938e877e2a25852d9ab14797ff.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m) { BDRVQcow2State *s = bs->opaque; int i, j = 0, l2_index, ret; - uint64_t *old_cluster, *l2_table; + uint64_t *old_cluster, *l2_slice; uint64_t cluster_offset = m->alloc_offset; trace_qcow2_cluster_link_l2(qemu_coroutine_self(), m->nb_clusters); @@ -XXX,XX +XXX,XX @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m) s->refcount_block_cache); } - ret = get_cluster_table(bs, m->offset, &l2_table, &l2_index); + ret = get_cluster_table(bs, m->offset, &l2_slice, &l2_index); if (ret < 0) { goto err; } - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice); - assert(l2_index + m->nb_clusters <= s->l2_size); + assert(l2_index + m->nb_clusters <= s->l2_slice_size); for (i = 0; i < m->nb_clusters; i++) { /* if two concurrent writes happen to the same unallocated cluster * each write allocates separate cluster and writes data concurrently. @@ -XXX,XX +XXX,XX @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m) * cluster the second one has to do RMW (which is done above by * perform_cow()), update l2 table with its cluster pointer and free * old cluster. This is what this loop does */ - if (l2_table[l2_index + i] != 0) { - old_cluster[j++] = l2_table[l2_index + i]; + if (l2_slice[l2_index + i] != 0) { + old_cluster[j++] = l2_slice[l2_index + i]; } - l2_table[l2_index + i] = cpu_to_be64((cluster_offset + + l2_slice[l2_index + i] = cpu_to_be64((cluster_offset + (i << s->cluster_bits)) | QCOW_OFLAG_COPIED); } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); /* * If this was a COW, we need to decrease the refcount of the old cluster. -- 2.13.6 From: Alberto Garcia <berto@igalia.com> handle_copied() loads an L2 table and limits the number of checked clusters to the amount that fits inside that table. Since we'll be loading L2 slices instead of full tables we need to update that limit. Apart from that, this function doesn't need any additional changes, so this patch simply updates the variable name from l2_table to l2_slice. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 541ac001a7d6b86bab2392554bee53c2b312148c.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset, BDRVQcow2State *s = bs->opaque; int l2_index; uint64_t cluster_offset; - uint64_t *l2_table; + uint64_t *l2_slice; uint64_t nb_clusters; unsigned int keep_clusters; int ret; @@ -XXX,XX +XXX,XX @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset, == offset_into_cluster(s, *host_offset)); /* - * Calculate the number of clusters to look for. We stop at L2 table + * Calculate the number of clusters to look for. We stop at L2 slice * boundaries to keep things simple. */ nb_clusters = size_to_clusters(s, offset_into_cluster(s, guest_offset) + *bytes); - l2_index = offset_to_l2_index(s, guest_offset); - nb_clusters = MIN(nb_clusters, s->l2_size - l2_index); + l2_index = offset_to_l2_slice_index(s, guest_offset); + nb_clusters = MIN(nb_clusters, s->l2_slice_size - l2_index); assert(nb_clusters <= INT_MAX); /* Find L2 entry for the first involved cluster */ - ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index); + ret = get_cluster_table(bs, guest_offset, &l2_slice, &l2_index); if (ret < 0) { return ret; } - cluster_offset = be64_to_cpu(l2_table[l2_index]); + cluster_offset = be64_to_cpu(l2_slice[l2_index]); /* Check how many clusters are already allocated and don't need COW */ if (qcow2_get_cluster_type(cluster_offset) == QCOW2_CLUSTER_NORMAL @@ -XXX,XX +XXX,XX @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset, /* We keep all QCOW_OFLAG_COPIED clusters */ keep_clusters = count_contiguous_clusters(nb_clusters, s->cluster_size, - &l2_table[l2_index], + &l2_slice[l2_index], QCOW_OFLAG_COPIED | QCOW_OFLAG_ZERO); assert(keep_clusters <= nb_clusters); @@ -XXX,XX +XXX,XX @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset, /* Cleanup */ out: - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); /* Only return a host offset if we actually made progress. Otherwise we * would make requirements for handle_alloc() that it can't fulfill */ -- 2.13.6 From: Alberto Garcia <berto@igalia.com> handle_alloc() loads an L2 table and limits the number of checked clusters to the amount that fits inside that table. Since we'll be loading L2 slices instead of full tables we need to update that limit. Apart from that, this function doesn't need any additional changes, so this patch simply updates the variable name from l2_table to l2_slice. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: b243299c7136f7014c5af51665431ddbf5e99afd.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset, { BDRVQcow2State *s = bs->opaque; int l2_index; - uint64_t *l2_table; + uint64_t *l2_slice; uint64_t entry; uint64_t nb_clusters; int ret; @@ -XXX,XX +XXX,XX @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset, assert(*bytes > 0); /* - * Calculate the number of clusters to look for. We stop at L2 table + * Calculate the number of clusters to look for. We stop at L2 slice * boundaries to keep things simple. */ nb_clusters = size_to_clusters(s, offset_into_cluster(s, guest_offset) + *bytes); - l2_index = offset_to_l2_index(s, guest_offset); - nb_clusters = MIN(nb_clusters, s->l2_size - l2_index); + l2_index = offset_to_l2_slice_index(s, guest_offset); + nb_clusters = MIN(nb_clusters, s->l2_slice_size - l2_index); assert(nb_clusters <= INT_MAX); /* Find L2 entry for the first involved cluster */ - ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index); + ret = get_cluster_table(bs, guest_offset, &l2_slice, &l2_index); if (ret < 0) { return ret; } - entry = be64_to_cpu(l2_table[l2_index]); + entry = be64_to_cpu(l2_slice[l2_index]); /* For the moment, overwrite compressed clusters one by one */ if (entry & QCOW_OFLAG_COMPRESSED) { nb_clusters = 1; } else { - nb_clusters = count_cow_clusters(s, nb_clusters, l2_table, l2_index); + nb_clusters = count_cow_clusters(s, nb_clusters, l2_slice, l2_index); } /* This function is only called when there were no non-COW clusters, so if @@ -XXX,XX +XXX,XX @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset, * nb_clusters already to a range of COW clusters */ preallocated_nb_clusters = count_contiguous_clusters(nb_clusters, s->cluster_size, - &l2_table[l2_index], QCOW_OFLAG_COPIED); + &l2_slice[l2_index], QCOW_OFLAG_COPIED); assert(preallocated_nb_clusters > 0); nb_clusters = preallocated_nb_clusters; @@ -XXX,XX +XXX,XX @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset, keep_old_clusters = true; } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); if (!alloc_cluster_offset) { /* Allocate, if necessary at a given offset in the image file */ -- 2.13.6 From: Alberto Garcia <berto@igalia.com> discard_single_l2() limits the number of clusters to be discarded to the amount that fits inside an L2 table. Since we'll be loading L2 slices instead of full tables we need to update that limit. The function is renamed to discard_in_l2_slice() for clarity. Apart from that, this function doesn't need any additional changes, so this patch simply updates the variable name from l2_table to l2_slice. Signed-off-by: Alberto Garcia <berto@igalia.com> Message-id: 1cb44a5b68be5334cb01b97a3db3a3c5a43396e5.1517840877.git.berto@igalia.com Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset) /* * This discards as many clusters of nb_clusters as possible at once (i.e. - * all clusters in the same L2 table) and returns the number of discarded + * all clusters in the same L2 slice) and returns the number of discarded * clusters. */ -static int discard_single_l2(BlockDriverState *bs, uint64_t offset, - uint64_t nb_clusters, enum qcow2_discard_type type, - bool full_discard) +static int discard_in_l2_slice(BlockDriverState *bs, uint64_t offset, + uint64_t nb_clusters, + enum qcow2_discard_type type, bool full_discard) { BDRVQcow2State *s = bs->opaque; - uint64_t *l2_table; + uint64_t *l2_slice; int l2_index; int ret; int i; - ret = get_cluster_table(bs, offset, &l2_table, &l2_index); + ret = get_cluster_table(bs, offset, &l2_slice, &l2_index); if (ret < 0) { return ret; } - /* Limit nb_clusters to one L2 table */ - nb_clusters = MIN(nb_clusters, s->l2_size - l2_index); + /* Limit nb_clusters to one L2 slice */ + nb_clusters = MIN(nb_clusters, s->l2_slice_size - l2_index); assert(nb_clusters <= INT_MAX); for (i = 0; i < nb_clusters; i++) { uint64_t old_l2_entry; - old_l2_entry = be64_to_cpu(l2_table[l2_index + i]); + old_l2_entry = be64_to_cpu(l2_slice[l2_index + i]); /* * If full_discard is false, make sure that a discarded area reads back @@ -XXX,XX +XXX,XX @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset, } /* First remove L2 entries */ - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice); if (!full_discard && s->qcow_version >= 3) { - l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO); + l2_slice[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO); } else { - l2_table[l2_index + i] = cpu_to_be64(0); + l2_slice[l2_index + i] = cpu_to_be64(0); } /* Then decrease the refcount */ qcow2_free_any_clusters(bs, old_l2_entry, 1, type); } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); return nb_clusters; } @@ -XXX,XX +XXX,XX @@ int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset, s->cache_discards = true; - /* Each L2 table is handled by its own loop iteration */ + /* Each L2 slice is handled by its own loop iteration */ while (nb_clusters > 0) { - cleared = discard_single_l2(bs, offset, nb_clusters, type, - full_discard); + cleared = discard_in_l2_slice(bs, offset, nb_clusters, type, + full_discard); if (cleared < 0) { ret = cleared; goto fail; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> zero_single_l2() limits the number of clusters to be zeroed to the amount that fits inside an L2 table. Since we'll be loading L2 slices instead of full tables we need to update that limit. The function is renamed to zero_in_l2_slice() for clarity. Apart from that, this function doesn't need any additional changes, so this patch simply updates the variable name from l2_table to l2_slice. Signed-off-by: Alberto Garcia <berto@igalia.com> Message-id: ebc16e7e79fa6969d8975ef487d679794de4fbcc.1517840877.git.berto@igalia.com Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ fail: /* * This zeroes as many clusters of nb_clusters as possible at once (i.e. - * all clusters in the same L2 table) and returns the number of zeroed + * all clusters in the same L2 slice) and returns the number of zeroed * clusters. */ -static int zero_single_l2(BlockDriverState *bs, uint64_t offset, - uint64_t nb_clusters, int flags) +static int zero_in_l2_slice(BlockDriverState *bs, uint64_t offset, + uint64_t nb_clusters, int flags) { BDRVQcow2State *s = bs->opaque; - uint64_t *l2_table; + uint64_t *l2_slice; int l2_index; int ret; int i; bool unmap = !!(flags & BDRV_REQ_MAY_UNMAP); - ret = get_cluster_table(bs, offset, &l2_table, &l2_index); + ret = get_cluster_table(bs, offset, &l2_slice, &l2_index); if (ret < 0) { return ret; } - /* Limit nb_clusters to one L2 table */ - nb_clusters = MIN(nb_clusters, s->l2_size - l2_index); + /* Limit nb_clusters to one L2 slice */ + nb_clusters = MIN(nb_clusters, s->l2_slice_size - l2_index); assert(nb_clusters <= INT_MAX); for (i = 0; i < nb_clusters; i++) { uint64_t old_offset; QCow2ClusterType cluster_type; - old_offset = be64_to_cpu(l2_table[l2_index + i]); + old_offset = be64_to_cpu(l2_slice[l2_index + i]); /* * Minimize L2 changes if the cluster already reads back as @@ -XXX,XX +XXX,XX @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset, continue; } - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice); if (cluster_type == QCOW2_CLUSTER_COMPRESSED || unmap) { - l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO); + l2_slice[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO); qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST); } else { - l2_table[l2_index + i] |= cpu_to_be64(QCOW_OFLAG_ZERO); + l2_slice[l2_index + i] |= cpu_to_be64(QCOW_OFLAG_ZERO); } } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); return nb_clusters; } @@ -XXX,XX +XXX,XX @@ int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset, return -ENOTSUP; } - /* Each L2 table is handled by its own loop iteration */ + /* Each L2 slice is handled by its own loop iteration */ nb_clusters = size_to_clusters(s, bytes); s->cache_discards = true; while (nb_clusters > 0) { - cleared = zero_single_l2(bs, offset, nb_clusters, flags); + cleared = zero_in_l2_slice(bs, offset, nb_clusters, flags); if (cleared < 0) { ret = cleared; goto fail; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> Adding support for L2 slices to qcow2_update_snapshot_refcount() needs (among other things) an extra loop that iterates over all slices of each L2 table. Putting all changes in one patch would make it hard to read because all semantic changes would be mixed with pure indentation changes. To make things easier this patch simply creates a new block and changes the indentation of all lines of code inside it. Thus, all modifications in this patch are cosmetic. There are no semantic changes and no variables are renamed yet. The next patch will take care of that. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 8ffaa5e55bd51121f80e498f4045b64902a94293.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-refcount.c | 144 +++++++++++++++++++++++++------------------------ 1 file changed, 75 insertions(+), 69 deletions(-) diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, goto fail; } - ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, - (void**) &l2_table); - if (ret < 0) { - goto fail; - } + { + ret = qcow2_cache_get(bs, s->l2_table_cache, + l2_offset, + (void **) &l2_table); + if (ret < 0) { + goto fail; + } - for (j = 0; j < s->l2_size; j++) { - uint64_t cluster_index; - uint64_t offset; - - entry = be64_to_cpu(l2_table[j]); - old_entry = entry; - entry &= ~QCOW_OFLAG_COPIED; - offset = entry & L2E_OFFSET_MASK; - - switch (qcow2_get_cluster_type(entry)) { - case QCOW2_CLUSTER_COMPRESSED: - nb_csectors = ((entry >> s->csize_shift) & - s->csize_mask) + 1; - if (addend != 0) { - ret = update_refcount(bs, - (entry & s->cluster_offset_mask) & ~511, + for (j = 0; j < s->l2_size; j++) { + uint64_t cluster_index; + uint64_t offset; + + entry = be64_to_cpu(l2_table[j]); + old_entry = entry; + entry &= ~QCOW_OFLAG_COPIED; + offset = entry & L2E_OFFSET_MASK; + + switch (qcow2_get_cluster_type(entry)) { + case QCOW2_CLUSTER_COMPRESSED: + nb_csectors = ((entry >> s->csize_shift) & + s->csize_mask) + 1; + if (addend != 0) { + ret = update_refcount( + bs, (entry & s->cluster_offset_mask) & ~511, nb_csectors * 512, abs(addend), addend < 0, QCOW2_DISCARD_SNAPSHOT); - if (ret < 0) { + if (ret < 0) { + goto fail; + } + } + /* compressed clusters are never modified */ + refcount = 2; + break; + + case QCOW2_CLUSTER_NORMAL: + case QCOW2_CLUSTER_ZERO_ALLOC: + if (offset_into_cluster(s, offset)) { + qcow2_signal_corruption( + bs, true, -1, -1, "Cluster " + "allocation offset %#" PRIx64 + " unaligned (L2 offset: %#" + PRIx64 ", L2 index: %#x)", + offset, l2_offset, j); + ret = -EIO; goto fail; } - } - /* compressed clusters are never modified */ - refcount = 2; - break; - - case QCOW2_CLUSTER_NORMAL: - case QCOW2_CLUSTER_ZERO_ALLOC: - if (offset_into_cluster(s, offset)) { - qcow2_signal_corruption(bs, true, -1, -1, "Cluster " - "allocation offset %#" PRIx64 - " unaligned (L2 offset: %#" - PRIx64 ", L2 index: %#x)", - offset, l2_offset, j); - ret = -EIO; - goto fail; - } - cluster_index = offset >> s->cluster_bits; - assert(cluster_index); - if (addend != 0) { - ret = qcow2_update_cluster_refcount(bs, - cluster_index, abs(addend), addend < 0, - QCOW2_DISCARD_SNAPSHOT); + cluster_index = offset >> s->cluster_bits; + assert(cluster_index); + if (addend != 0) { + ret = qcow2_update_cluster_refcount( + bs, cluster_index, abs(addend), addend < 0, + QCOW2_DISCARD_SNAPSHOT); + if (ret < 0) { + goto fail; + } + } + + ret = qcow2_get_refcount(bs, cluster_index, &refcount); if (ret < 0) { goto fail; } - } + break; - ret = qcow2_get_refcount(bs, cluster_index, &refcount); - if (ret < 0) { - goto fail; - } - break; - - case QCOW2_CLUSTER_ZERO_PLAIN: - case QCOW2_CLUSTER_UNALLOCATED: - refcount = 0; - break; + case QCOW2_CLUSTER_ZERO_PLAIN: + case QCOW2_CLUSTER_UNALLOCATED: + refcount = 0; + break; - default: - abort(); - } + default: + abort(); + } - if (refcount == 1) { - entry |= QCOW_OFLAG_COPIED; - } - if (entry != old_entry) { - if (addend > 0) { - qcow2_cache_set_dependency(bs, s->l2_table_cache, - s->refcount_block_cache); + if (refcount == 1) { + entry |= QCOW_OFLAG_COPIED; + } + if (entry != old_entry) { + if (addend > 0) { + qcow2_cache_set_dependency(bs, s->l2_table_cache, + s->refcount_block_cache); + } + l2_table[j] = cpu_to_be64(entry); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, + l2_table); } - l2_table[j] = cpu_to_be64(entry); - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); } - } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + + } if (addend != 0) { ret = qcow2_update_cluster_refcount(bs, l2_offset >> -- 2.13.6 From: Alberto Garcia <berto@igalia.com> qcow2_update_snapshot_refcount() increases the refcount of all clusters of a given snapshot. In order to do that it needs to load all its L2 tables and iterate over their entries. Since we'll be loading L2 slices instead of full tables we need to add an extra loop that iterates over all slices of each L2 table. This function doesn't need any additional changes so apart from that this patch simply updates the variable name from l2_table to l2_slice. Signed-off-by: Alberto Garcia <berto@igalia.com> Message-id: 5f4db199b9637f4833b58487135124d70add8cf0.1517840877.git.berto@igalia.com Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-refcount.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, int64_t l1_table_offset, int l1_size, int addend) { BDRVQcow2State *s = bs->opaque; - uint64_t *l1_table, *l2_table, l2_offset, entry, l1_size2, refcount; + uint64_t *l1_table, *l2_slice, l2_offset, entry, l1_size2, refcount; bool l1_allocated = false; int64_t old_entry, old_l2_offset; + unsigned slice, slice_size2, n_slices; int i, j, l1_modified = 0, nb_csectors; int ret; assert(addend >= -1 && addend <= 1); - l2_table = NULL; + l2_slice = NULL; l1_table = NULL; l1_size2 = l1_size * sizeof(uint64_t); + slice_size2 = s->l2_slice_size * sizeof(uint64_t); + n_slices = s->cluster_size / slice_size2; s->cache_discards = true; @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, goto fail; } - { + for (slice = 0; slice < n_slices; slice++) { ret = qcow2_cache_get(bs, s->l2_table_cache, - l2_offset, - (void **) &l2_table); + l2_offset + slice * slice_size2, + (void **) &l2_slice); if (ret < 0) { goto fail; } - for (j = 0; j < s->l2_size; j++) { + for (j = 0; j < s->l2_slice_size; j++) { uint64_t cluster_index; uint64_t offset; - entry = be64_to_cpu(l2_table[j]); + entry = be64_to_cpu(l2_slice[j]); old_entry = entry; entry &= ~QCOW_OFLAG_COPIED; offset = entry & L2E_OFFSET_MASK; @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, case QCOW2_CLUSTER_NORMAL: case QCOW2_CLUSTER_ZERO_ALLOC: if (offset_into_cluster(s, offset)) { + /* Here l2_index means table (not slice) index */ + int l2_index = slice * s->l2_slice_size + j; qcow2_signal_corruption( bs, true, -1, -1, "Cluster " "allocation offset %#" PRIx64 " unaligned (L2 offset: %#" PRIx64 ", L2 index: %#x)", - offset, l2_offset, j); + offset, l2_offset, l2_index); ret = -EIO; goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, qcow2_cache_set_dependency(bs, s->l2_table_cache, s->refcount_block_cache); } - l2_table[j] = cpu_to_be64(entry); + l2_slice[j] = cpu_to_be64(entry); qcow2_cache_entry_mark_dirty(s->l2_table_cache, - l2_table); + l2_slice); } } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); - + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); } if (addend != 0) { @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, ret = bdrv_flush(bs); fail: - if (l2_table) { - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + if (l2_slice) { + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); } s->cache_discards = false; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> At the moment it doesn't really make a difference whether we call qcow2_get_refcount() before of after reading the L2 table, but if we want to support L2 slices we'll need to read the refcount first. This patch simply changes the order of those two operations to prepare for that. The patch with the actual semantic changes will be easier to read because of this. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 947a91d934053a2dbfef979aeb9568f57ef57c5d.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, goto fail; } + ret = qcow2_get_refcount(bs, l2_offset >> s->cluster_bits, + &l2_refcount); + if (ret < 0) { + goto fail; + } + if (is_active_l1) { /* get active L2 tables from cache */ ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, goto fail; } - ret = qcow2_get_refcount(bs, l2_offset >> s->cluster_bits, - &l2_refcount); - if (ret < 0) { - goto fail; - } - for (j = 0; j < s->l2_size; j++) { uint64_t l2_entry = be64_to_cpu(l2_table[j]); int64_t offset = l2_entry & L2E_OFFSET_MASK; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> Adding support for L2 slices to expand_zero_clusters_in_l1() needs (among other things) an extra loop that iterates over all slices of each L2 table. Putting all changes in one patch would make it hard to read because all semantic changes would be mixed with pure indentation changes. To make things easier this patch simply creates a new block and changes the indentation of all lines of code inside it. Thus, all modifications in this patch are cosmetic. There are no semantic changes and no variables are renamed yet. The next patch will take care of that. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: c2ae9f31ed5b6e591477ad4654448badd1c89d73.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 187 ++++++++++++++++++++++++++------------------------ 1 file changed, 96 insertions(+), 91 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, goto fail; } - if (is_active_l1) { - /* get active L2 tables from cache */ - ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, - (void **)&l2_table); - } else { - /* load inactive L2 tables from disk */ - ret = bdrv_read(bs->file, l2_offset / BDRV_SECTOR_SIZE, - (void *)l2_table, s->cluster_sectors); - } - if (ret < 0) { - goto fail; - } - - for (j = 0; j < s->l2_size; j++) { - uint64_t l2_entry = be64_to_cpu(l2_table[j]); - int64_t offset = l2_entry & L2E_OFFSET_MASK; - QCow2ClusterType cluster_type = qcow2_get_cluster_type(l2_entry); - - if (cluster_type != QCOW2_CLUSTER_ZERO_PLAIN && - cluster_type != QCOW2_CLUSTER_ZERO_ALLOC) { - continue; + { + if (is_active_l1) { + /* get active L2 tables from cache */ + ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, + (void **)&l2_table); + } else { + /* load inactive L2 tables from disk */ + ret = bdrv_read(bs->file, l2_offset / BDRV_SECTOR_SIZE, + (void *)l2_table, s->cluster_sectors); + } + if (ret < 0) { + goto fail; } - if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { - if (!bs->backing) { - /* not backed; therefore we can simply deallocate the - * cluster */ - l2_table[j] = 0; - l2_dirty = true; + for (j = 0; j < s->l2_size; j++) { + uint64_t l2_entry = be64_to_cpu(l2_table[j]); + int64_t offset = l2_entry & L2E_OFFSET_MASK; + QCow2ClusterType cluster_type = + qcow2_get_cluster_type(l2_entry); + + if (cluster_type != QCOW2_CLUSTER_ZERO_PLAIN && + cluster_type != QCOW2_CLUSTER_ZERO_ALLOC) { continue; } - offset = qcow2_alloc_clusters(bs, s->cluster_size); - if (offset < 0) { - ret = offset; - goto fail; - } + if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { + if (!bs->backing) { + /* not backed; therefore we can simply deallocate the + * cluster */ + l2_table[j] = 0; + l2_dirty = true; + continue; + } + + offset = qcow2_alloc_clusters(bs, s->cluster_size); + if (offset < 0) { + ret = offset; + goto fail; + } - if (l2_refcount > 1) { - /* For shared L2 tables, set the refcount accordingly (it is - * already 1 and needs to be l2_refcount) */ - ret = qcow2_update_cluster_refcount(bs, - offset >> s->cluster_bits, + if (l2_refcount > 1) { + /* For shared L2 tables, set the refcount accordingly + * (it is already 1 and needs to be l2_refcount) */ + ret = qcow2_update_cluster_refcount( + bs, offset >> s->cluster_bits, refcount_diff(1, l2_refcount), false, QCOW2_DISCARD_OTHER); - if (ret < 0) { - qcow2_free_clusters(bs, offset, s->cluster_size, - QCOW2_DISCARD_OTHER); - goto fail; + if (ret < 0) { + qcow2_free_clusters(bs, offset, s->cluster_size, + QCOW2_DISCARD_OTHER); + goto fail; + } } } - } - if (offset_into_cluster(s, offset)) { - qcow2_signal_corruption(bs, true, -1, -1, - "Cluster allocation offset " - "%#" PRIx64 " unaligned (L2 offset: %#" - PRIx64 ", L2 index: %#x)", offset, - l2_offset, j); - if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { - qcow2_free_clusters(bs, offset, s->cluster_size, - QCOW2_DISCARD_ALWAYS); + if (offset_into_cluster(s, offset)) { + qcow2_signal_corruption( + bs, true, -1, -1, + "Cluster allocation offset " + "%#" PRIx64 " unaligned (L2 offset: %#" + PRIx64 ", L2 index: %#x)", offset, + l2_offset, j); + if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { + qcow2_free_clusters(bs, offset, s->cluster_size, + QCOW2_DISCARD_ALWAYS); + } + ret = -EIO; + goto fail; } - ret = -EIO; - goto fail; - } - ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size); - if (ret < 0) { - if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { - qcow2_free_clusters(bs, offset, s->cluster_size, - QCOW2_DISCARD_ALWAYS); + ret = qcow2_pre_write_overlap_check(bs, 0, offset, + s->cluster_size); + if (ret < 0) { + if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { + qcow2_free_clusters(bs, offset, s->cluster_size, + QCOW2_DISCARD_ALWAYS); + } + goto fail; } - goto fail; - } - ret = bdrv_pwrite_zeroes(bs->file, offset, s->cluster_size, 0); - if (ret < 0) { - if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { - qcow2_free_clusters(bs, offset, s->cluster_size, - QCOW2_DISCARD_ALWAYS); + ret = bdrv_pwrite_zeroes(bs->file, offset, s->cluster_size, 0); + if (ret < 0) { + if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { + qcow2_free_clusters(bs, offset, s->cluster_size, + QCOW2_DISCARD_ALWAYS); + } + goto fail; } - goto fail; - } - if (l2_refcount == 1) { - l2_table[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED); - } else { - l2_table[j] = cpu_to_be64(offset); + if (l2_refcount == 1) { + l2_table[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED); + } else { + l2_table[j] = cpu_to_be64(offset); + } + l2_dirty = true; } - l2_dirty = true; - } - if (is_active_l1) { - if (l2_dirty) { - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); - qcow2_cache_depends_on_flush(s->l2_table_cache); - } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); - } else { - if (l2_dirty) { - ret = qcow2_pre_write_overlap_check(bs, - QCOW2_OL_INACTIVE_L2 | QCOW2_OL_ACTIVE_L2, l2_offset, - s->cluster_size); - if (ret < 0) { - goto fail; + if (is_active_l1) { + if (l2_dirty) { + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); + qcow2_cache_depends_on_flush(s->l2_table_cache); } + qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + } else { + if (l2_dirty) { + ret = qcow2_pre_write_overlap_check( + bs, QCOW2_OL_INACTIVE_L2 | QCOW2_OL_ACTIVE_L2, + l2_offset, s->cluster_size); + if (ret < 0) { + goto fail; + } - ret = bdrv_write(bs->file, l2_offset / BDRV_SECTOR_SIZE, - (void *)l2_table, s->cluster_sectors); - if (ret < 0) { - goto fail; + ret = bdrv_write(bs->file, l2_offset / BDRV_SECTOR_SIZE, + (void *)l2_table, s->cluster_sectors); + if (ret < 0) { + goto fail; + } } } } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> expand_zero_clusters_in_l1() expands zero clusters as a necessary step to downgrade qcow2 images to a version that doesn't support metadata zero clusters. This function takes an L1 table (which may or may not be active) and iterates over all its L2 tables looking for zero clusters. Since we'll be loading L2 slices instead of full tables we need to add an extra loop that iterates over all slices of each L2 table, and we should also use the slice size when allocating the buffer used when the L1 table is not active. This function doesn't need any additional changes so apart from that this patch simply updates the variable name from l2_table to l2_slice. Finally, and since we have to touch the bdrv_read() / bdrv_write() calls anyway, this patch takes the opportunity to replace them with the byte-based bdrv_pread() / bdrv_pwrite(). Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 43590976f730501688096cff103f2923b72b0f32.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 51 ++++++++++++++++++++++++++++----------------------- 1 file changed, 28 insertions(+), 23 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, { BDRVQcow2State *s = bs->opaque; bool is_active_l1 = (l1_table == s->l1_table); - uint64_t *l2_table = NULL; + uint64_t *l2_slice = NULL; + unsigned slice, slice_size2, n_slices; int ret; int i, j; + slice_size2 = s->l2_slice_size * sizeof(uint64_t); + n_slices = s->cluster_size / slice_size2; + if (!is_active_l1) { /* inactive L2 tables require a buffer to be stored in when loading * them from disk */ - l2_table = qemu_try_blockalign(bs->file->bs, s->cluster_size); - if (l2_table == NULL) { + l2_slice = qemu_try_blockalign(bs->file->bs, slice_size2); + if (l2_slice == NULL) { return -ENOMEM; } } for (i = 0; i < l1_size; i++) { uint64_t l2_offset = l1_table[i] & L1E_OFFSET_MASK; - bool l2_dirty = false; uint64_t l2_refcount; if (!l2_offset) { @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, goto fail; } - { + for (slice = 0; slice < n_slices; slice++) { + uint64_t slice_offset = l2_offset + slice * slice_size2; + bool l2_dirty = false; if (is_active_l1) { /* get active L2 tables from cache */ - ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, - (void **)&l2_table); + ret = qcow2_cache_get(bs, s->l2_table_cache, slice_offset, + (void **)&l2_slice); } else { /* load inactive L2 tables from disk */ - ret = bdrv_read(bs->file, l2_offset / BDRV_SECTOR_SIZE, - (void *)l2_table, s->cluster_sectors); + ret = bdrv_pread(bs->file, slice_offset, l2_slice, slice_size2); } if (ret < 0) { goto fail; } - for (j = 0; j < s->l2_size; j++) { - uint64_t l2_entry = be64_to_cpu(l2_table[j]); + for (j = 0; j < s->l2_slice_size; j++) { + uint64_t l2_entry = be64_to_cpu(l2_slice[j]); int64_t offset = l2_entry & L2E_OFFSET_MASK; QCow2ClusterType cluster_type = qcow2_get_cluster_type(l2_entry); @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, if (!bs->backing) { /* not backed; therefore we can simply deallocate the * cluster */ - l2_table[j] = 0; + l2_slice[j] = 0; l2_dirty = true; continue; } @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, } if (offset_into_cluster(s, offset)) { + int l2_index = slice * s->l2_slice_size + j; qcow2_signal_corruption( bs, true, -1, -1, "Cluster allocation offset " "%#" PRIx64 " unaligned (L2 offset: %#" PRIx64 ", L2 index: %#x)", offset, - l2_offset, j); + l2_offset, l2_index); if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) { qcow2_free_clusters(bs, offset, s->cluster_size, QCOW2_DISCARD_ALWAYS); @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, } if (l2_refcount == 1) { - l2_table[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED); + l2_slice[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED); } else { - l2_table[j] = cpu_to_be64(offset); + l2_slice[j] = cpu_to_be64(offset); } l2_dirty = true; } if (is_active_l1) { if (l2_dirty) { - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice); qcow2_cache_depends_on_flush(s->l2_table_cache); } - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); } else { if (l2_dirty) { ret = qcow2_pre_write_overlap_check( bs, QCOW2_OL_INACTIVE_L2 | QCOW2_OL_ACTIVE_L2, - l2_offset, s->cluster_size); + slice_offset, slice_size2); if (ret < 0) { goto fail; } - ret = bdrv_write(bs->file, l2_offset / BDRV_SECTOR_SIZE, - (void *)l2_table, s->cluster_sectors); + ret = bdrv_pwrite(bs->file, slice_offset, + l2_slice, slice_size2); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, ret = 0; fail: - if (l2_table) { + if (l2_slice) { if (!is_active_l1) { - qemu_vfree(l2_table); + qemu_vfree(l2_slice); } else { - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); } } return ret; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> The qcow2_truncate() code is mostly independent from whether we're using L2 slices or full L2 tables, but in full and falloc preallocation modes new L2 tables are allocated using qcow2_alloc_cluster_link_l2(). Therefore the code needs to be modified to ensure that all nb_clusters that are processed in each call can be allocated with just one L2 slice. Signed-off-by: Alberto Garcia <berto@igalia.com> Message-id: 1fd7d272b5e7b66254a090b74cf2bed1cc334c0e.1517840877.git.berto@igalia.com Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset, host_offset = allocation_start; guest_offset = old_length; while (nb_new_data_clusters) { - int64_t guest_cluster = guest_offset >> s->cluster_bits; - int64_t nb_clusters = MIN(nb_new_data_clusters, - s->l2_size - guest_cluster % s->l2_size); + int64_t nb_clusters = MIN( + nb_new_data_clusters, + s->l2_slice_size - offset_to_l2_slice_index(s, guest_offset)); QCowL2Meta allocation = { .offset = guest_offset, .alloc_offset = host_offset, -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function doesn't need any changes to support L2 slices, but since it's now dealing with slices instead of full tables, the l2_table variable is renamed for clarity. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 0c5d4b9bf163aa3b49ec19cc512a50d83563f2ad.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, { BDRVQcow2State *s = bs->opaque; int l2_index, ret; - uint64_t *l2_table; + uint64_t *l2_slice; int64_t cluster_offset; int nb_csectors; - ret = get_cluster_table(bs, offset, &l2_table, &l2_index); + ret = get_cluster_table(bs, offset, &l2_slice, &l2_index); if (ret < 0) { return 0; } /* Compression can't overwrite anything. Fail if the cluster was already * allocated. */ - cluster_offset = be64_to_cpu(l2_table[l2_index]); + cluster_offset = be64_to_cpu(l2_slice[l2_index]); if (cluster_offset & L2E_OFFSET_MASK) { - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); return 0; } cluster_offset = qcow2_alloc_bytes(bs, compressed_size); if (cluster_offset < 0) { - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); return 0; } @@ -XXX,XX +XXX,XX @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, /* compressed clusters never have the copied flag */ BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE_COMPRESSED); - qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table); - l2_table[l2_index] = cpu_to_be64(cluster_offset); - qcow2_cache_put(s->l2_table_cache, (void **) &l2_table); + qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice); + l2_slice[l2_index] = cpu_to_be64(cluster_offset); + qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); return cluster_offset; } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function doesn't need any changes to support L2 slices, but since it's now dealing with slices intead of full tables, the l2_table variable is renamed for clarity. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 812b0c3505bb1687e51285dccf1a94f0cecb1f74.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ fail: } /* - * Checks how many clusters in a given L2 table are contiguous in the image + * Checks how many clusters in a given L2 slice are contiguous in the image * file. As soon as one of the flags in the bitmask stop_flags changes compared * to the first cluster, the search is stopped and the cluster is not counted * as contiguous. (This allows it, for example, to stop at the first compressed * cluster which may require a different handling) */ static int count_contiguous_clusters(int nb_clusters, int cluster_size, - uint64_t *l2_table, uint64_t stop_flags) + uint64_t *l2_slice, uint64_t stop_flags) { int i; QCow2ClusterType first_cluster_type; uint64_t mask = stop_flags | L2E_OFFSET_MASK | QCOW_OFLAG_COMPRESSED; - uint64_t first_entry = be64_to_cpu(l2_table[0]); + uint64_t first_entry = be64_to_cpu(l2_slice[0]); uint64_t offset = first_entry & mask; if (!offset) { @@ -XXX,XX +XXX,XX @@ static int count_contiguous_clusters(int nb_clusters, int cluster_size, first_cluster_type == QCOW2_CLUSTER_ZERO_ALLOC); for (i = 0; i < nb_clusters; i++) { - uint64_t l2_entry = be64_to_cpu(l2_table[i]) & mask; + uint64_t l2_entry = be64_to_cpu(l2_slice[i]) & mask; if (offset + (uint64_t) i * cluster_size != l2_entry) { break; } -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function doesn't need any changes to support L2 slices, but since it's now dealing with slices instead of full tables, the l2_table variable is renamed for clarity. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 78bcc54bc632574dd0b900a77a00a1b6ffc359e6.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int count_contiguous_clusters(int nb_clusters, int cluster_size, /* * Checks how many consecutive unallocated clusters in a given L2 - * table have the same cluster type. + * slice have the same cluster type. */ static int count_contiguous_clusters_unallocated(int nb_clusters, - uint64_t *l2_table, + uint64_t *l2_slice, QCow2ClusterType wanted_type) { int i; @@ -XXX,XX +XXX,XX @@ static int count_contiguous_clusters_unallocated(int nb_clusters, assert(wanted_type == QCOW2_CLUSTER_ZERO_PLAIN || wanted_type == QCOW2_CLUSTER_UNALLOCATED); for (i = 0; i < nb_clusters; i++) { - uint64_t entry = be64_to_cpu(l2_table[i]); + uint64_t entry = be64_to_cpu(l2_slice[i]); QCow2ClusterType type = qcow2_get_cluster_type(entry); if (type != wanted_type) { -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This function doesn't need any changes to support L2 slices, but since it's now dealing with slices intead of full tables, the l2_table variable is renamed for clarity. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 6107001fc79e6739242f1de7d191375e4f130aac.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-cluster.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ err: * which must copy from the backing file) */ static int count_cow_clusters(BDRVQcow2State *s, int nb_clusters, - uint64_t *l2_table, int l2_index) + uint64_t *l2_slice, int l2_index) { int i; for (i = 0; i < nb_clusters; i++) { - uint64_t l2_entry = be64_to_cpu(l2_table[l2_index + i]); + uint64_t l2_entry = be64_to_cpu(l2_slice[l2_index + i]); QCow2ClusterType cluster_type = qcow2_get_cluster_type(l2_entry); switch(cluster_type) { -- 2.13.6 From: Alberto Garcia <berto@igalia.com> Now that the code is ready to handle L2 slices we can finally add an option to allow configuring their size. An L2 slice is the portion of an L2 table that is read by the qcow2 cache. Until now the cache was always reading full L2 tables, and since the L2 table size is equal to the cluster size this was not very efficient with large clusters. Here's a more detailed explanation of why it makes sense to have smaller cache entries in order to load L2 data: https://lists.gnu.org/archive/html/qemu-block/2017-09/msg00635.html This patch introduces a new command-line option to the qcow2 driver named l2-cache-entry-size (cf. l2-cache-size). The cache entry size has the same restrictions as the cluster size: it must be a power of two and it has the same range of allowed values, with the additional requirement that it must not be larger than the cluster size. The L2 cache entry size (L2 slice size) remains equal to the cluster size for now by default, so this feature must be explicitly enabled. Although my tests show that 4KB slices consistently improve performance and give the best results, let's wait and make more tests with different cluster sizes before deciding on an optimal default. Now that the cache entry size is not necessarily equal to the cluster size we need to reflect that in the MIN_L2_CACHE_SIZE documentation. That minimum value is a requirement of the COW algorithm: we need to read two L2 slices (and not two L2 tables) in order to do COW, see l2_allocate() for the actual code. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: c73e5611ff4a9ec5d20de68a6c289553a13d2354.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 6 ++++++ block/qcow2.h | 6 ++++-- block/qcow2-cache.c | 10 ++++++++-- block/qcow2.c | 34 +++++++++++++++++++++++++++------- 4 files changed, 45 insertions(+), 11 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # @l2-cache-size: the maximum size of the L2 table cache in # bytes (since 2.2) # +# @l2-cache-entry-size: the size of each entry in the L2 cache in +# bytes. It must be a power of two between 512 +# and the cluster size. The default value is +# the cluster size (since 2.12) +# # @refcount-cache-size: the maximum size of the refcount block cache # in bytes (since 2.2) # @@ -XXX,XX +XXX,XX @@ '*overlap-check': 'Qcow2OverlapChecks', '*cache-size': 'int', '*l2-cache-size': 'int', + '*l2-cache-entry-size': 'int', '*refcount-cache-size': 'int', '*cache-clean-interval': 'int', '*encrypt': 'BlockdevQcow2Encryption' } } diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ #define MAX_CLUSTER_BITS 21 /* Must be at least 2 to cover COW */ -#define MIN_L2_CACHE_SIZE 2 /* clusters */ +#define MIN_L2_CACHE_SIZE 2 /* cache entries */ /* Must be at least 4 to cover all cases of refcount table growth */ #define MIN_REFCOUNT_CACHE_SIZE 4 /* clusters */ @@ -XXX,XX +XXX,XX @@ #define QCOW2_OPT_OVERLAP_INACTIVE_L2 "overlap-check.inactive-l2" #define QCOW2_OPT_CACHE_SIZE "cache-size" #define QCOW2_OPT_L2_CACHE_SIZE "l2-cache-size" +#define QCOW2_OPT_L2_CACHE_ENTRY_SIZE "l2-cache-entry-size" #define QCOW2_OPT_REFCOUNT_CACHE_SIZE "refcount-cache-size" #define QCOW2_OPT_CACHE_CLEAN_INTERVAL "cache-clean-interval" @@ -XXX,XX +XXX,XX @@ void qcow2_free_snapshots(BlockDriverState *bs); int qcow2_read_snapshots(BlockDriverState *bs); /* qcow2-cache.c functions */ -Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables); +Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables, + unsigned table_size); int qcow2_cache_destroy(Qcow2Cache *c); void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table); diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ void qcow2_cache_clean_unused(Qcow2Cache *c) c->cache_clean_lru_counter = c->lru_counter; } -Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables) +Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables, + unsigned table_size) { BDRVQcow2State *s = bs->opaque; Qcow2Cache *c; + assert(num_tables > 0); + assert(is_power_of_2(table_size)); + assert(table_size >= (1 << MIN_CLUSTER_BITS)); + assert(table_size <= s->cluster_size); + c = g_new0(Qcow2Cache, 1); c->size = num_tables; - c->table_size = s->cluster_size; + c->table_size = table_size; c->entries = g_try_new0(Qcow2CachedTable, num_tables); c->table_array = qemu_try_blockalign(bs->file->bs, (size_t) num_tables * c->table_size); diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static QemuOptsList qcow2_runtime_opts = { .help = "Maximum L2 table cache size", }, { + .name = QCOW2_OPT_L2_CACHE_ENTRY_SIZE, + .type = QEMU_OPT_SIZE, + .help = "Size of each entry in the L2 cache", + }, + { .name = QCOW2_OPT_REFCOUNT_CACHE_SIZE, .type = QEMU_OPT_SIZE, .help = "Maximum refcount block cache size", @@ -XXX,XX +XXX,XX @@ static void qcow2_attach_aio_context(BlockDriverState *bs, static void read_cache_sizes(BlockDriverState *bs, QemuOpts *opts, uint64_t *l2_cache_size, + uint64_t *l2_cache_entry_size, uint64_t *refcount_cache_size, Error **errp) { BDRVQcow2State *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static void read_cache_sizes(BlockDriverState *bs, QemuOpts *opts, *refcount_cache_size = qemu_opt_get_size(opts, QCOW2_OPT_REFCOUNT_CACHE_SIZE, 0); + *l2_cache_entry_size = qemu_opt_get_size( + opts, QCOW2_OPT_L2_CACHE_ENTRY_SIZE, s->cluster_size); + if (combined_cache_size_set) { if (l2_cache_size_set && refcount_cache_size_set) { error_setg(errp, QCOW2_OPT_CACHE_SIZE ", " QCOW2_OPT_L2_CACHE_SIZE @@ -XXX,XX +XXX,XX @@ static void read_cache_sizes(BlockDriverState *bs, QemuOpts *opts, / DEFAULT_L2_REFCOUNT_SIZE_RATIO; } } + + if (*l2_cache_entry_size < (1 << MIN_CLUSTER_BITS) || + *l2_cache_entry_size > s->cluster_size || + !is_power_of_2(*l2_cache_entry_size)) { + error_setg(errp, "L2 cache entry size must be a power of two " + "between %d and the cluster size (%d)", + 1 << MIN_CLUSTER_BITS, s->cluster_size); + return; + } } typedef struct Qcow2ReopenState { @@ -XXX,XX +XXX,XX @@ static int qcow2_update_options_prepare(BlockDriverState *bs, QemuOpts *opts = NULL; const char *opt_overlap_check, *opt_overlap_check_template; int overlap_check_template = 0; - uint64_t l2_cache_size, refcount_cache_size; + uint64_t l2_cache_size, l2_cache_entry_size, refcount_cache_size; int i; const char *encryptfmt; QDict *encryptopts = NULL; @@ -XXX,XX +XXX,XX @@ static int qcow2_update_options_prepare(BlockDriverState *bs, } /* get L2 table/refcount block cache size from command line options */ - read_cache_sizes(bs, opts, &l2_cache_size, &refcount_cache_size, - &local_err); + read_cache_sizes(bs, opts, &l2_cache_size, &l2_cache_entry_size, + &refcount_cache_size, &local_err); if (local_err) { error_propagate(errp, local_err); ret = -EINVAL; goto fail; } - l2_cache_size /= s->cluster_size; + l2_cache_size /= l2_cache_entry_size; if (l2_cache_size < MIN_L2_CACHE_SIZE) { l2_cache_size = MIN_L2_CACHE_SIZE; } @@ -XXX,XX +XXX,XX @@ static int qcow2_update_options_prepare(BlockDriverState *bs, } } - r->l2_slice_size = s->cluster_size / sizeof(uint64_t); - r->l2_table_cache = qcow2_cache_create(bs, l2_cache_size); - r->refcount_block_cache = qcow2_cache_create(bs, refcount_cache_size); + r->l2_slice_size = l2_cache_entry_size / sizeof(uint64_t); + r->l2_table_cache = qcow2_cache_create(bs, l2_cache_size, + l2_cache_entry_size); + r->refcount_block_cache = qcow2_cache_create(bs, refcount_cache_size, + s->cluster_size); if (r->l2_table_cache == NULL || r->refcount_block_cache == NULL) { error_setg(errp, "Could not allocate metadata caches"); ret = -ENOMEM; -- 2.13.6 From: Alberto Garcia <berto@igalia.com> The l2-cache-entry-size setting can only contain values that are powers of two between 512 and the cluster size. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: bd3547b670b8d0af11480c760991a22bcae5b48c.1517840877.git.berto@igalia.com [mreitz: Changed non-power-of-two test value from 300 to 4242] Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/103 | 17 +++++++++++++++++ tests/qemu-iotests/103.out | 3 +++ 2 files changed, 20 insertions(+) diff --git a/tests/qemu-iotests/103 b/tests/qemu-iotests/103 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/103 +++ b/tests/qemu-iotests/103 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "open -o cache-size=1M,refcount-cache-size=2M $TEST_IMG" 2>&1 \ $QEMU_IO -c "open -o cache-size=0,l2-cache-size=0,refcount-cache-size=0 $TEST_IMG" \ 2>&1 | _filter_testdir | _filter_imgfmt +# Invalid cache entry sizes +$QEMU_IO -c "open -o l2-cache-entry-size=256 $TEST_IMG" \ + 2>&1 | _filter_testdir | _filter_imgfmt +$QEMU_IO -c "open -o l2-cache-entry-size=4242 $TEST_IMG" \ + 2>&1 | _filter_testdir | _filter_imgfmt +$QEMU_IO -c "open -o l2-cache-entry-size=128k $TEST_IMG" \ + 2>&1 | _filter_testdir | _filter_imgfmt + echo echo '=== Testing valid option combinations ===' echo @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "open -o l2-cache-size=1M,refcount-cache-size=0.25M $TEST_IMG" \ -c 'read -P 42 0 64k' \ | _filter_qemu_io +# Valid cache entry sizes +$QEMU_IO -c "open -o l2-cache-entry-size=512 $TEST_IMG" \ + 2>&1 | _filter_testdir | _filter_imgfmt +$QEMU_IO -c "open -o l2-cache-entry-size=16k $TEST_IMG" \ + 2>&1 | _filter_testdir | _filter_imgfmt +$QEMU_IO -c "open -o l2-cache-entry-size=64k $TEST_IMG" \ + 2>&1 | _filter_testdir | _filter_imgfmt + + echo echo '=== Testing minimal L2 cache and COW ===' echo diff --git a/tests/qemu-iotests/103.out b/tests/qemu-iotests/103.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/103.out +++ b/tests/qemu-iotests/103.out @@ -XXX,XX +XXX,XX @@ can't open device TEST_DIR/t.IMGFMT: cache-size, l2-cache-size and refcount-cach can't open device TEST_DIR/t.IMGFMT: l2-cache-size may not exceed cache-size can't open device TEST_DIR/t.IMGFMT: refcount-cache-size may not exceed cache-size can't open device TEST_DIR/t.IMGFMT: cache-size, l2-cache-size and refcount-cache-size may not be set the same time +can't open device TEST_DIR/t.IMGFMT: L2 cache entry size must be a power of two between 512 and the cluster size (65536) +can't open device TEST_DIR/t.IMGFMT: L2 cache entry size must be a power of two between 512 and the cluster size (65536) +can't open device TEST_DIR/t.IMGFMT: L2 cache entry size must be a power of two between 512 and the cluster size (65536) === Testing valid option combinations === -- 2.13.6 From: Alberto Garcia <berto@igalia.com> expand_zero_clusters_in_l1() is used when downgrading qcow2 images from v3 to v2 (compat=0.10). This is one of the functions that needed more changes to support L2 slices, so this patch extends iotest 061 to test downgrading a qcow2 image using a smaller slice size. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 3e5662dce5e4926c8fabbad4c0b9142b2a506dd4.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/061 | 16 ++++++++++++ tests/qemu-iotests/061.out | 61 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/061 +++ b/tests/qemu-iotests/061 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io _check_test_img echo +echo "=== Testing version downgrade with zero expansion and 4K cache entries ===" +echo +IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M +$QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "write -z 32M 128k" "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c map "$TEST_IMG" | _filter_qemu_io +$PYTHON qcow2.py "$TEST_IMG" dump-header +$QEMU_IMG amend -o "compat=0.10" --image-opts \ + driver=qcow2,file.filename=$TEST_IMG,l2-cache-entry-size=4096 +$PYTHON qcow2.py "$TEST_IMG" dump-header +$QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "read -P 0 32M 128k" "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c map "$TEST_IMG" | _filter_qemu_io +_check_test_img + +echo echo "=== Testing dirty version downgrade ===" echo IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/061.out +++ b/tests/qemu-iotests/061.out @@ -XXX,XX +XXX,XX @@ read 131072/131072 bytes at offset 0 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) No errors were found on the image. +=== Testing version downgrade with zero expansion and 4K cache entries === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +wrote 131072/131072 bytes at offset 0 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 131072/131072 bytes at offset 33554432 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +128 KiB (0x20000) bytes allocated at offset 0 bytes (0x0) +31.875 MiB (0x1fe0000) bytes not allocated at offset 128 KiB (0x20000) +128 KiB (0x20000) bytes allocated at offset 32 MiB (0x2000000) +31.875 MiB (0x1fe0000) bytes not allocated at offset 32.125 MiB (0x2020000) +magic 0x514649fb +version 3 +backing_file_offset 0x0 +backing_file_size 0x0 +cluster_bits 16 +size 67108864 +crypt_method 0 +l1_size 1 +l1_table_offset 0x30000 +refcount_table_offset 0x10000 +refcount_table_clusters 1 +nb_snapshots 0 +snapshot_offset 0x0 +incompatible_features 0x0 +compatible_features 0x1 +autoclear_features 0x0 +refcount_order 4 +header_length 104 + +Header extension: +magic 0x6803f857 +length 144 +data <binary> + +magic 0x514649fb +version 2 +backing_file_offset 0x0 +backing_file_size 0x0 +cluster_bits 16 +size 67108864 +crypt_method 0 +l1_size 1 +l1_table_offset 0x30000 +refcount_table_offset 0x10000 +refcount_table_clusters 1 +nb_snapshots 0 +snapshot_offset 0x0 +incompatible_features 0x0 +compatible_features 0x0 +autoclear_features 0x0 +refcount_order 4 +header_length 72 + +read 131072/131072 bytes at offset 0 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 131072/131072 bytes at offset 33554432 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +64 MiB (0x4000000) bytes not allocated at offset 0 bytes (0x0) +No errors were found on the image. + === Testing dirty version downgrade === Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 -- 2.13.6 From: Alberto Garcia <berto@igalia.com> This test tries reopening a qcow2 image with valid and invalid options. This patch adds l2-cache-entry-size to the set. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 3d3b7d2dbfc020deaef60fb58739b0801eb9517c.1517840877.git.berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/137 | 5 +++++ tests/qemu-iotests/137.out | 2 ++ 2 files changed, 7 insertions(+) diff --git a/tests/qemu-iotests/137 b/tests/qemu-iotests/137 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/137 +++ b/tests/qemu-iotests/137 @@ -XXX,XX +XXX,XX @@ $QEMU_IO \ -c "reopen -o overlap-check.inactive-l2=off" \ -c "reopen -o cache-size=1M" \ -c "reopen -o l2-cache-size=512k" \ + -c "reopen -o l2-cache-entry-size=512" \ + -c "reopen -o l2-cache-entry-size=4k" \ + -c "reopen -o l2-cache-entry-size=64k" \ -c "reopen -o refcount-cache-size=128k" \ -c "reopen -o cache-clean-interval=5" \ -c "reopen -o cache-clean-interval=0" \ @@ -XXX,XX +XXX,XX @@ $QEMU_IO \ -c "reopen -o cache-size=1M,l2-cache-size=2M" \ -c "reopen -o cache-size=1M,refcount-cache-size=2M" \ -c "reopen -o l2-cache-size=256T" \ + -c "reopen -o l2-cache-entry-size=33k" \ + -c "reopen -o l2-cache-entry-size=128k" \ -c "reopen -o refcount-cache-size=256T" \ -c "reopen -o overlap-check=constant,overlap-check.template=all" \ -c "reopen -o overlap-check=blubb" \ diff --git a/tests/qemu-iotests/137.out b/tests/qemu-iotests/137.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/137.out +++ b/tests/qemu-iotests/137.out @@ -XXX,XX +XXX,XX @@ cache-size, l2-cache-size and refcount-cache-size may not be set the same time l2-cache-size may not exceed cache-size refcount-cache-size may not exceed cache-size L2 cache size too big +L2 cache entry size must be a power of two between 512 and the cluster size (65536) +L2 cache entry size must be a power of two between 512 and the cluster size (65536) L2 cache size too big Conflicting values for qcow2 options 'overlap-check' ('constant') and 'overlap-check.template' ('all') Unsupported value 'blubb' for qcow2 option 'overlap-check'. Allowed are any of the following: none, constant, cached, all -- 2.13.6 The following changes since commit 16aaacb307ed607b9780c12702c44f0fe52edc7e: Merge remote-tracking branch 'remotes/cohuck/tags/s390x-20200430' into staging (2020-04-30 14:00:36 +0100) are available in the Git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to eaae29ef89d498d0eac553c77b554f310a47f809: qemu-storage-daemon: Fix non-string --object properties (2020-04-30 17:51:07 +0200) ---------------------------------------------------------------- Block layer patches: - Fix resize (extending) of short overlays - nvme: introduce PMR support from NVMe 1.4 spec - qemu-storage-daemon: Fix non-string --object properties ---------------------------------------------------------------- Alberto Garcia (1): qcow2: Add incompatibility note between backing files and raw external data files Andrzej Jakowski (1): nvme: introduce PMR support from NVMe 1.4 spec Kevin Wolf (12): block: Add flags to BlockDriver.bdrv_co_truncate() block: Add flags to bdrv(_co)_truncate() block-backend: Add flags to blk_truncate() qcow2: Support BDRV_REQ_ZERO_WRITE for truncate raw-format: Support BDRV_REQ_ZERO_WRITE for truncate file-posix: Support BDRV_REQ_ZERO_WRITE for truncate block: truncate: Don't make backing file data visible iotests: Filter testfiles out in filter_img_info() iotests: Test committing to short backing file qcow2: Forward ZERO_WRITE flag for full preallocation qom: Factor out user_creatable_add_dict() qemu-storage-daemon: Fix non-string --object properties Paolo Bonzini (1): qemu-iotests: allow qcow2 external discarded clusters to contain stale data docs/interop/qcow2.txt | 3 + hw/block/nvme.h | 2 + include/block/block.h | 5 +- include/block/block_int.h | 10 +- include/block/nvme.h | 172 ++++++++++++++++++++++++++ include/qom/object_interfaces.h | 16 +++ include/sysemu/block-backend.h | 2 +- block.c | 3 +- block/block-backend.c | 4 +- block/commit.c | 4 +- block/crypto.c | 7 +- block/file-posix.c | 6 +- block/file-win32.c | 2 +- block/gluster.c | 1 + block/io.c | 43 ++++++- block/iscsi.c | 2 +- block/mirror.c | 2 +- block/nfs.c | 3 +- block/parallels.c | 6 +- block/qcow.c | 4 +- block/qcow2-cluster.c | 2 +- block/qcow2-refcount.c | 2 +- block/qcow2.c | 73 +++++++++-- block/qed.c | 3 +- block/raw-format.c | 6 +- block/rbd.c | 1 + block/sheepdog.c | 4 +- block/ssh.c | 2 +- block/vdi.c | 2 +- block/vhdx-log.c | 2 +- block/vhdx.c | 6 +- block/vmdk.c | 8 +- block/vpc.c | 2 +- blockdev.c | 2 +- hw/block/nvme.c | 109 ++++++++++++++++ qemu-img.c | 2 +- qemu-io-cmds.c | 2 +- qemu-storage-daemon.c | 4 +- qom/object_interfaces.c | 31 +++++ qom/qom-qmp-cmds.c | 24 +--- tests/test-block-iothread.c | 9 +- tests/qemu-iotests/iotests.py | 5 +- hw/block/Makefile.objs | 2 +- hw/block/trace-events | 4 + tests/qemu-iotests/244 | 10 +- tests/qemu-iotests/244.out | 9 +- tests/qemu-iotests/274 | 155 +++++++++++++++++++++++ tests/qemu-iotests/274.out | 268 ++++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/group | 1 + 49 files changed, 951 insertions(+), 96 deletions(-) create mode 100755 tests/qemu-iotests/274 create mode 100644 tests/qemu-iotests/274.out From: Alberto Garcia <berto@igalia.com> Backing files and raw external data files are mutually exclusive. The documentation of the raw external data bit (in autoclear_features) already indicates that, but we should also mention it on the other side. Suggested-by: Eric Blake <eblake@redhat.com> Signed-off-by: Alberto Garcia <berto@igalia.com> Message-Id: <20200410121816.8334-1-berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- docs/interop/qcow2.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docs/interop/qcow2.txt b/docs/interop/qcow2.txt index XXXXXXX..XXXXXXX 100644 --- a/docs/interop/qcow2.txt +++ b/docs/interop/qcow2.txt @@ -XXX,XX +XXX,XX @@ The first cluster of a qcow2 image contains the file header: is stored (NB: The string is not null terminated). 0 if the image doesn't have a backing file. + Note: backing files are incompatible with raw external data + files (auto-clear feature bit 1). + 16 - 19: backing_file_size Length of the backing file name in bytes. Must not be longer than 1023 bytes. Undefined if the image doesn't have -- 2.25.3 From: Paolo Bonzini <pbonzini@redhat.com> Test 244 checks the expected behavior of qcow2 external data files with respect to zero and discarded clusters. Filesystems however are free to ignore discard requests, and this seems to be the case for overlayfs. Relax the tests to skip checks on the external data file for discarded areas, which implies not using qemu-img compare in the data_file_raw=on case. This fixes docker tests on RHEL8. Cc: Kevin Wolf <kwolf@redhat.com> Cc: qemu-block@nongnu.org Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20200409191006.24429-1-pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/244 | 10 ++++++++-- tests/qemu-iotests/244.out | 9 ++++++--- 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/244 +++ b/tests/qemu-iotests/244 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'read -P 0 0 1M' \ echo $QEMU_IO -c 'read -P 0 0 1M' \ -c 'read -P 0x11 1M 1M' \ - -c 'read -P 0 2M 2M' \ -c 'read -P 0x11 4M 1M' \ -c 'read -P 0 5M 1M' \ -f raw "$TEST_IMG.data" | @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'read -P 0 0 1M' \ -f $IMGFMT "$TEST_IMG" | _filter_qemu_io +# Discarded clusters are only marked as such in the qcow2 metadata, but +# they can contain stale data in the external data file. Instead, zero +# clusters must be zeroed in the external data file too. echo -$QEMU_IMG compare "$TEST_IMG" "$TEST_IMG.data" +$QEMU_IO -c 'read -P 0 0 1M' \ + -c 'read -P 0x11 1M 1M' \ + -c 'read -P 0 3M 3M' \ + -f raw "$TEST_IMG".data | + _filter_qemu_io echo -n "qcow2 file size after I/O: " du -b $TEST_IMG | cut -f1 diff --git a/tests/qemu-iotests/244.out b/tests/qemu-iotests/244.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/244.out +++ b/tests/qemu-iotests/244.out @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 0 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -read 2097152/2097152 bytes at offset 2097152 -2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 1048576/1048576 bytes at offset 4194304 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 1048576/1048576 bytes at offset 5242880 @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 read 4194304/4194304 bytes at offset 2097152 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -Images are identical. +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 3145728/3145728 bytes at offset 3145728 +3 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qcow2 file size after I/O: 327680 === bdrv_co_block_status test for file and offset=0 === -- 2.25.3 This adds a new BdrvRequestFlags parameter to the .bdrv_co_truncate() driver callbacks, and a supported_truncate_flags field in BlockDriverState that allows drivers to advertise support for request flags in the context of truncate. For now, we always pass 0 and no drivers declare support for any flag. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424125448.63318-2-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 10 +++++++++- block/crypto.c | 3 ++- block/file-posix.c | 2 +- block/file-win32.c | 2 +- block/gluster.c | 1 + block/io.c | 8 +++++++- block/iscsi.c | 2 +- block/nfs.c | 3 ++- block/qcow2.c | 2 +- block/qed.c | 1 + block/raw-format.c | 2 +- block/rbd.c | 1 + block/sheepdog.c | 4 ++-- block/ssh.c | 2 +- tests/test-block-iothread.c | 3 ++- 15 files changed, 33 insertions(+), 13 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { */ int coroutine_fn (*bdrv_co_truncate)(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp); + BdrvRequestFlags flags, Error **errp); int64_t (*bdrv_getlength)(BlockDriverState *bs); bool has_variable_length; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* Flags honored during pwrite_zeroes (so far: BDRV_REQ_FUA, * BDRV_REQ_MAY_UNMAP, BDRV_REQ_WRITE_UNCHANGED) */ unsigned int supported_zero_flags; + /* + * Flags honoured during truncate (so far: BDRV_REQ_ZERO_WRITE). + * + * If BDRV_REQ_ZERO_WRITE is given, the truncate operation must make sure + * that any added space reads as all zeros. If this can't be guaranteed, + * the operation must fail. + */ + unsigned int supported_truncate_flags; /* the following member gives a name to every node on the bs graph. */ char node_name[32]; diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static int block_crypto_co_create_generic(BlockDriverState *bs, static int coroutine_fn block_crypto_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { BlockCrypto *crypto = bs->opaque; uint64_t payload_offset = diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ raw_regular_truncate(BlockDriverState *bs, int fd, int64_t offset, static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVRawState *s = bs->opaque; struct stat st; diff --git a/block/file-win32.c b/block/file-win32.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-win32.c +++ b/block/file-win32.c @@ -XXX,XX +XXX,XX @@ static void raw_close(BlockDriverState *bs) static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVRawState *s = bs->opaque; LONG low, high; diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qemu_gluster_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp) { BDRVGlusterState *s = bs->opaque; diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, BlockDriverState *bs = child->bs; BlockDriver *drv = bs->drv; BdrvTrackedRequest req; + BdrvRequestFlags flags = 0; int64_t old_size, new_bytes; int ret; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, } if (drv->bdrv_co_truncate) { - ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, errp); + if (flags & ~bs->supported_truncate_flags) { + error_setg(errp, "Block driver does not support requested flags"); + ret = -ENOTSUP; + goto out; + } + ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, flags, errp); } else if (bs->file && drv->is_filter) { ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, errp); } else { diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static void iscsi_reopen_commit(BDRVReopenState *reopen_state) static int coroutine_fn iscsi_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { IscsiLun *iscsilun = bs->opaque; int64_t cur_length; diff --git a/block/nfs.c b/block/nfs.c index XXXXXXX..XXXXXXX 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -XXX,XX +XXX,XX @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs) static int coroutine_fn nfs_file_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { NFSClient *client = bs->opaque; int ret; diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ fail: static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVQcow2State *s = bs->opaque; uint64_t old_length; diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp) { BDRVQEDState *s = bs->opaque; diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVRawState *s = bs->opaque; diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qemu_rbd_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp) { int r; diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static int64_t sd_getlength(BlockDriverState *bs) static int coroutine_fn sd_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVSheepdogState *s = bs->opaque; int ret, fd; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num, assert(!flags); if (offset > s->inode.vdi_size) { - ret = sd_co_truncate(bs, offset, false, PREALLOC_MODE_OFF, NULL); + ret = sd_co_truncate(bs, offset, false, PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { return ret; } diff --git a/block/ssh.c b/block/ssh.c index XXXXXXX..XXXXXXX 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -XXX,XX +XXX,XX @@ static int64_t ssh_getlength(BlockDriverState *bs) static int coroutine_fn ssh_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVSSHState *s = bs->opaque; diff --git a/tests/test-block-iothread.c b/tests/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-block-iothread.c +++ b/tests/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_test_co_pdiscard(BlockDriverState *bs, static int coroutine_fn bdrv_test_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { return 0; } -- 2.25.3 Now that block drivers can support flags for .bdrv_co_truncate, expose the parameter in the node level interfaces bdrv_co_truncate() and bdrv_truncate(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424125448.63318-3-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 5 +++-- block/block-backend.c | 2 +- block/crypto.c | 2 +- block/io.c | 12 +++++++----- block/parallels.c | 6 +++--- block/qcow.c | 4 ++-- block/qcow2-refcount.c | 2 +- block/qcow2.c | 15 +++++++++------ block/raw-format.c | 2 +- block/vhdx-log.c | 2 +- block/vhdx.c | 2 +- block/vmdk.c | 2 +- tests/test-block-iothread.c | 6 +++--- 13 files changed, 34 insertions(+), 28 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs, void bdrv_refresh_filename(BlockDriverState *bs); int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp); + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp); int bdrv_truncate(BdrvChild *child, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp); + PreallocMode prealloc, BdrvRequestFlags flags, Error **errp); int64_t bdrv_nb_sectors(BlockDriverState *bs); int64_t bdrv_getlength(BlockDriverState *bs); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, return -ENOMEDIUM; } - return bdrv_truncate(blk->root, offset, exact, prealloc, errp); + return bdrv_truncate(blk->root, offset, exact, prealloc, 0, errp); } int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ block_crypto_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, offset += payload_offset; - return bdrv_co_truncate(bs->file, offset, exact, prealloc, errp); + return bdrv_co_truncate(bs->file, offset, exact, prealloc, 0, errp); } static void block_crypto_close(BlockDriverState *bs) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void bdrv_parent_cb_resize(BlockDriverState *bs) * 'offset' bytes in length. */ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { BlockDriverState *bs = child->bs; BlockDriver *drv = bs->drv; BdrvTrackedRequest req; - BdrvRequestFlags flags = 0; int64_t old_size, new_bytes; int ret; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, } ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, flags, errp); } else if (bs->file && drv->is_filter) { - ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, errp); + ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, flags, errp); } else { error_setg(errp, "Image format driver does not support resize"); ret = -ENOTSUP; @@ -XXX,XX +XXX,XX @@ typedef struct TruncateCo { int64_t offset; bool exact; PreallocMode prealloc; + BdrvRequestFlags flags; Error **errp; int ret; } TruncateCo; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_truncate_co_entry(void *opaque) { TruncateCo *tco = opaque; tco->ret = bdrv_co_truncate(tco->child, tco->offset, tco->exact, - tco->prealloc, tco->errp); + tco->prealloc, tco->flags, tco->errp); aio_wait_kick(); } int bdrv_truncate(BdrvChild *child, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, Error **errp) { Coroutine *co; TruncateCo tco = { @@ -XXX,XX +XXX,XX @@ int bdrv_truncate(BdrvChild *child, int64_t offset, bool exact, .offset = offset, .exact = exact, .prealloc = prealloc, + .flags = flags, .errp = errp, .ret = NOT_DONE, }; diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num, } else { ret = bdrv_truncate(bs->file, (s->data_end + space) << BDRV_SECTOR_BITS, - false, PREALLOC_MODE_OFF, NULL); + false, PREALLOC_MODE_OFF, 0, NULL); } if (ret < 0) { return ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, * That means we have to pass exact=true. */ ret = bdrv_truncate(bs->file, res->image_end_offset, true, - PREALLOC_MODE_OFF, &local_err); + PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); res->check_errors++; @@ -XXX,XX +XXX,XX @@ static void parallels_close(BlockDriverState *bs) /* errors are ignored, so we might as well pass exact=true */ bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS, true, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); } g_free(s->bat_dirty_bmap); diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, return -E2BIG; } ret = bdrv_truncate(bs->file, cluster_offset + s->cluster_size, - false, PREALLOC_MODE_OFF, NULL); + false, PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int qcow_make_empty(BlockDriverState *bs) l1_length) < 0) return -1; ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) return ret; diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res, } ret = bdrv_truncate(bs->file, offset + s->cluster_size, false, - PREALLOC_MODE_OFF, &local_err); + PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); goto resize_fail; diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn preallocate_co(BlockDriverState *bs, uint64_t offset, mode = PREALLOC_MODE_OFF; } ret = bdrv_co_truncate(s->data_file, host_offset + cur_bytes, false, - mode, errp); + mode, 0, errp); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, * always fulfilled, so there is no need to pass it on.) */ bdrv_co_truncate(bs->file, (last_cluster + 1) * s->cluster_size, - false, PREALLOC_MODE_OFF, &local_err); + false, PREALLOC_MODE_OFF, 0, &local_err); if (local_err) { warn_reportf_err(local_err, "Failed to truncate the tail of the image: "); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, * file should be resized to the exact target size, too, * so we pass @exact here. */ - ret = bdrv_co_truncate(s->data_file, offset, exact, prealloc, errp); + ret = bdrv_co_truncate(s->data_file, offset, exact, prealloc, 0, + errp); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, new_file_size = allocation_start + nb_new_data_clusters * s->cluster_size; /* Image file grows, so @exact does not matter */ - ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, errp); + ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, 0, + errp); if (ret < 0) { error_prepend(errp, "Failed to resize underlying file: "); qcow2_free_clusters(bs, allocation_start, @@ -XXX,XX +XXX,XX @@ qcow2_co_pwritev_compressed_part(BlockDriverState *bs, if (len < 0) { return len; } - return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, NULL); + return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, 0, + NULL); } if (offset_into_cluster(s, offset)) { @@ -XXX,XX +XXX,XX @@ static int make_completely_empty(BlockDriverState *bs) } ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size, false, - PREALLOC_MODE_OFF, &local_err); + PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); goto fail; diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, s->size = offset; offset += s->offset; - return bdrv_co_truncate(bs->file, offset, exact, prealloc, errp); + return bdrv_co_truncate(bs->file, offset, exact, prealloc, 0, errp); } static void raw_eject(BlockDriverState *bs, bool eject_flag) diff --git a/block/vhdx-log.c b/block/vhdx-log.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -XXX,XX +XXX,XX @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s, goto exit; } ret = bdrv_truncate(bs->file, new_file_size, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { goto exit; } diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s, } return bdrv_truncate(bs->file, *new_offset + s->block_size, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); } /* diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ vmdk_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, } length = QEMU_ALIGN_UP(length, BDRV_SECTOR_SIZE); ret = bdrv_truncate(s->extents[i].file, length, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { return ret; } diff --git a/tests/test-block-iothread.c b/tests/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-block-iothread.c +++ b/tests/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_truncate(BdrvChild *c) int ret; /* Normal success path */ - ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, NULL); + ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, 0, NULL); g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ - ret = bdrv_truncate(c, -2, false, PREALLOC_MODE_OFF, NULL); + ret = bdrv_truncate(c, -2, false, PREALLOC_MODE_OFF, 0, NULL); g_assert_cmpint(ret, ==, -EINVAL); /* Error: Read-only image */ c->bs->read_only = true; c->bs->open_flags &= ~BDRV_O_RDWR; - ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, NULL); + ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, 0, NULL); g_assert_cmpint(ret, ==, -EACCES); c->bs->read_only = false; -- 2.25.3 Now that node level interface bdrv_truncate() supports passing request flags to the block driver, expose this on the BlockBackend level, too. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424125448.63318-4-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/sysemu/block-backend.h | 2 +- block.c | 3 ++- block/block-backend.c | 4 ++-- block/commit.c | 4 ++-- block/crypto.c | 2 +- block/mirror.c | 2 +- block/qcow2.c | 4 ++-- block/qed.c | 2 +- block/vdi.c | 2 +- block/vhdx.c | 4 ++-- block/vmdk.c | 6 +++--- block/vpc.c | 2 +- blockdev.c | 2 +- qemu-img.c | 2 +- qemu-io-cmds.c | 2 +- 15 files changed, 22 insertions(+), 21 deletions(-) diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf, int bytes); int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp); + PreallocMode prealloc, BdrvRequestFlags flags, Error **errp); int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes); int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, int64_t pos, int size); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int64_t create_file_fallback_truncate(BlockBackend *blk, int64_t size; int ret; - ret = blk_truncate(blk, minimum_size, false, PREALLOC_MODE_OFF, &local_err); + ret = blk_truncate(blk, minimum_size, false, PREALLOC_MODE_OFF, 0, + &local_err); if (ret < 0 && ret != -ENOTSUP) { error_propagate(errp, local_err); return ret; diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf, } int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, Error **errp) { if (!blk_is_available(blk)) { error_setg(errp, "No medium inserted"); return -ENOMEDIUM; } - return bdrv_truncate(blk->root, offset, exact, prealloc, 0, errp); + return bdrv_truncate(blk->root, offset, exact, prealloc, flags, errp); } int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) } if (base_len < len) { - ret = blk_truncate(s->base, len, false, PREALLOC_MODE_OFF, NULL); + ret = blk_truncate(s->base, len, false, PREALLOC_MODE_OFF, 0, NULL); if (ret) { goto out; } @@ -XXX,XX +XXX,XX @@ int bdrv_commit(BlockDriverState *bs) * grow the backing file image if possible. If not possible, * we must return an error */ if (length > backing_length) { - ret = blk_truncate(backing, length, false, PREALLOC_MODE_OFF, + ret = blk_truncate(backing, length, false, PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_init_func(QCryptoBlock *block, * which will be used by the crypto header */ return blk_truncate(data->blk, data->size + headerlen, false, - data->prealloc, errp); + data->prealloc, 0, errp); } diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_run(Job *job, Error **errp) if (s->bdev_length > base_length) { ret = blk_truncate(s->target, s->bdev_length, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { goto immediate_exit; } diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) /* Okay, now that we have a valid image, let's give it the right size */ ret = blk_truncate(blk, qcow2_opts->size, false, qcow2_opts->preallocation, - errp); + 0, errp); if (ret < 0) { error_prepend(errp, "Could not resize image: "); goto out; @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, * Amending image options should ensure that the image has * exactly the given new values, so pass exact=true here. */ - ret = blk_truncate(blk, new_size, true, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, new_size, true, PREALLOC_MODE_OFF, 0, errp); blk_unref(blk); if (ret < 0) { return ret; diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts, * The QED format associates file length with allocation status, * so a new file (which is empty) must have a length of 0. */ - ret = blk_truncate(blk, 0, true, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, 0, true, PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto out; } diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, if (image_type == VDI_TYPE_STATIC) { ret = blk_truncate(blk, offset + blocks * block_size, false, - PREALLOC_MODE_OFF, errp); + PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { error_prepend(errp, "Failed to statically allocate file"); goto exit; diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s, /* All zeroes, so we can just extend the file - the end of the BAT * is the furthest thing we have written yet */ ret = blk_truncate(blk, data_file_offset, false, PREALLOC_MODE_OFF, - errp); + 0, errp); if (ret < 0) { goto exit; } } else if (type == VHDX_TYPE_FIXED) { ret = blk_truncate(blk, data_file_offset + image_size, false, - PREALLOC_MODE_OFF, errp); + PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto exit; } diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_init_extent(BlockBackend *blk, int gd_buf_size; if (flat) { - ret = blk_truncate(blk, filesize, false, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, filesize, false, PREALLOC_MODE_OFF, 0, errp); goto exit; } magic = cpu_to_be32(VMDK4_MAGIC); @@ -XXX,XX +XXX,XX @@ static int vmdk_init_extent(BlockBackend *blk, } ret = blk_truncate(blk, le64_to_cpu(header.grain_offset) << 9, false, - PREALLOC_MODE_OFF, errp); + PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vmdk_co_do_create(int64_t size, /* bdrv_pwrite write padding zeros to align to sector, we don't need that * for description file */ if (desc_offset == 0) { - ret = blk_truncate(blk, desc_len, false, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, desc_len, false, PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto exit; } diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ static int create_fixed_disk(BlockBackend *blk, uint8_t *buf, /* Add footer to total size */ total_size += HEADER_SIZE; - ret = blk_truncate(blk, total_size, false, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, total_size, false, PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { return ret; } diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_block_resize(bool has_device, const char *device, } bdrv_drained_begin(bs); - ret = blk_truncate(blk, size, false, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, size, false, PREALLOC_MODE_OFF, 0, errp); bdrv_drained_end(bs); out: diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_resize(int argc, char **argv) * resizing, so pass @exact=true. It is of no use to report * success when the image has not actually been resized. */ - ret = blk_truncate(blk, total_size, true, prealloc, &err); + ret = blk_truncate(blk, total_size, true, prealloc, 0, &err); if (!ret) { qprintf(quiet, "Image resized.\n"); } else { diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int truncate_f(BlockBackend *blk, int argc, char **argv) * exact=true. It is better to err on the "emit more errors" side * than to be overly permissive. */ - ret = blk_truncate(blk, offset, true, PREALLOC_MODE_OFF, &local_err); + ret = blk_truncate(blk, offset, true, PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); return ret; -- 2.25.3 If BDRV_REQ_ZERO_WRITE is set and we're extending the image, calling qcow2_cluster_zeroize() with flags=0 does the right thing: It doesn't undo any previous preallocation, but just adds the zero flag to all relevant L2 entries. If an external data file is in use, a write_zeroes request to the data file is made instead. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200424125448.63318-5-kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-cluster.c | 2 +- block/qcow2.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 1 deletion(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset, /* Caller must pass aligned values, except at image end */ assert(QEMU_IS_ALIGNED(offset, s->cluster_size)); assert(QEMU_IS_ALIGNED(end_offset, s->cluster_size) || - end_offset == bs->total_sectors << BDRV_SECTOR_BITS); + end_offset >= bs->total_sectors << BDRV_SECTOR_BITS); /* The zero flag is only supported by version 3 and newer */ if (s->qcow_version < 3) { diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, bs->supported_zero_flags = header.version >= 3 ? BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK : 0; + bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; /* Repair image if dirty */ if (!(flags & (BDRV_O_CHECK | BDRV_O_INACTIVE)) && !bs->read_only && @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, g_assert_not_reached(); } + if ((flags & BDRV_REQ_ZERO_WRITE) && offset > old_length) { + uint64_t zero_start = QEMU_ALIGN_UP(old_length, s->cluster_size); + + /* + * Use zero clusters as much as we can. qcow2_cluster_zeroize() + * requires a cluster-aligned start. The end may be unaligned if it is + * at the end of the image (which it is here). + */ + ret = qcow2_cluster_zeroize(bs, zero_start, offset - zero_start, 0); + if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to zero out new clusters"); + goto fail; + } + + /* Write explicit zeros for the unaligned head */ + if (zero_start > old_length) { + uint64_t len = zero_start - old_length; + uint8_t *buf = qemu_blockalign0(bs, len); + QEMUIOVector qiov; + qemu_iovec_init_buf(&qiov, buf, len); + + qemu_co_mutex_unlock(&s->lock); + ret = qcow2_co_pwritev_part(bs, old_length, len, &qiov, 0, 0); + qemu_co_mutex_lock(&s->lock); + + qemu_vfree(buf); + if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to zero out the new area"); + goto fail; + } + } + } + if (prealloc != PREALLOC_MODE_OFF) { /* Flush metadata before actually changing the image size */ ret = qcow2_write_caches(bs); -- 2.25.3 The raw format driver can simply forward the flag and let its bs->file child take care of actually providing the zeros. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200424125448.63318-6-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/raw-format.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, s->size = offset; offset += s->offset; - return bdrv_co_truncate(bs->file, offset, exact, prealloc, 0, errp); + return bdrv_co_truncate(bs->file, offset, exact, prealloc, flags, errp); } static void raw_eject(BlockDriverState *bs, bool eject_flag) @@ -XXX,XX +XXX,XX @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED | ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) & bs->file->bs->supported_zero_flags); + bs->supported_truncate_flags = bs->file->bs->supported_truncate_flags & + BDRV_REQ_ZERO_WRITE; if (bs->probed && !bdrv_is_read_only(bs)) { bdrv_refresh_filename(bs->file->bs); -- 2.25.3 For regular files, we always get BDRV_REQ_ZERO_WRITE behaviour from the OS, so we can advertise the flag and just ignore it. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424125448.63318-7-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/file-posix.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options, #endif bs->supported_zero_flags = BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK; + if (S_ISREG(st.st_mode)) { + /* When extending regular files, we get zeros from the OS */ + bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; + } ret = 0; fail: if (filename && (bdrv_flags & BDRV_O_TEMPORARY)) { -- 2.25.3 When extending the size of an image that has a backing file larger than its old size, make sure that the backing file data doesn't become visible in the guest, but the added area is properly zeroed out. Consider the following scenario where the overlay is shorter than its backing file: base.qcow2: AAAAAAAA overlay.qcow2: BBBB When resizing (extending) overlay.qcow2, the new blocks should not stay unallocated and make the additional As from base.qcow2 visible like before this patch, but zeros should be read. A similar case happens with the various variants of a commit job when an intermediate file is short (- for unallocated): base.qcow2: A-A-AAAA mid.qcow2: BB-B top.qcow2: C--C--C- After commit top.qcow2 to mid.qcow2, the following happens: mid.qcow2: CB-C00C0 (correct result) mid.qcow2: CB-C--C- (before this fix) Without the fix, blocks that previously read as zeros on top.qcow2 suddenly turn into A. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200424125448.63318-8-kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, goto out; } + /* + * If the image has a backing file that is large enough that it would + * provide data for the new area, we cannot leave it unallocated because + * then the backing file content would become visible. Instead, zero-fill + * the new area. + * + * Note that if the image has a backing file, but was opened without the + * backing file, taking care of keeping things consistent with that backing + * file is the user's responsibility. + */ + if (new_bytes && bs->backing) { + int64_t backing_len; + + backing_len = bdrv_getlength(backing_bs(bs)); + if (backing_len < 0) { + ret = backing_len; + error_setg_errno(errp, -ret, "Could not get backing file size"); + goto out; + } + + if (backing_len > old_size) { + flags |= BDRV_REQ_ZERO_WRITE; + } + } + if (drv->bdrv_co_truncate) { if (flags & ~bs->supported_truncate_flags) { error_setg(errp, "Block driver does not support requested flags"); -- 2.25.3 We want to keep TEST_IMG for the full path of the main test image, but filter_testfiles() must be called for other test images before replacing other things like the image format because the test directory path could contain the format as a substring. Insert a filter_testfiles() call between both. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200424125448.63318-9-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/iotests.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def filter_img_info(output, filename): for line in output.split('\n'): if 'disk size' in line or 'actual-size' in line: continue - line = line.replace(filename, 'TEST_IMG') \ - .replace(imgfmt, 'IMGFMT') + line = line.replace(filename, 'TEST_IMG') + line = filter_testfiles(line) + line = line.replace(imgfmt, 'IMGFMT') line = re.sub('iters: [0-9]+', 'iters: XXX', line) line = re.sub('uuid: [-a-f0-9]+', 'uuid: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX', line) line = re.sub('cid: [0-9]+', 'cid: XXXXXXXXXX', line) -- 2.25.3 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200424125448.63318-10-kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/274 | 155 +++++++++++++++++++++ tests/qemu-iotests/274.out | 268 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/group | 1 + 3 files changed, 424 insertions(+) create mode 100755 tests/qemu-iotests/274 create mode 100644 tests/qemu-iotests/274.out diff --git a/tests/qemu-iotests/274 b/tests/qemu-iotests/274 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/274 @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Copyright (C) 2019 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# +# Creator/Owner: Kevin Wolf <kwolf@redhat.com> +# +# Some tests for short backing files and short overlays + +import iotests + +iotests.verify_image_format(supported_fmts=['qcow2']) +iotests.verify_platform(['linux']) + +size_short = 1 * 1024 * 1024 +size_long = 2 * 1024 * 1024 +size_diff = size_long - size_short + +def create_chain() -> None: + iotests.qemu_img_log('create', '-f', iotests.imgfmt, base, + str(size_long)) + iotests.qemu_img_log('create', '-f', iotests.imgfmt, '-b', base, mid, + str(size_short)) + iotests.qemu_img_log('create', '-f', iotests.imgfmt, '-b', mid, top, + str(size_long)) + + iotests.qemu_io_log('-c', 'write -P 1 0 %d' % size_long, base) + +def create_vm() -> iotests.VM: + vm = iotests.VM() + vm.add_blockdev('file,filename=%s,node-name=base-file' % base) + vm.add_blockdev('%s,file=base-file,node-name=base' % iotests.imgfmt) + vm.add_blockdev('file,filename=%s,node-name=mid-file' % mid) + vm.add_blockdev('%s,file=mid-file,node-name=mid,backing=base' + % iotests.imgfmt) + vm.add_drive(top, 'backing=mid,node-name=top') + return vm + +with iotests.FilePath('base') as base, \ + iotests.FilePath('mid') as mid, \ + iotests.FilePath('top') as top: + + iotests.log('== Commit tests ==') + + create_chain() + + iotests.log('=== Check visible data ===') + + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, top) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), top) + + iotests.log('=== Checking allocation status ===') + + iotests.qemu_io_log('-c', 'alloc 0 %d' % size_short, + '-c', 'alloc %d %d' % (size_short, size_diff), + base) + + iotests.qemu_io_log('-c', 'alloc 0 %d' % size_short, + '-c', 'alloc %d %d' % (size_short, size_diff), + mid) + + iotests.qemu_io_log('-c', 'alloc 0 %d' % size_short, + '-c', 'alloc %d %d' % (size_short, size_diff), + top) + + iotests.log('=== Checking map ===') + + iotests.qemu_img_log('map', '--output=json', base) + iotests.qemu_img_log('map', '--output=human', base) + iotests.qemu_img_log('map', '--output=json', mid) + iotests.qemu_img_log('map', '--output=human', mid) + iotests.qemu_img_log('map', '--output=json', top) + iotests.qemu_img_log('map', '--output=human', top) + + iotests.log('=== Testing qemu-img commit (top -> mid) ===') + + iotests.qemu_img_log('commit', top) + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + + iotests.log('=== Testing HMP commit (top -> mid) ===') + + create_chain() + with create_vm() as vm: + vm.launch() + vm.qmp_log('human-monitor-command', command_line='commit drive0') + + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + + iotests.log('=== Testing QMP active commit (top -> mid) ===') + + create_chain() + with create_vm() as vm: + vm.launch() + vm.qmp_log('block-commit', device='top', base_node='mid', + job_id='job0', auto_dismiss=False) + vm.run_job('job0', wait=5) + + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + + + iotests.log('== Resize tests ==') + + # Use different sizes for different allocation modes: + # + # We want to have at least one test where 32 bit truncation in the size of + # the overlapping area becomes visible. This is covered by the + # prealloc='off' case (1G to 6G is an overlap of 5G). + # + # However, we can only do this for modes that don't preallocate data + # because otherwise we might run out of space on the test host. + # + # We also want to test some unaligned combinations. + for (prealloc, base_size, top_size_old, top_size_new, off) in [ + ('off', '6G', '1G', '8G', '5G'), + ('metadata', '32G', '30G', '33G', '31G'), + ('falloc', '10M', '5M', '15M', '9M'), + ('full', '16M', '8M', '12M', '11M'), + ('off', '384k', '253k', '512k', '253k'), + ('off', '400k', '256k', '512k', '336k'), + ('off', '512k', '256k', '500k', '436k')]: + + iotests.log('=== preallocation=%s ===' % prealloc) + iotests.qemu_img_log('create', '-f', iotests.imgfmt, base, base_size) + iotests.qemu_img_log('create', '-f', iotests.imgfmt, '-b', base, top, + top_size_old) + iotests.qemu_io_log('-c', 'write -P 1 %s 64k' % off, base) + + # After this, top_size_old to base_size should be allocated/zeroed. + # + # In theory, leaving base_size to top_size_new unallocated would be + # correct, but in practice, if we zero out anything, we zero out + # everything up to top_size_new. + iotests.qemu_img_log('resize', '-f', iotests.imgfmt, + '--preallocation', prealloc, top, top_size_new) + iotests.qemu_io_log('-c', 'read -P 0 %s 64k' % off, top) + iotests.qemu_io_log('-c', 'map', top) + iotests.qemu_img_log('map', '--output=json', top) diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ +== Commit tests == +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Check visible data === +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Checking allocation status === +1048576/1048576 bytes allocated at offset 0 bytes +1048576/1048576 bytes allocated at offset 1 MiB + +0/1048576 bytes allocated at offset 0 bytes +0/0 bytes allocated at offset 1 MiB + +0/1048576 bytes allocated at offset 0 bytes +0/1048576 bytes allocated at offset 1 MiB + +=== Checking map === +[{ "start": 0, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": 327680}] + +Offset Length Mapped to File +0 0x200000 0x50000 TEST_DIR/PID-base + +[{ "start": 0, "length": 1048576, "depth": 1, "zero": false, "data": true, "offset": 327680}] + +Offset Length Mapped to File +0 0x100000 0x50000 TEST_DIR/PID-base + +[{ "start": 0, "length": 1048576, "depth": 2, "zero": false, "data": true, "offset": 327680}, +{ "start": 1048576, "length": 1048576, "depth": 0, "zero": true, "data": false}] + +Offset Length Mapped to File +0 0x100000 0x50000 TEST_DIR/PID-base + +=== Testing qemu-img commit (top -> mid) === +Image committed. + +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +Format specific information: + compat: 1.1 + lazy refcounts: false + refcount bits: 16 + corrupt: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing HMP commit (top -> mid) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +{"execute": "human-monitor-command", "arguments": {"command-line": "commit drive0"}} +{"return": ""} +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +Format specific information: + compat: 1.1 + lazy refcounts: false + refcount bits: 16 + corrupt: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing QMP active commit (top -> mid) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +{"execute": "block-commit", "arguments": {"auto-dismiss": false, "base-node": "mid", "device": "top", "job-id": "job0"}} +{"return": {}} +{"execute": "job-complete", "arguments": {"id": "job0"}} +{"return": {}} +{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"execute": "job-dismiss", "arguments": {"id": "job0"}} +{"return": {}} +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +Format specific information: + compat: 1.1 + lazy refcounts: false + refcount bits: 16 + corrupt: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== Resize tests == +=== preallocation=off === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=6442450944 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=1073741824 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 5368709120 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 5368709120 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +1 GiB (0x40000000) bytes not allocated at offset 0 bytes (0x0) +7 GiB (0x1c0000000) bytes allocated at offset 1 GiB (0x40000000) + +[{ "start": 0, "length": 1073741824, "depth": 1, "zero": true, "data": false}, +{ "start": 1073741824, "length": 7516192768, "depth": 0, "zero": true, "data": false}] + +=== preallocation=metadata === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=34359738368 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=32212254720 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 33285996544 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 33285996544 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +30 GiB (0x780000000) bytes not allocated at offset 0 bytes (0x0) +3 GiB (0xc0000000) bytes allocated at offset 30 GiB (0x780000000) + +[{ "start": 0, "length": 32212254720, "depth": 1, "zero": true, "data": false}, +{ "start": 32212254720, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 327680}, +{ "start": 32749125632, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 537264128}, +{ "start": 33285996544, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 1074200576}, +{ "start": 33822867456, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 1611137024}, +{ "start": 34359738368, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 2148139008}, +{ "start": 34896609280, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 2685075456}] + +=== preallocation=falloc === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=10485760 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=5242880 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 9437184 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 9437184 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +5 MiB (0x500000) bytes not allocated at offset 0 bytes (0x0) +10 MiB (0xa00000) bytes allocated at offset 5 MiB (0x500000) + +[{ "start": 0, "length": 5242880, "depth": 1, "zero": true, "data": false}, +{ "start": 5242880, "length": 10485760, "depth": 0, "zero": true, "data": false, "offset": 327680}] + +=== preallocation=full === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=16777216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=8388608 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 11534336 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 11534336 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +8 MiB (0x800000) bytes not allocated at offset 0 bytes (0x0) +4 MiB (0x400000) bytes allocated at offset 8 MiB (0x800000) + +[{ "start": 0, "length": 8388608, "depth": 1, "zero": true, "data": false}, +{ "start": 8388608, "length": 4194304, "depth": 0, "zero": true, "data": false, "offset": 327680}] + +=== preallocation=off === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=393216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=259072 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 259072 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 259072 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +192 KiB (0x30000) bytes not allocated at offset 0 bytes (0x0) +320 KiB (0x50000) bytes allocated at offset 192 KiB (0x30000) + +[{ "start": 0, "length": 196608, "depth": 1, "zero": true, "data": false}, +{ "start": 196608, "length": 65536, "depth": 0, "zero": false, "data": true, "offset": 327680}, +{ "start": 262144, "length": 262144, "depth": 0, "zero": true, "data": false}] + +=== preallocation=off === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=409600 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 344064 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 344064 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +256 KiB (0x40000) bytes not allocated at offset 0 bytes (0x0) +256 KiB (0x40000) bytes allocated at offset 256 KiB (0x40000) + +[{ "start": 0, "length": 262144, "depth": 1, "zero": true, "data": false}, +{ "start": 262144, "length": 262144, "depth": 0, "zero": true, "data": false}] + +=== preallocation=off === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=524288 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 446464 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 446464 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +256 KiB (0x40000) bytes not allocated at offset 0 bytes (0x0) +244 KiB (0x3d000) bytes allocated at offset 256 KiB (0x40000) + +[{ "start": 0, "length": 262144, "depth": 1, "zero": true, "data": false}, +{ "start": 262144, "length": 249856, "depth": 0, "zero": true, "data": false}] + diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -XXX,XX +XXX,XX @@ 270 rw backing quick 272 rw 273 backing quick +274 rw backing 277 rw quick 279 rw backing quick 280 rw migration quick -- 2.25.3 The BDRV_REQ_ZERO_WRITE is currently implemented in a way that first the image is possibly preallocated and then the zero flag is added to all clusters. This means that a copy-on-write operation may be needed when writing to these clusters, despite having used preallocation, negating one of the major benefits of preallocation. Instead, try to forward the BDRV_REQ_ZERO_WRITE to the protocol driver, and if the protocol driver can ensure that the new area reads as zeros, we can skip setting the zero flag in the qcow2 layer. Unfortunately, the same approach doesn't work for metadata preallocation, so we'll still set the zero flag there. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424142701.67053-1-kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.c | 22 +++++++++++++++++++--- tests/qemu-iotests/274.out | 4 ++-- 2 files changed, 21 insertions(+), 5 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, /* Allocate the data area */ new_file_size = allocation_start + nb_new_data_clusters * s->cluster_size; - /* Image file grows, so @exact does not matter */ - ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, 0, - errp); + /* + * Image file grows, so @exact does not matter. + * + * If we need to zero out the new area, try first whether the protocol + * driver can already take care of this. + */ + if (flags & BDRV_REQ_ZERO_WRITE) { + ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, + BDRV_REQ_ZERO_WRITE, NULL); + if (ret >= 0) { + flags &= ~BDRV_REQ_ZERO_WRITE; + } + } else { + ret = -1; + } + if (ret < 0) { + ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, 0, + errp); + } if (ret < 0) { error_prepend(errp, "Failed to resize underlying file: "); qcow2_free_clusters(bs, allocation_start, diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/274.out +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 9437184 10 MiB (0xa00000) bytes allocated at offset 5 MiB (0x500000) [{ "start": 0, "length": 5242880, "depth": 1, "zero": true, "data": false}, -{ "start": 5242880, "length": 10485760, "depth": 0, "zero": true, "data": false, "offset": 327680}] +{ "start": 5242880, "length": 10485760, "depth": 0, "zero": false, "data": true, "offset": 327680}] === preallocation=full === Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=16777216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 11534336 4 MiB (0x400000) bytes allocated at offset 8 MiB (0x800000) [{ "start": 0, "length": 8388608, "depth": 1, "zero": true, "data": false}, -{ "start": 8388608, "length": 4194304, "depth": 0, "zero": true, "data": false, "offset": 327680}] +{ "start": 8388608, "length": 4194304, "depth": 0, "zero": false, "data": true, "offset": 327680}] === preallocation=off === Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=393216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -- 2.25.3 From: Andrzej Jakowski <andrzej.jakowski@linux.intel.com> This patch introduces support for PMR that has been defined as part of NVMe 1.4 spec. User can now specify a pmrdev option that should point to HostMemoryBackend. pmrdev memory region will subsequently be exposed as PCI BAR 2 in emulated NVMe device. Guest OS can perform mmio read and writes to the PMR region that will stay persistent across system reboot. Signed-off-by: Andrzej Jakowski <andrzej.jakowski@linux.intel.com> Reviewed-by: Klaus Jensen <k.jensen@samsung.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20200330164656.9348-1-andrzej.jakowski@linux.intel.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- hw/block/nvme.h | 2 + include/block/nvme.h | 172 +++++++++++++++++++++++++++++++++++++++++ hw/block/nvme.c | 109 ++++++++++++++++++++++++++ hw/block/Makefile.objs | 2 +- hw/block/trace-events | 4 + 5 files changed, 288 insertions(+), 1 deletion(-) diff --git a/hw/block/nvme.h b/hw/block/nvme.h index XXXXXXX..XXXXXXX 100644 --- a/hw/block/nvme.h +++ b/hw/block/nvme.h @@ -XXX,XX +XXX,XX @@ typedef struct NvmeCtrl { uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */ char *serial; + HostMemoryBackend *pmrdev; + NvmeNamespace *namespaces; NvmeSQueue **sq; NvmeCQueue **cq; diff --git a/include/block/nvme.h b/include/block/nvme.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -XXX,XX +XXX,XX @@ typedef struct NvmeBar { uint64_t acq; uint32_t cmbloc; uint32_t cmbsz; + uint8_t padding[3520]; /* not used by QEMU */ + uint32_t pmrcap; + uint32_t pmrctl; + uint32_t pmrsts; + uint32_t pmrebs; + uint32_t pmrswtp; + uint32_t pmrmsc; } NvmeBar; enum NvmeCapShift { @@ -XXX,XX +XXX,XX @@ enum NvmeCapShift { CAP_CSS_SHIFT = 37, CAP_MPSMIN_SHIFT = 48, CAP_MPSMAX_SHIFT = 52, + CAP_PMR_SHIFT = 56, }; enum NvmeCapMask { @@ -XXX,XX +XXX,XX @@ enum NvmeCapMask { CAP_CSS_MASK = 0xff, CAP_MPSMIN_MASK = 0xf, CAP_MPSMAX_MASK = 0xf, + CAP_PMR_MASK = 0x1, }; #define NVME_CAP_MQES(cap) (((cap) >> CAP_MQES_SHIFT) & CAP_MQES_MASK) @@ -XXX,XX +XXX,XX @@ enum NvmeCapMask { << CAP_MPSMIN_SHIFT) #define NVME_CAP_SET_MPSMAX(cap, val) (cap |= (uint64_t)(val & CAP_MPSMAX_MASK)\ << CAP_MPSMAX_SHIFT) +#define NVME_CAP_SET_PMRS(cap, val) (cap |= (uint64_t)(val & CAP_PMR_MASK)\ + << CAP_PMR_SHIFT) enum NvmeCcShift { CC_EN_SHIFT = 0, @@ -XXX,XX +XXX,XX @@ enum NvmeCmbszMask { #define NVME_CMBSZ_GETSIZE(cmbsz) \ (NVME_CMBSZ_SZ(cmbsz) * (1 << (12 + 4 * NVME_CMBSZ_SZU(cmbsz)))) +enum NvmePmrcapShift { + PMRCAP_RDS_SHIFT = 3, + PMRCAP_WDS_SHIFT = 4, + PMRCAP_BIR_SHIFT = 5, + PMRCAP_PMRTU_SHIFT = 8, + PMRCAP_PMRWBM_SHIFT = 10, + PMRCAP_PMRTO_SHIFT = 16, + PMRCAP_CMSS_SHIFT = 24, +}; + +enum NvmePmrcapMask { + PMRCAP_RDS_MASK = 0x1, + PMRCAP_WDS_MASK = 0x1, + PMRCAP_BIR_MASK = 0x7, + PMRCAP_PMRTU_MASK = 0x3, + PMRCAP_PMRWBM_MASK = 0xf, + PMRCAP_PMRTO_MASK = 0xff, + PMRCAP_CMSS_MASK = 0x1, +}; + +#define NVME_PMRCAP_RDS(pmrcap) \ + ((pmrcap >> PMRCAP_RDS_SHIFT) & PMRCAP_RDS_MASK) +#define NVME_PMRCAP_WDS(pmrcap) \ + ((pmrcap >> PMRCAP_WDS_SHIFT) & PMRCAP_WDS_MASK) +#define NVME_PMRCAP_BIR(pmrcap) \ + ((pmrcap >> PMRCAP_BIR_SHIFT) & PMRCAP_BIR_MASK) +#define NVME_PMRCAP_PMRTU(pmrcap) \ + ((pmrcap >> PMRCAP_PMRTU_SHIFT) & PMRCAP_PMRTU_MASK) +#define NVME_PMRCAP_PMRWBM(pmrcap) \ + ((pmrcap >> PMRCAP_PMRWBM_SHIFT) & PMRCAP_PMRWBM_MASK) +#define NVME_PMRCAP_PMRTO(pmrcap) \ + ((pmrcap >> PMRCAP_PMRTO_SHIFT) & PMRCAP_PMRTO_MASK) +#define NVME_PMRCAP_CMSS(pmrcap) \ + ((pmrcap >> PMRCAP_CMSS_SHIFT) & PMRCAP_CMSS_MASK) + +#define NVME_PMRCAP_SET_RDS(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_RDS_MASK) << PMRCAP_RDS_SHIFT) +#define NVME_PMRCAP_SET_WDS(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_WDS_MASK) << PMRCAP_WDS_SHIFT) +#define NVME_PMRCAP_SET_BIR(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_BIR_MASK) << PMRCAP_BIR_SHIFT) +#define NVME_PMRCAP_SET_PMRTU(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_PMRTU_MASK) << PMRCAP_PMRTU_SHIFT) +#define NVME_PMRCAP_SET_PMRWBM(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_PMRWBM_MASK) << PMRCAP_PMRWBM_SHIFT) +#define NVME_PMRCAP_SET_PMRTO(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_PMRTO_MASK) << PMRCAP_PMRTO_SHIFT) +#define NVME_PMRCAP_SET_CMSS(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_CMSS_MASK) << PMRCAP_CMSS_SHIFT) + +enum NvmePmrctlShift { + PMRCTL_EN_SHIFT = 0, +}; + +enum NvmePmrctlMask { + PMRCTL_EN_MASK = 0x1, +}; + +#define NVME_PMRCTL_EN(pmrctl) ((pmrctl >> PMRCTL_EN_SHIFT) & PMRCTL_EN_MASK) + +#define NVME_PMRCTL_SET_EN(pmrctl, val) \ + (pmrctl |= (uint64_t)(val & PMRCTL_EN_MASK) << PMRCTL_EN_SHIFT) + +enum NvmePmrstsShift { + PMRSTS_ERR_SHIFT = 0, + PMRSTS_NRDY_SHIFT = 8, + PMRSTS_HSTS_SHIFT = 9, + PMRSTS_CBAI_SHIFT = 12, +}; + +enum NvmePmrstsMask { + PMRSTS_ERR_MASK = 0xff, + PMRSTS_NRDY_MASK = 0x1, + PMRSTS_HSTS_MASK = 0x7, + PMRSTS_CBAI_MASK = 0x1, +}; + +#define NVME_PMRSTS_ERR(pmrsts) \ + ((pmrsts >> PMRSTS_ERR_SHIFT) & PMRSTS_ERR_MASK) +#define NVME_PMRSTS_NRDY(pmrsts) \ + ((pmrsts >> PMRSTS_NRDY_SHIFT) & PMRSTS_NRDY_MASK) +#define NVME_PMRSTS_HSTS(pmrsts) \ + ((pmrsts >> PMRSTS_HSTS_SHIFT) & PMRSTS_HSTS_MASK) +#define NVME_PMRSTS_CBAI(pmrsts) \ + ((pmrsts >> PMRSTS_CBAI_SHIFT) & PMRSTS_CBAI_MASK) + +#define NVME_PMRSTS_SET_ERR(pmrsts, val) \ + (pmrsts |= (uint64_t)(val & PMRSTS_ERR_MASK) << PMRSTS_ERR_SHIFT) +#define NVME_PMRSTS_SET_NRDY(pmrsts, val) \ + (pmrsts |= (uint64_t)(val & PMRSTS_NRDY_MASK) << PMRSTS_NRDY_SHIFT) +#define NVME_PMRSTS_SET_HSTS(pmrsts, val) \ + (pmrsts |= (uint64_t)(val & PMRSTS_HSTS_MASK) << PMRSTS_HSTS_SHIFT) +#define NVME_PMRSTS_SET_CBAI(pmrsts, val) \ + (pmrsts |= (uint64_t)(val & PMRSTS_CBAI_MASK) << PMRSTS_CBAI_SHIFT) + +enum NvmePmrebsShift { + PMREBS_PMRSZU_SHIFT = 0, + PMREBS_RBB_SHIFT = 4, + PMREBS_PMRWBZ_SHIFT = 8, +}; + +enum NvmePmrebsMask { + PMREBS_PMRSZU_MASK = 0xf, + PMREBS_RBB_MASK = 0x1, + PMREBS_PMRWBZ_MASK = 0xffffff, +}; + +#define NVME_PMREBS_PMRSZU(pmrebs) \ + ((pmrebs >> PMREBS_PMRSZU_SHIFT) & PMREBS_PMRSZU_MASK) +#define NVME_PMREBS_RBB(pmrebs) \ + ((pmrebs >> PMREBS_RBB_SHIFT) & PMREBS_RBB_MASK) +#define NVME_PMREBS_PMRWBZ(pmrebs) \ + ((pmrebs >> PMREBS_PMRWBZ_SHIFT) & PMREBS_PMRWBZ_MASK) + +#define NVME_PMREBS_SET_PMRSZU(pmrebs, val) \ + (pmrebs |= (uint64_t)(val & PMREBS_PMRSZU_MASK) << PMREBS_PMRSZU_SHIFT) +#define NVME_PMREBS_SET_RBB(pmrebs, val) \ + (pmrebs |= (uint64_t)(val & PMREBS_RBB_MASK) << PMREBS_RBB_SHIFT) +#define NVME_PMREBS_SET_PMRWBZ(pmrebs, val) \ + (pmrebs |= (uint64_t)(val & PMREBS_PMRWBZ_MASK) << PMREBS_PMRWBZ_SHIFT) + +enum NvmePmrswtpShift { + PMRSWTP_PMRSWTU_SHIFT = 0, + PMRSWTP_PMRSWTV_SHIFT = 8, +}; + +enum NvmePmrswtpMask { + PMRSWTP_PMRSWTU_MASK = 0xf, + PMRSWTP_PMRSWTV_MASK = 0xffffff, +}; + +#define NVME_PMRSWTP_PMRSWTU(pmrswtp) \ + ((pmrswtp >> PMRSWTP_PMRSWTU_SHIFT) & PMRSWTP_PMRSWTU_MASK) +#define NVME_PMRSWTP_PMRSWTV(pmrswtp) \ + ((pmrswtp >> PMRSWTP_PMRSWTV_SHIFT) & PMRSWTP_PMRSWTV_MASK) + +#define NVME_PMRSWTP_SET_PMRSWTU(pmrswtp, val) \ + (pmrswtp |= (uint64_t)(val & PMRSWTP_PMRSWTU_MASK) << PMRSWTP_PMRSWTU_SHIFT) +#define NVME_PMRSWTP_SET_PMRSWTV(pmrswtp, val) \ + (pmrswtp |= (uint64_t)(val & PMRSWTP_PMRSWTV_MASK) << PMRSWTP_PMRSWTV_SHIFT) + +enum NvmePmrmscShift { + PMRMSC_CMSE_SHIFT = 1, + PMRMSC_CBA_SHIFT = 12, +}; + +enum NvmePmrmscMask { + PMRMSC_CMSE_MASK = 0x1, + PMRMSC_CBA_MASK = 0xfffffffffffff, +}; + +#define NVME_PMRMSC_CMSE(pmrmsc) \ + ((pmrmsc >> PMRMSC_CMSE_SHIFT) & PMRMSC_CMSE_MASK) +#define NVME_PMRMSC_CBA(pmrmsc) \ + ((pmrmsc >> PMRMSC_CBA_SHIFT) & PMRMSC_CBA_MASK) + +#define NVME_PMRMSC_SET_CMSE(pmrmsc, val) \ + (pmrmsc |= (uint64_t)(val & PMRMSC_CMSE_MASK) << PMRMSC_CMSE_SHIFT) +#define NVME_PMRMSC_SET_CBA(pmrmsc, val) \ + (pmrmsc |= (uint64_t)(val & PMRMSC_CBA_MASK) << PMRMSC_CBA_SHIFT) + typedef struct NvmeCmd { uint8_t opcode; uint8_t fuse; diff --git a/hw/block/nvme.c b/hw/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/nvme.c +++ b/hw/block/nvme.c @@ -XXX,XX +XXX,XX @@ * -drive file=<file>,if=none,id=<drive_id> * -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>, \ * cmb_size_mb=<cmb_size_mb[optional]>, \ + * [pmrdev=<mem_backend_file_id>,] \ * num_queues=<N[optional]> * * Note cmb_size_mb denotes size of CMB in MB. CMB is assumed to be at * offset 0 in BAR2 and supports only WDS, RDS and SQS for now. + * + * cmb_size_mb= and pmrdev= options are mutually exclusive due to limitation + * in available BAR's. cmb_size_mb= will take precedence over pmrdev= when + * both provided. + * Enabling pmr emulation can be achieved by pointing to memory-backend-file. + * For example: + * -object memory-backend-file,id=<mem_id>,share=on,mem-path=<file_path>, \ + * size=<size> .... -device nvme,...,pmrdev=<mem_id> */ #include "qemu/osdep.h" @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "qapi/error.h" #include "qapi/visitor.h" +#include "sysemu/hostmem.h" #include "sysemu/block-backend.h" +#include "exec/ram_addr.h" #include "qemu/log.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, NVME_GUEST_ERR(nvme_ub_mmiowr_cmbsz_readonly, "invalid write to read only CMBSZ, ignored"); return; + case 0xE00: /* PMRCAP */ + NVME_GUEST_ERR(nvme_ub_mmiowr_pmrcap_readonly, + "invalid write to PMRCAP register, ignored"); + return; + case 0xE04: /* TODO PMRCTL */ + break; + case 0xE08: /* PMRSTS */ + NVME_GUEST_ERR(nvme_ub_mmiowr_pmrsts_readonly, + "invalid write to PMRSTS register, ignored"); + return; + case 0xE0C: /* PMREBS */ + NVME_GUEST_ERR(nvme_ub_mmiowr_pmrebs_readonly, + "invalid write to PMREBS register, ignored"); + return; + case 0xE10: /* PMRSWTP */ + NVME_GUEST_ERR(nvme_ub_mmiowr_pmrswtp_readonly, + "invalid write to PMRSWTP register, ignored"); + return; + case 0xE14: /* TODO PMRMSC */ + break; default: NVME_GUEST_ERR(nvme_ub_mmiowr_invalid, "invalid MMIO write," @@ -XXX,XX +XXX,XX @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) } if (addr < sizeof(n->bar)) { + /* + * When PMRWBM bit 1 is set then read from + * from PMRSTS should ensure prior writes + * made it to persistent media + */ + if (addr == 0xE08 && + (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) { + qemu_ram_writeback(n->pmrdev->mr.ram_block, + 0, n->pmrdev->size); + } memcpy(&val, ptr + addr, size); } else { NVME_GUEST_ERR(nvme_ub_mmiord_invalid_ofs, @@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) error_setg(errp, "serial property not set"); return; } + + if (!n->cmb_size_mb && n->pmrdev) { + if (host_memory_backend_is_mapped(n->pmrdev)) { + char *path = object_get_canonical_path_component(OBJECT(n->pmrdev)); + error_setg(errp, "can't use already busy memdev: %s", path); + g_free(path); + return; + } + + if (!is_power_of_2(n->pmrdev->size)) { + error_setg(errp, "pmr backend size needs to be power of 2 in size"); + return; + } + + host_memory_backend_set_mapped(n->pmrdev, true); + } + blkconf_blocksizes(&n->conf); if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk), false, errp)) { @@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 | PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem); + } else if (n->pmrdev) { + /* Controller Capabilities register */ + NVME_CAP_SET_PMRS(n->bar.cap, 1); + + /* PMR Capabities register */ + n->bar.pmrcap = 0; + NVME_PMRCAP_SET_RDS(n->bar.pmrcap, 0); + NVME_PMRCAP_SET_WDS(n->bar.pmrcap, 0); + NVME_PMRCAP_SET_BIR(n->bar.pmrcap, 2); + NVME_PMRCAP_SET_PMRTU(n->bar.pmrcap, 0); + /* Turn on bit 1 support */ + NVME_PMRCAP_SET_PMRWBM(n->bar.pmrcap, 0x02); + NVME_PMRCAP_SET_PMRTO(n->bar.pmrcap, 0); + NVME_PMRCAP_SET_CMSS(n->bar.pmrcap, 0); + + /* PMR Control register */ + n->bar.pmrctl = 0; + NVME_PMRCTL_SET_EN(n->bar.pmrctl, 0); + + /* PMR Status register */ + n->bar.pmrsts = 0; + NVME_PMRSTS_SET_ERR(n->bar.pmrsts, 0); + NVME_PMRSTS_SET_NRDY(n->bar.pmrsts, 0); + NVME_PMRSTS_SET_HSTS(n->bar.pmrsts, 0); + NVME_PMRSTS_SET_CBAI(n->bar.pmrsts, 0); + + /* PMR Elasticity Buffer Size register */ + n->bar.pmrebs = 0; + NVME_PMREBS_SET_PMRSZU(n->bar.pmrebs, 0); + NVME_PMREBS_SET_RBB(n->bar.pmrebs, 0); + NVME_PMREBS_SET_PMRWBZ(n->bar.pmrebs, 0); + + /* PMR Sustained Write Throughput register */ + n->bar.pmrswtp = 0; + NVME_PMRSWTP_SET_PMRSWTU(n->bar.pmrswtp, 0); + NVME_PMRSWTP_SET_PMRSWTV(n->bar.pmrswtp, 0); + + /* PMR Memory Space Control register */ + n->bar.pmrmsc = 0; + NVME_PMRMSC_SET_CMSE(n->bar.pmrmsc, 0); + NVME_PMRMSC_SET_CBA(n->bar.pmrmsc, 0); + + pci_register_bar(pci_dev, NVME_PMRCAP_BIR(n->bar.pmrcap), + PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 | + PCI_BASE_ADDRESS_MEM_PREFETCH, &n->pmrdev->mr); } for (i = 0; i < n->num_namespaces; i++) { @@ -XXX,XX +XXX,XX @@ static void nvme_exit(PCIDevice *pci_dev) if (n->cmb_size_mb) { g_free(n->cmbuf); } + + if (n->pmrdev) { + host_memory_backend_set_mapped(n->pmrdev, false); + } msix_uninit_exclusive_bar(pci_dev); } static Property nvme_props[] = { DEFINE_BLOCK_PROPERTIES(NvmeCtrl, conf), + DEFINE_PROP_LINK("pmrdev", NvmeCtrl, pmrdev, TYPE_MEMORY_BACKEND, + HostMemoryBackend *), DEFINE_PROP_STRING("serial", NvmeCtrl, serial), DEFINE_PROP_UINT32("cmb_size_mb", NvmeCtrl, cmb_size_mb, 0), DEFINE_PROP_UINT32("num_queues", NvmeCtrl, num_queues, 64), diff --git a/hw/block/Makefile.objs b/hw/block/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/block/Makefile.objs +++ b/hw/block/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_PFLASH_CFI02) += pflash_cfi02.o common-obj-$(CONFIG_XEN) += xen-block.o common-obj-$(CONFIG_ECC) += ecc.o common-obj-$(CONFIG_ONENAND) += onenand.o -common-obj-$(CONFIG_NVME_PCI) += nvme.o common-obj-$(CONFIG_SWIM) += swim.o common-obj-$(CONFIG_SH4) += tc58128.o obj-$(CONFIG_VIRTIO_BLK) += virtio-blk.o obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk.o +obj-$(CONFIG_NVME_PCI) += nvme.o obj-y += dataplane/ diff --git a/hw/block/trace-events b/hw/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/block/trace-events +++ b/hw/block/trace-events @@ -XXX,XX +XXX,XX @@ nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CA nvme_ub_mmiowr_ssreset_unsupported(void) "attempted NVM subsystem reset but CAP.NSSRS is zero (not supported)" nvme_ub_mmiowr_cmbloc_reserved(void) "invalid write to reserved CMBLOC when CMBSZ is zero, ignored" nvme_ub_mmiowr_cmbsz_readonly(void) "invalid write to read only CMBSZ, ignored" +nvme_ub_mmiowr_pmrcap_readonly(void) "invalid write to read only PMRCAP, ignored" +nvme_ub_mmiowr_pmrsts_readonly(void) "invalid write to read only PMRSTS, ignored" +nvme_ub_mmiowr_pmrebs_readonly(void) "invalid write to read only PMREBS, ignored" +nvme_ub_mmiowr_pmrswtp_readonly(void) "invalid write to read only PMRSWTP, ignored" nvme_ub_mmiowr_invalid(uint64_t offset, uint64_t data) "invalid MMIO write, offset=0x%"PRIx64", data=0x%"PRIx64"" nvme_ub_mmiord_misaligned32(uint64_t offset) "MMIO read not 32-bit aligned, offset=0x%"PRIx64"" nvme_ub_mmiord_toosmall(uint64_t offset) "MMIO read smaller than 32-bits, offset=0x%"PRIx64"" -- 2.25.3 The QMP handler qmp_object_add() and the implementation of --object in qemu-storage-daemon can share most of the code. Currently, qemu-storage-daemon calls qmp_object_add(), but this is not correct because different visitors need to be used. As a first step towards a fix, make qmp_object_add() a wrapper around a new function user_creatable_add_dict() that can get an additional parameter. The handling of "props" is only required for compatibility and not required for the qemu-storage-daemon command line, so it stays in qmp_object_add(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qom/object_interfaces.h | 12 ++++++++++++ qom/object_interfaces.c | 27 +++++++++++++++++++++++++++ qom/qom-qmp-cmds.c | 24 +----------------------- 3 files changed, 40 insertions(+), 23 deletions(-) diff --git a/include/qom/object_interfaces.h b/include/qom/object_interfaces.h index XXXXXXX..XXXXXXX 100644 --- a/include/qom/object_interfaces.h +++ b/include/qom/object_interfaces.h @@ -XXX,XX +XXX,XX @@ Object *user_creatable_add_type(const char *type, const char *id, const QDict *qdict, Visitor *v, Error **errp); +/** + * user_creatable_add_dict: + * @qdict: the object definition + * @errp: if an error occurs, a pointer to an area to store the error + * + * Create an instance of the user creatable object that is defined by + * @qdict. The object type is taken from the QDict key 'qom-type', its + * ID from the key 'id'. The remaining entries in @qdict are used to + * initialize the object properties. + */ +void user_creatable_add_dict(QDict *qdict, Error **errp); + /** * user_creatable_add_opts: * @opts: the object definition diff --git a/qom/object_interfaces.c b/qom/object_interfaces.c index XXXXXXX..XXXXXXX 100644 --- a/qom/object_interfaces.c +++ b/qom/object_interfaces.c @@ -XXX,XX +XXX,XX @@ #include "qapi/qmp/qerror.h" #include "qapi/qmp/qjson.h" #include "qapi/qmp/qstring.h" +#include "qapi/qobject-input-visitor.h" #include "qom/object_interfaces.h" #include "qemu/help_option.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ out: return obj; } +void user_creatable_add_dict(QDict *qdict, Error **errp) +{ + Visitor *v; + Object *obj; + g_autofree char *type = NULL; + g_autofree char *id = NULL; + + type = g_strdup(qdict_get_try_str(qdict, "qom-type")); + if (!type) { + error_setg(errp, QERR_MISSING_PARAMETER, "qom-type"); + return; + } + qdict_del(qdict, "qom-type"); + + id = g_strdup(qdict_get_try_str(qdict, "id")); + if (!id) { + error_setg(errp, QERR_MISSING_PARAMETER, "id"); + return; + } + qdict_del(qdict, "id"); + + v = qobject_input_visitor_new(QOBJECT(qdict)); + obj = user_creatable_add_type(type, id, qdict, v, errp); + visit_free(v); + object_unref(obj); +} Object *user_creatable_add_opts(QemuOpts *opts, Error **errp) { diff --git a/qom/qom-qmp-cmds.c b/qom/qom-qmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qom/qom-qmp-cmds.c +++ b/qom/qom-qmp-cmds.c @@ -XXX,XX +XXX,XX @@ #include "qapi/qapi-commands-qom.h" #include "qapi/qmp/qdict.h" #include "qapi/qmp/qerror.h" -#include "qapi/qobject-input-visitor.h" #include "qemu/cutils.h" #include "qom/object_interfaces.h" #include "qom/qom-qobject.h" @@ -XXX,XX +XXX,XX @@ void qmp_object_add(QDict *qdict, QObject **ret_data, Error **errp) { QObject *props; QDict *pdict; - Visitor *v; - Object *obj; - g_autofree char *type = NULL; - g_autofree char *id = NULL; - - type = g_strdup(qdict_get_try_str(qdict, "qom-type")); - if (!type) { - error_setg(errp, QERR_MISSING_PARAMETER, "qom-type"); - return; - } - qdict_del(qdict, "qom-type"); - - id = g_strdup(qdict_get_try_str(qdict, "id")); - if (!id) { - error_setg(errp, QERR_MISSING_PARAMETER, "id"); - return; - } - qdict_del(qdict, "id"); props = qdict_get(qdict, "props"); if (props) { @@ -XXX,XX +XXX,XX @@ void qmp_object_add(QDict *qdict, QObject **ret_data, Error **errp) qobject_unref(pdict); } - v = qobject_input_visitor_new(QOBJECT(qdict)); - obj = user_creatable_add_type(type, id, qdict, v, errp); - visit_free(v); - object_unref(obj); + user_creatable_add_dict(qdict, errp); } void qmp_object_del(const char *id, Error **errp) -- 2.25.3 After processing the option string with the keyval parser, we get a QDict that contains only strings. This QDict must be fed to a keyval visitor which converts the strings into the right data types. qmp_object_add(), however, uses the normal QObject input visitor, which expects a QDict where all properties already have the QType that matches the data type required by the QOM object type. Change the --object implementation in qemu-storage-daemon so that it doesn't call qmp_object_add(), but calls user_creatable_add_dict() directly instead and pass it a new keyval boolean that decides which visitor must be used. Reported-by: Coiby Xu <coiby.xu@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qom/object_interfaces.h | 6 +++++- qemu-storage-daemon.c | 4 +--- qom/object_interfaces.c | 8 ++++++-- qom/qom-qmp-cmds.c | 2 +- 4 files changed, 13 insertions(+), 7 deletions(-) diff --git a/include/qom/object_interfaces.h b/include/qom/object_interfaces.h index XXXXXXX..XXXXXXX 100644 --- a/include/qom/object_interfaces.h +++ b/include/qom/object_interfaces.h @@ -XXX,XX +XXX,XX @@ Object *user_creatable_add_type(const char *type, const char *id, /** * user_creatable_add_dict: * @qdict: the object definition + * @keyval: if true, use a keyval visitor for processing @qdict (i.e. + * assume that all @qdict values are strings); otherwise, use + * the normal QObject visitor (i.e. assume all @qdict values + * have the QType expected by the QOM object type) * @errp: if an error occurs, a pointer to an area to store the error * * Create an instance of the user creatable object that is defined by @@ -XXX,XX +XXX,XX @@ Object *user_creatable_add_type(const char *type, const char *id, * ID from the key 'id'. The remaining entries in @qdict are used to * initialize the object properties. */ -void user_creatable_add_dict(QDict *qdict, Error **errp); +void user_creatable_add_dict(QDict *qdict, bool keyval, Error **errp); /** * user_creatable_add_opts: diff --git a/qemu-storage-daemon.c b/qemu-storage-daemon.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-storage-daemon.c +++ b/qemu-storage-daemon.c @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) QemuOpts *opts; const char *type; QDict *args; - QObject *ret_data = NULL; /* FIXME The keyval parser rejects 'help' arguments, so we must * unconditionall try QemuOpts first. */ @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) qemu_opts_del(opts); args = keyval_parse(optarg, "qom-type", &error_fatal); - qmp_object_add(args, &ret_data, &error_fatal); + user_creatable_add_dict(args, true, &error_fatal); qobject_unref(args); - qobject_unref(ret_data); break; } default: diff --git a/qom/object_interfaces.c b/qom/object_interfaces.c index XXXXXXX..XXXXXXX 100644 --- a/qom/object_interfaces.c +++ b/qom/object_interfaces.c @@ -XXX,XX +XXX,XX @@ out: return obj; } -void user_creatable_add_dict(QDict *qdict, Error **errp) +void user_creatable_add_dict(QDict *qdict, bool keyval, Error **errp) { Visitor *v; Object *obj; @@ -XXX,XX +XXX,XX @@ void user_creatable_add_dict(QDict *qdict, Error **errp) } qdict_del(qdict, "id"); - v = qobject_input_visitor_new(QOBJECT(qdict)); + if (keyval) { + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + } else { + v = qobject_input_visitor_new(QOBJECT(qdict)); + } obj = user_creatable_add_type(type, id, qdict, v, errp); visit_free(v); object_unref(obj); diff --git a/qom/qom-qmp-cmds.c b/qom/qom-qmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qom/qom-qmp-cmds.c +++ b/qom/qom-qmp-cmds.c @@ -XXX,XX +XXX,XX @@ void qmp_object_add(QDict *qdict, QObject **ret_data, Error **errp) qobject_unref(pdict); } - user_creatable_add_dict(qdict, errp); + user_creatable_add_dict(qdict, false, errp); } void qmp_object_del(const char *id, Error **errp) -- 2.25.3