rpms/qemu-kvm
5
0
Fork 0
Code Issues Pull Requests Releases Activity

import qemu-kvm-4.2.0-52.module+el8.5.0+11386+ef5875dd

Browse Source
This commit is contained in:
CentOS Sources 2021-06-29 18:52:21 +00:00 committed by Andrew Lukoshko
parent 63c0d3bd35
commit b8d4c1fef6
5 changed files with 702 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

76
SOURCES/kvm-block-file-posix-Fix-problem-with-fallocate-PUNCH_HO.patch Normal file
View File

@ -0,0 +1,76 @@
From 8c339c3535728179acc94deb5b922aebcfac9ab6 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 3 Jun 2021 16:13:34 -0400
Subject: [PATCH 2/4] block/file-posix: Fix problem with fallocate(PUNCH_HOLE)
on GPFS
RH-Author: Thomas Huth <thuth@redhat.com>
Message-id: <20210603161334.607005-2-thuth@redhat.com>
Patchwork-id: 101673
O-Subject: [RHEL-8.5.0 qemu-kvm PATCH 1/1] block/file-posix: Fix problem with fallocate(PUNCH_HOLE) on GPFS
Bugzilla: 1944861
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Laszlo Ersek <lersek@redhat.com>
A customer reported that running
qemu-img convert -t none -O qcow2 -f qcow2 input.qcow2 output.qcow2
fails for them with the following error message when the images are
stored on a GPFS file system :
qemu-img: error while writing sector 0: Invalid argument
After analyzing the strace output, it seems like the problem is in
handle_aiocb_write_zeroes(): The call to fallocate(FALLOC_FL_PUNCH_HOLE)
returns EINVAL, which can apparently happen if the file system has
a different idea of the granularity of the operation. It's arguably
a bug in GPFS, since the PUNCH_HOLE mode should not result in EINVAL
according to the man-page of fallocate(), but the file system is out
there in production and so we have to deal with it. In commit 294682cc3a
("block: workaround for unaligned byte range in fallocate()") we also
already applied the a work-around for the same problem to the earlier
fallocate(FALLOC_FL_ZERO_RANGE) call, so do it now similar with the
PUNCH_HOLE call. But instead of silently catching and returning
-ENOTSUP (which causes the caller to fall back to writing zeroes),
let's rather inform the user once about the buggy file system and
try the other fallback instead.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20210527172020.847617-2-thuth@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 73ebf29729d1a40feaa9f8ab8951b6ee6dbfbede)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1944861
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/file-posix.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/block/file-posix.c b/block/file-posix.c
index 62a463229f..371572f1b0 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -1587,6 +1587,17 @@ static int handle_aiocb_write_zeroes(void *opaque)
return ret;
}
s->has_fallocate = false;
+ } else if (ret == -EINVAL) {
+ /*
+ * Some file systems like older versions of GPFS do not like un-
+ * aligned byte ranges, and return EINVAL in such a case, though
+ * they should not do it according to the man-page of fallocate().
+ * Warn about the bad filesystem and try the final fallback instead.
+ */
+ warn_report_once("Your file system is misbehaving: "
+ "fallocate(FALLOC_FL_PUNCH_HOLE) returned EINVAL. "
+ "Please report this bug to your file sytem "
+ "vendor.");
} else if (ret != -ENOTSUP) {
return ret;
} else {
--
2.27.0

466
SOURCES/kvm-file-posix-Mitigate-file-fragmentation-with-extent-s.patch Normal file
View File

@ -0,0 +1,466 @@
From 7ee01b5ccb7fc660dafaf3fdb1578649d17fbddf Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 26 May 2021 09:05:52 -0400
Subject: [PATCH 1/4] file-posix: Mitigate file fragmentation with extent size
hints
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20210526090552.155820-2-kwolf@redhat.com>
Patchwork-id: 101638
O-Subject: [RHEL-8.5.0 qemu-kvm PATCH 1/1] file-posix: Mitigate file fragmentation with extent size hints
Bugzilla: 1877163
RH-Acked-by: Sergio Lopez Pascual <slp@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Max Reitz <mreitz@redhat.com>
Especially when O_DIRECT is used with image files so that the page cache
indirection can't cause a merge of allocating requests, the file will
fragment on the file system layer, with a potentially very small
fragment size (this depends on the requests the guest sent).
On Linux, fragmentation can be reduced by setting an extent size hint
when creating the file (at least on XFS, it can't be set any more after
the first extent has been allocated), basically giving raw files a
"cluster size" for allocation.
This adds a create option to set the extent size hint, and changes the
default from not setting a hint to setting it to 1 MB. The main reason
why qcow2 defaults to smaller cluster sizes is that COW becomes more
expensive, which is not an issue with raw files, so we can choose a
larger size. The tradeoff here is only potentially wasted disk space.
For qcow2 (or other image formats) over file-posix, the advantage should
even be greater because they grow sequentially without leaving holes, so
there won't be wasted space. Setting even larger extent size hints for
such images may make sense. This can be done with the new option, but
let's keep the default conservative for now.
The effect is very visible with a test that intentionally creates a
badly fragmented file with qemu-img bench (the time difference while
creating the file is already remarkable) and then looks at the number of
extents and the time a simple "qemu-img map" takes.
Without an extent size hint:
$ ./qemu-img create -f raw -o extent_size_hint=0 ~/tmp/test.raw 10G
Formatting '/home/kwolf/tmp/test.raw', fmt=raw size=10737418240 extent_size_hint=0
$ ./qemu-img bench -f raw -t none -n -w ~/tmp/test.raw -c 1000000 -S 8192 -o 0
Sending 1000000 write requests, 4096 bytes each, 64 in parallel (starting at offset 0, step size 8192)
Run completed in 25.848 seconds.
$ ./qemu-img bench -f raw -t none -n -w ~/tmp/test.raw -c 1000000 -S 8192 -o 4096
Sending 1000000 write requests, 4096 bytes each, 64 in parallel (starting at offset 4096, step size 8192)
Run completed in 19.616 seconds.
$ filefrag ~/tmp/test.raw
/home/kwolf/tmp/test.raw: 2000000 extents found
$ time ./qemu-img map ~/tmp/test.raw
Offset Length Mapped to File
0 0x1e8480000 0 /home/kwolf/tmp/test.raw
real 0m1,279s
user 0m0,043s
sys 0m1,226s
With the new default extent size hint of 1 MB:
$ ./qemu-img create -f raw -o extent_size_hint=1M ~/tmp/test.raw 10G
Formatting '/home/kwolf/tmp/test.raw', fmt=raw size=10737418240 extent_size_hint=1048576
$ ./qemu-img bench -f raw -t none -n -w ~/tmp/test.raw -c 1000000 -S 8192 -o 0
Sending 1000000 write requests, 4096 bytes each, 64 in parallel (starting at offset 0, step size 8192)
Run completed in 11.833 seconds.
$ ./qemu-img bench -f raw -t none -n -w ~/tmp/test.raw -c 1000000 -S 8192 -o 4096
Sending 1000000 write requests, 4096 bytes each, 64 in parallel (starting at offset 4096, step size 8192)
Run completed in 10.155 seconds.
$ filefrag ~/tmp/test.raw
/home/kwolf/tmp/test.raw: 178 extents found
$ time ./qemu-img map ~/tmp/test.raw
Offset Length Mapped to File
0 0x1e8480000 0 /home/kwolf/tmp/test.raw
real 0m0,061s
user 0m0,040s
sys 0m0,014s
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20200707142329.48303-1-kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit ffa244c84a1a30dff69ecc80b0137a2b6d428ecb)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/file-posix.c | 44 ++++++++++++++++++++++++++++++++
include/block/block_int.h | 1 +
qapi/block-core.json | 11 +++++---
tests/qemu-iotests/082.out | 16 ++++++++++++
tests/qemu-iotests/106 | 7 +++--
tests/qemu-iotests/175 | 6 ++---
tests/qemu-iotests/243 | 6 ++---
tests/qemu-iotests/common.filter | 1 +
8 files changed, 80 insertions(+), 12 deletions(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index 2d834fbdf6..62a463229f 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -30,6 +30,7 @@
#include "block/block_int.h"
#include "qemu/module.h"
#include "qemu/option.h"
+#include "qemu/units.h"
#include "trace.h"
#include "block/thread-pool.h"
#include "qemu/iov.h"
@@ -2289,6 +2290,14 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
if (!file_opts->has_preallocation) {
file_opts->preallocation = PREALLOC_MODE_OFF;
}
+ if (!file_opts->has_extent_size_hint) {
+ file_opts->extent_size_hint = 1 * MiB;
+ }
+ if (file_opts->extent_size_hint > UINT32_MAX) {
+ result = -EINVAL;
+ error_setg(errp, "Extent size hint is too large");
+ goto out;
+ }
/* Create file */
fd = qemu_open(file_opts->filename, O_RDWR | O_CREAT | O_BINARY, 0644);
@@ -2346,6 +2355,27 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
}
#endif
}
+#ifdef FS_IOC_FSSETXATTR
+ /*
+ * Try to set the extent size hint. Failure is not fatal, and a warning is
+ * only printed if the option was explicitly specified.
+ */
+ {
+ struct fsxattr attr;
+ result = ioctl(fd, FS_IOC_FSGETXATTR, &attr);
+ if (result == 0) {
+ attr.fsx_xflags |= FS_XFLAG_EXTSIZE;
+ attr.fsx_extsize = file_opts->extent_size_hint;
+ result = ioctl(fd, FS_IOC_FSSETXATTR, &attr);
+ }
+ if (result < 0 && file_opts->has_extent_size_hint &&
+ file_opts->extent_size_hint)
+ {
+ warn_report("Failed to set extent size hint: %s",
+ strerror(errno));
+ }
+ }
+#endif
/* Resize and potentially preallocate the file to the desired
* final size */
@@ -2381,6 +2411,8 @@ static int coroutine_fn raw_co_create_opts(BlockDriver *drv,
{
BlockdevCreateOptions options;
int64_t total_size = 0;
+ int64_t extent_size_hint = 0;
+ bool has_extent_size_hint = false;
bool nocow = false;
PreallocMode prealloc;
char *buf = NULL;
@@ -2392,6 +2424,11 @@ static int coroutine_fn raw_co_create_opts(BlockDriver *drv,
/* Read out options */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
+ if (qemu_opt_get(opts, BLOCK_OPT_EXTENT_SIZE_HINT)) {
+ has_extent_size_hint = true;
+ extent_size_hint =
+ qemu_opt_get_size_del(opts, BLOCK_OPT_EXTENT_SIZE_HINT, -1);
+ }
nocow = qemu_opt_get_bool(opts, BLOCK_OPT_NOCOW, false);
buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
prealloc = qapi_enum_parse(&PreallocMode_lookup, buf,
@@ -2411,6 +2448,8 @@ static int coroutine_fn raw_co_create_opts(BlockDriver *drv,
.preallocation = prealloc,
.has_nocow = true,
.nocow = nocow,
+ .has_extent_size_hint = has_extent_size_hint,
+ .extent_size_hint = extent_size_hint,
},
};
return raw_co_create(&options, errp);
@@ -2902,6 +2941,11 @@ static QemuOptsList raw_create_opts = {
#endif
", full)"
},
+ {
+ .name = BLOCK_OPT_EXTENT_SIZE_HINT,
+ .type = QEMU_OPT_SIZE,
+ .help = "Extent size hint for the image file, 0 to disable"
+ },
{ /* end of list */ }
}
};
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 41f13ecbed..4b23da2eb0 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -53,6 +53,7 @@
#define BLOCK_OPT_ADAPTER_TYPE "adapter_type"
#define BLOCK_OPT_REDUNDANCY "redundancy"
#define BLOCK_OPT_NOCOW "nocow"
+#define BLOCK_OPT_EXTENT_SIZE_HINT "extent_size_hint"
#define BLOCK_OPT_OBJECT_SIZE "object_size"
#define BLOCK_OPT_REFCOUNT_BITS "refcount_bits"
#define BLOCK_OPT_DATA_FILE "data_file"
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 289320902d..c7aa919fa3 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -4272,14 +4272,17 @@
# falloc (if defined CONFIG_POSIX_FALLOCATE),
# full (if defined CONFIG_POSIX))
# @nocow Turn off copy-on-write (valid only on btrfs; default: off)
+# @extent-size-hint: Extent size hint to add to the image file; 0 for not
+# adding an extent size hint (default: 1 MB, since 5.1)
#
# Since: 2.12
##
{ 'struct': 'BlockdevCreateOptionsFile',
- 'data': { 'filename': 'str',
- 'size': 'size',
- '*preallocation': 'PreallocMode',
- '*nocow': 'bool' } }
+ 'data': { 'filename': 'str',
+ 'size': 'size',
+ '*preallocation': 'PreallocMode',
+ '*nocow': 'bool',
+ '*extent-size-hint': 'size'} }
##
# @BlockdevCreateOptionsGluster:
diff --git a/tests/qemu-iotests/082.out b/tests/qemu-iotests/082.out
index 9d4ed4dc9d..7a87946fa2 100644
--- a/tests/qemu-iotests/082.out
+++ b/tests/qemu-iotests/082.out
@@ -59,6 +59,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -82,6 +83,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -105,6 +107,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -128,6 +131,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -151,6 +155,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -174,6 +179,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -197,6 +203,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -220,6 +227,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -339,6 +347,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -362,6 +371,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -385,6 +395,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -408,6 +419,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -431,6 +443,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -454,6 +467,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -477,6 +491,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
@@ -500,6 +515,7 @@ Supported options:
encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
+ extent_size_hint=<size> - Extent size hint for the image file, 0 to disable
lazy_refcounts=<bool (on/off)> - Postpone refcount updates
nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs)
preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full)
diff --git a/tests/qemu-iotests/106 b/tests/qemu-iotests/106
index ac47eaa0f5..ee6f51d08b 100755
--- a/tests/qemu-iotests/106
+++ b/tests/qemu-iotests/106
@@ -51,7 +51,10 @@ for create_mode in off falloc full; do
echo
echo "--- create_mode=$create_mode growth_mode=$growth_mode ---"
- IMGOPTS="preallocation=$create_mode" _make_test_img ${CREATION_SIZE}K
+ # Our calculation below assumes kilobytes as unit for the actual size.
+ # Disable the extent size hint because it would give us a result in
+ # megabytes.
+ IMGOPTS="preallocation=$create_mode,extent_size_hint=0" _make_test_img ${CREATION_SIZE}K
$QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K
expected_size=0
@@ -98,7 +101,7 @@ for growth_mode in falloc full; do
# plain int. We should use the correct type for the result, and
# this tests we do.
- _make_test_img 2G
+ _make_test_img -o "extent_size_hint=0" 2G
$QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K
actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size')
diff --git a/tests/qemu-iotests/175 b/tests/qemu-iotests/175
index 55db2803ed..8a8494aeb6 100755
--- a/tests/qemu-iotests/175
+++ b/tests/qemu-iotests/175
@@ -89,20 +89,20 @@ min_blocks=$(stat -c '%b' "$TEST_DIR/empty")
echo
echo "== creating image with default preallocation =="
-_make_test_img $size | _filter_imgfmt
+_make_test_img -o extent_size_hint=0 $size | _filter_imgfmt
stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $size
for mode in off full falloc; do
echo
echo "== creating image with preallocation $mode =="
- IMGOPTS=preallocation=$mode _make_test_img $size | _filter_imgfmt
+ IMGOPTS="preallocation=$mode,extent_size_hint=0" _make_test_img $size | _filter_imgfmt
stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $size
done
for new_size in 4096 1048576; do
echo
echo "== resize empty image with block_resize =="
- _make_test_img 0 | _filter_imgfmt
+ _make_test_img -o extent_size_hint=0 0 | _filter_imgfmt
_block_resize $TEST_IMG $new_size >/dev/null
stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $new_size
done
diff --git a/tests/qemu-iotests/243 b/tests/qemu-iotests/243
index e563761307..104c7256c4 100755
--- a/tests/qemu-iotests/243
+++ b/tests/qemu-iotests/243
@@ -47,7 +47,7 @@ for mode in off metadata falloc full; do
echo "=== preallocation=$mode ==="
echo
- IMGOPTS="preallocation=$mode" _make_test_img 64M
+ IMGOPTS="preallocation=$mode,extent_size_hint=0" _make_test_img 64M
printf "File size: "
du -b $TEST_IMG | cut -f1
@@ -64,7 +64,7 @@ for mode in off metadata falloc full; do
echo "=== External data file: preallocation=$mode ==="
echo
- IMGOPTS="data_file=$TEST_IMG.data,preallocation=$mode" _make_test_img 64M
+ IMGOPTS="data_file=$TEST_IMG.data,preallocation=$mode,extent_size_hint=0" _make_test_img 64M
echo -n "qcow2 file size: "
du -b $TEST_IMG | cut -f1
@@ -75,7 +75,7 @@ for mode in off metadata falloc full; do
echo -n "qcow2 disk usage: "
[ $(du -B1 $TEST_IMG | cut -f1) -lt 1048576 ] && echo "low" || echo "high"
echo -n "data disk usage: "
- [ $(du -B1 $TEST_IMG.data | cut -f1) -lt 1048576 ] && echo "low" || echo "high"
+ [ $(du -B1 $TEST_IMG.data | cut -f1) -lt 2097152 ] && echo "low" || echo "high"
done
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index c8e8663665..f29c1d3238 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -146,6 +146,7 @@ _filter_img_create()
-e "s# refcount_bits=[0-9]\\+##g" \
-e "s# key-secret=[a-zA-Z0-9]\\+##g" \
-e "s# iter-time=[0-9]\\+##g" \
+ -e "s# extent_size_hint=[0-9]\\+##g" \
-e "s# force_size=\\(on\\|off\\)##g"
}
--
2.27.0

50
SOURCES/kvm-spapr-Remove-stale-comment-about-power-saving-LPCR-b.patch Normal file
View File

@ -0,0 +1,50 @@
From b46fdf56b1a7938468565838bdadf260870e4f9b Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Wed, 9 Jun 2021 10:05:00 -0400
Subject: [PATCH 3/4] spapr: Remove stale comment about power-saving LPCR bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
Message-id: <20210609100501.427096-2-lvivier@redhat.com>
Patchwork-id: 101682
O-Subject: [RHEL-8.5.0 qemu-kvm PATCH 1/2] spapr: Remove stale comment about power-saving LPCR bits
Bugzilla: 1969768
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: David Gibson <dgibson@redhat.com>
RH-Acked-by: Greg Kurz <gkurz@redhat.com>
From: Nicholas Piggin <npiggin@gmail.com>
Commit 47a9b551547 ("spapr: Clean up handling of LPCR power-saving exit
bits") moved this logic but did not remove the comment from the
previous location.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Message-Id: <20210526091626.3388262-2-npiggin@gmail.com>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: Greg Kurz <groug@kaod.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 7be3bf6c8429969f97728bb712d9a99997835607)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
hw/ppc/spapr_rtas.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
index 8d8d8cdfcb..295eac986e 100644
--- a/hw/ppc/spapr_rtas.c
+++ b/hw/ppc/spapr_rtas.c
@@ -163,7 +163,6 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr,
env->msr = (1ULL << MSR_SF) | (1ULL << MSR_ME);
- /* Enable Power-saving mode Exit Cause exceptions for the new CPU */
lpcr = env->spr[SPR_LPCR];
if (!pcc->interrupts_big_endian(callcpu)) {
lpcr |= LPCR_ILE;
--
2.27.0

89
SOURCES/kvm-spapr-Set-LPCR-to-current-AIL-mode-when-starting-a-n.patch Normal file
View File

@ -0,0 +1,89 @@
From 28794dca79a94d01c8732b84fe6ac6ba2986ce45 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Wed, 9 Jun 2021 10:05:01 -0400
Subject: [PATCH 4/4] spapr: Set LPCR to current AIL mode when starting a new
CPU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
Message-id: <20210609100501.427096-3-lvivier@redhat.com>
Patchwork-id: 101683
O-Subject: [RHEL-8.5.0 qemu-kvm PATCH 2/2] spapr: Set LPCR to current AIL mode when starting a new CPU
Bugzilla: 1969768
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: David Gibson <dgibson@redhat.com>
RH-Acked-by: Greg Kurz <gkurz@redhat.com>
From: Nicholas Piggin <npiggin@gmail.com>
TCG does not keep track of AIL mode in a central place, it's based on
the current LPCR[AIL] bits. Synchronize the new CPU's LPCR to the
current LPCR in rtas_start_cpu(), similarly to the way the ILE bit is
synchronized.
Open-code the ILE setting as well now that the caller's LPCR is
available directly, there is no need for the indirection.
Without this, under both TCG and KVM, adding a POWER8/9/10 class CPU
with a new core ID after a modern Linux has booted results in the new
CPU's LPCR missing the LPCR[AIL]=0b11 setting that the other CPUs have.
This can cause crashes and unexpected behaviour.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Message-Id: <20210526091626.3388262-3-npiggin@gmail.com>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: Greg Kurz <groug@kaod.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit ac559ecbea2649819e7b3fdd09f4e0243e0128db)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
hw/ppc/spapr_rtas.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
index 295eac986e..5acb7c1f10 100644
--- a/hw/ppc/spapr_rtas.c
+++ b/hw/ppc/spapr_rtas.c
@@ -132,8 +132,8 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr,
target_ulong id, start, r3;
PowerPCCPU *newcpu;
CPUPPCState *env;
- PowerPCCPUClass *pcc;
target_ulong lpcr;
+ target_ulong caller_lpcr;
if (nargs != 3 || nret != 1) {
rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
@@ -152,7 +152,6 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr,
}
env = &newcpu->env;
- pcc = POWERPC_CPU_GET_CLASS(newcpu);
if (!CPU(newcpu)->halted) {
rtas_st(rets, 0, RTAS_OUT_HW_ERROR);
@@ -163,10 +162,15 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr,
env->msr = (1ULL << MSR_SF) | (1ULL << MSR_ME);
+ caller_lpcr = callcpu->env.spr[SPR_LPCR];
lpcr = env->spr[SPR_LPCR];
- if (!pcc->interrupts_big_endian(callcpu)) {
- lpcr |= LPCR_ILE;
- }
+
+ /* Set ILE the same way */
+ lpcr = (lpcr & ~LPCR_ILE) | (caller_lpcr & LPCR_ILE);
+
+ /* Set AIL the same way */
+ lpcr = (lpcr & ~LPCR_AIL) | (caller_lpcr & LPCR_AIL);
+
if (env->mmu_model == POWERPC_MMU_3_00) {
/*
* New cpus are expected to start in the same radix/hash mode
--
2.27.0

22
SPECS/qemu-kvm.spec
View File

@ -67,7 +67,7 @@ Obsoletes: %1-rhev
Summary: QEMU is a machine emulator and virtualizer
Name: qemu-kvm
Version: 4.2.0
Release: 51%{?dist}
Release: 52%{?dist}
# Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped
Epoch: 15
License: GPLv2 and GPLv2+ and CC-BY
@ -1164,6 +1164,14 @@ Patch506: kvm-pc-bios-s390-ccw-fix-off-by-one-error.patch
Patch507: kvm-pc-bios-s390-ccw-break-loop-if-a-null-block-number-i.patch
# For bz#1942880 - RHEL8.4 Nightly[0322] - KVM guest fails to find zipl boot menu index (qemu-kvm)
Patch508: kvm-pc-bios-s390-ccw-don-t-try-to-read-the-next-block-if.patch
# For bz#1877163 - [FJ 8.3 Bug] The progress bar of the "virt-clone --nonsparse" command shows the progress rate exceeding 100%.
Patch509: kvm-file-posix-Mitigate-file-fragmentation-with-extent-s.patch
# For bz#1944861 - Qemu-img convert fails when source image is on gpfs
Patch510: kvm-block-file-posix-Fix-problem-with-fallocate-PUNCH_HO.patch
# For bz#1969768 - [ppc64le] Hotplug vcpu device hit call trace:[qemu output] KVM: unknown exit, hardware reason 7fff9ce87ed8
Patch511: kvm-spapr-Remove-stale-comment-about-power-saving-LPCR-b.patch
# For bz#1969768 - [ppc64le] Hotplug vcpu device hit call trace:[qemu output] KVM: unknown exit, hardware reason 7fff9ce87ed8
Patch512: kvm-spapr-Set-LPCR-to-current-AIL-mode-when-starting-a-n.patch
BuildRequires: wget
BuildRequires: rpm-build
@ -2112,6 +2120,18 @@ useradd -r -u 107 -g qemu -G kvm -d / -s /sbin/nologin \
%changelog
* Fri Jun 11 2021 Danilo Cesar Lemes de Paula <ddepaula@redhat.com> - 4.2.0-52.el8
- kvm-file-posix-Mitigate-file-fragmentation-with-extent-s.patch [bz#1877163]
- kvm-block-file-posix-Fix-problem-with-fallocate-PUNCH_HO.patch [bz#1944861]
- kvm-spapr-Remove-stale-comment-about-power-saving-LPCR-b.patch [bz#1969768]
- kvm-spapr-Set-LPCR-to-current-AIL-mode-when-starting-a-n.patch [bz#1969768]
- Resolves: bz#1877163
([FJ 8.3 Bug] The progress bar of the "virt-clone --nonsparse" command shows the progress rate exceeding 100%.)
- Resolves: bz#1944861
(Qemu-img convert fails when source image is on gpfs)
- Resolves: bz#1969768
([ppc64le] Hotplug vcpu device hit call trace:[qemu output] KVM: unknown exit, hardware reason 7fff9ce87ed8)
* Tue May 25 2021 Danilo Cesar Lemes de Paula <ddepaula@redhat.com> - 4.2.0-51.el8
- kvm-linux-headers-Add-VFIO_CCW_REQ_IRQ_INDEX.patch [bz#1940450]
- kvm-vfio-ccw-Connect-the-device-request-notifier.patch [bz#1940450]