If hv_netvsc driver is unloaded and reloaded, the NET_DEVICE_REGISTER
handler cannot perform VF register successfully as the register call
is received before netvsc_probe is finished. This is because we
register register_netdevice_notifier() very early( even before
vmbus_driver_register()).
To fix this, we try to register each such matching VF( if it is visible
as a netdevice) at the end of netvsc_probe.
Cc: stable(a)vger.kernel.org
Fixes: 85520856466e ("hv_netvsc: Fix race of register_netdevice_notifier and VF register")
Suggested-by: Dexuan Cui <decui(a)microsoft.com>
Signed-off-by: Shradha Gupta <shradhagupta(a)linux.microsoft.com>
---
Changes in v2:
* Fixed the subject line of patch with branch details(net)
* Added the logic to attach just the one right vf during register
* Corrected comment messages
* Renamed the context marco with a more appropriate name
* Created a new function to avoid code repetition.
---
drivers/net/hyperv/netvsc_drv.c | 82 +++++++++++++++++++++++++--------
1 file changed, 62 insertions(+), 20 deletions(-)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 273bd8a20122..11831a1c9762 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -42,6 +42,10 @@
#define LINKCHANGE_INT (2 * HZ)
#define VF_TAKEOVER_INT (HZ / 10)
+/* Macros to define the context of vf registration */
+#define VF_REG_IN_PROBE 1
+#define VF_REG_IN_NOTIFIER 2
+
static unsigned int ring_size __ro_after_init = 128;
module_param(ring_size, uint, 0444);
MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
@@ -2185,7 +2189,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
}
static int netvsc_vf_join(struct net_device *vf_netdev,
- struct net_device *ndev)
+ struct net_device *ndev, int context)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
int ret;
@@ -2208,7 +2212,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
goto upper_link_failed;
}
- schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+ /* If this registration is called from probe context vf_takeover
+ * is taken care of later in probe itself.
+ */
+ if (context == VF_REG_IN_NOTIFIER)
+ schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
@@ -2346,7 +2354,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev)
return NOTIFY_DONE;
}
-static int netvsc_register_vf(struct net_device *vf_netdev)
+static int netvsc_register_vf(struct net_device *vf_netdev, int context)
{
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
@@ -2386,7 +2394,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
- if (netvsc_vf_join(vf_netdev, ndev) != 0)
+ if (netvsc_vf_join(vf_netdev, ndev, context) != 0)
return NOTIFY_DONE;
dev_hold(vf_netdev);
@@ -2484,10 +2492,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
return NOTIFY_OK;
}
+static int check_dev_is_matching_vf(struct net_device *event_ndev)
+{
+ /* Skip NetVSC interfaces */
+ if (event_ndev->netdev_ops == &device_ops)
+ return -ENODEV;
+
+ /* Avoid non-Ethernet type devices */
+ if (event_ndev->type != ARPHRD_ETHER)
+ return -ENODEV;
+
+ /* Avoid Vlan dev with same MAC registering as VF */
+ if (is_vlan_dev(event_ndev))
+ return -ENODEV;
+
+ /* Avoid Bonding master dev with same MAC registering as VF */
+ if (netif_is_bond_master(event_ndev))
+ return -ENODEV;
+
+ return 0;
+}
+
static int netvsc_probe(struct hv_device *dev,
const struct hv_vmbus_device_id *dev_id)
{
- struct net_device *net = NULL;
+ struct net_device *net = NULL, *vf_netdev;
struct net_device_context *net_device_ctx;
struct netvsc_device_info *device_info = NULL;
struct netvsc_device *nvdev;
@@ -2599,6 +2628,30 @@ static int netvsc_probe(struct hv_device *dev,
}
list_add(&net_device_ctx->list, &netvsc_dev_list);
+
+ /* When the hv_netvsc driver is unloaded and reloaded, the
+ * NET_DEVICE_REGISTER for the vf device is replayed before probe
+ * is complete. This is because register_netdevice_notifier() gets
+ * registered before vmbus_driver_register() so that callback func
+ * is set before probe and we don't miss events like NETDEV_POST_INIT
+ * So, in this section we try to register the matching vf device that
+ * is present as a netdevice, knowing that its register call is not
+ * processed in the netvsc_netdev_notifier(as probing is progress and
+ * get_netvsc_byslot fails).
+ */
+ for_each_netdev(dev_net(net), vf_netdev) {
+ ret = check_dev_is_matching_vf(vf_netdev);
+ if (ret != 0)
+ continue;
+
+ if (net != get_netvsc_byslot(vf_netdev))
+ continue;
+
+ netvsc_prepare_bonding(vf_netdev);
+ netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
+ __netvsc_vf_setup(net, vf_netdev);
+ break;
+ }
rtnl_unlock();
netvsc_devinfo_put(device_info);
@@ -2754,28 +2807,17 @@ static int netvsc_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+ int ret = 0;
- /* Skip our own events */
- if (event_dev->netdev_ops == &device_ops)
- return NOTIFY_DONE;
-
- /* Avoid non-Ethernet type devices */
- if (event_dev->type != ARPHRD_ETHER)
- return NOTIFY_DONE;
-
- /* Avoid Vlan dev with same MAC registering as VF */
- if (is_vlan_dev(event_dev))
- return NOTIFY_DONE;
-
- /* Avoid Bonding master dev with same MAC registering as VF */
- if (netif_is_bond_master(event_dev))
+ ret = check_dev_is_matching_vf(event_dev);
+ if (ret != 0)
return NOTIFY_DONE;
switch (event) {
case NETDEV_POST_INIT:
return netvsc_prepare_bonding(event_dev);
case NETDEV_REGISTER:
- return netvsc_register_vf(event_dev);
+ return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER);
case NETDEV_UNREGISTER:
return netvsc_unregister_vf(event_dev);
case NETDEV_UP:
--
2.34.1
The patch titled
Subject: nilfs2: fix potential bug in end_buffer_async_write
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
nilfs2-fix-potential-bug-in-end_buffer_async_write.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Subject: nilfs2: fix potential bug in end_buffer_async_write
Date: Sun, 4 Feb 2024 01:16:45 +0900
According to a syzbot report, end_buffer_async_write(), which handles the
completion of block device writes, may detect abnormal condition of the
buffer async_write flag and cause a BUG_ON failure when using nilfs2.
Nilfs2 itself does not use end_buffer_async_write(). But, the async_write
flag is now used as a marker by commit 7f42ec394156 ("nilfs2: fix issue
with race condition of competition between segments for dirty blocks") as
a means of resolving double list insertion of dirty blocks in
nilfs_lookup_dirty_data_buffers() and nilfs_lookup_node_buffers() and the
resulting crash.
This modification is safe as long as it is used for file data and b-tree
node blocks where the page caches are independent. However, it was
irrelevant and redundant to also introduce async_write for segment summary
and super root blocks that share buffers with the backing device. This
led to the possibility that the BUG_ON check in end_buffer_async_write
would fail as described above, if independent writebacks of the backing
device occurred in parallel.
The use of async_write for segment summary buffers has already been
removed in a previous change.
Fix this issue by removing the manipulation of the async_write flag for
the remaining super root block buffer.
Link: https://lkml.kernel.org/r/20240203161645.4992-1-konishi.ryusuke@gmail.com
Fixes: 7f42ec394156 ("nilfs2: fix issue with race condition of competition between segments for dirty blocks")
Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Reported-by: syzbot+5c04210f7c7f897c1e7f(a)syzkaller.appspotmail.com
Closes: https://lkml.kernel.org/r/00000000000019a97c05fd42f8c8@google.com
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
fs/nilfs2/segment.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
--- a/fs/nilfs2/segment.c~nilfs2-fix-potential-bug-in-end_buffer_async_write
+++ a/fs/nilfs2/segment.c
@@ -1703,7 +1703,6 @@ static void nilfs_segctor_prepare_write(
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
- set_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
if (bh->b_folio != bd_folio) {
folio_lock(bd_folio);
@@ -1714,6 +1713,7 @@ static void nilfs_segctor_prepare_write(
}
break;
}
+ set_buffer_async_write(bh);
if (bh->b_folio != fs_folio) {
nilfs_begin_folio_io(fs_folio);
fs_folio = bh->b_folio;
@@ -1800,7 +1800,6 @@ static void nilfs_abort_logs(struct list
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
- clear_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
clear_buffer_uptodate(bh);
if (bh->b_folio != bd_folio) {
@@ -1809,6 +1808,7 @@ static void nilfs_abort_logs(struct list
}
break;
}
+ clear_buffer_async_write(bh);
if (bh->b_folio != fs_folio) {
nilfs_end_folio_io(fs_folio, err);
fs_folio = bh->b_folio;
@@ -1896,8 +1896,9 @@ static void nilfs_segctor_complete_write
BIT(BH_Delay) | BIT(BH_NILFS_Volatile) |
BIT(BH_NILFS_Redirected));
- set_mask_bits(&bh->b_state, clear_bits, set_bits);
if (bh == segbuf->sb_super_root) {
+ set_buffer_uptodate(bh);
+ clear_buffer_dirty(bh);
if (bh->b_folio != bd_folio) {
folio_end_writeback(bd_folio);
bd_folio = bh->b_folio;
@@ -1905,6 +1906,7 @@ static void nilfs_segctor_complete_write
update_sr = true;
break;
}
+ set_mask_bits(&bh->b_state, clear_bits, set_bits);
if (bh->b_folio != fs_folio) {
nilfs_end_folio_io(fs_folio, 0);
fs_folio = bh->b_folio;
_
Patches currently in -mm which might be from konishi.ryusuke(a)gmail.com are
nilfs2-fix-data-corruption-in-dsync-block-recovery-for-small-block-sizes.patch
nilfs2-fix-hang-in-nilfs_lookup_dirty_data_buffers.patch
nilfs2-fix-potential-bug-in-end_buffer_async_write.patch
nilfs2-convert-segment-buffer-to-use-kmap_local.patch
nilfs2-convert-nilfs_copy_buffer-to-use-kmap_local.patch
nilfs2-convert-metadata-file-common-code-to-use-kmap_local.patch
nilfs2-convert-sufile-to-use-kmap_local.patch
nilfs2-convert-persistent-object-allocator-to-use-kmap_local.patch
nilfs2-convert-dat-to-use-kmap_local.patch
nilfs2-move-nilfs_bmap_write-call-out-of-nilfs_write_inode_common.patch
nilfs2-do-not-acquire-rwsem-in-nilfs_bmap_write.patch
nilfs2-convert-ifile-to-use-kmap_local.patch
nilfs2-localize-highmem-mapping-for-checkpoint-creation-within-cpfile.patch
nilfs2-localize-highmem-mapping-for-checkpoint-finalization-within-cpfile.patch
nilfs2-localize-highmem-mapping-for-checkpoint-reading-within-cpfile.patch
nilfs2-remove-nilfs_cpfile_getput_checkpoint.patch
nilfs2-convert-cpfile-to-use-kmap_local.patch
The patch titled
Subject: mm/damon/sysfs-schemes: fix wrong DAMOS tried regions update timeout setup
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
mm-damon-sysfs-schemes-fix-wrong-damos-tried-regions-update-timeout-setup.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: SeongJae Park <sj(a)kernel.org>
Subject: mm/damon/sysfs-schemes: fix wrong DAMOS tried regions update timeout setup
Date: Fri, 2 Feb 2024 11:19:56 -0800
DAMON sysfs interface's update_schemes_tried_regions command has a timeout
of two apply intervals of the DAMOS scheme. Having zero value DAMOS
scheme apply interval means it will use the aggregation interval as the
value. However, the timeout setup logic is mistakenly using the sampling
interval insted of the aggregartion interval for the case. This could
cause earlier-than-expected timeout of the command. Fix it.
Link: https://lkml.kernel.org/r/20240202191956.88791-1-sj@kernel.org
Fixes: 7d6fa31a2fd7 ("mm/damon/sysfs-schemes: add timeout for update_schemes_tried_regions")
Signed-off-by: SeongJae Park <sj(a)kernel.org>
Cc: <stable(a)vger.kernel.org> # 6.7.x
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/damon/sysfs-schemes.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/damon/sysfs-schemes.c~mm-damon-sysfs-schemes-fix-wrong-damos-tried-regions-update-timeout-setup
+++ a/mm/damon/sysfs-schemes.c
@@ -2194,7 +2194,7 @@ static void damos_tried_regions_init_upd
sysfs_regions->upd_timeout_jiffies = jiffies +
2 * usecs_to_jiffies(scheme->apply_interval_us ?
scheme->apply_interval_us :
- ctx->attrs.sample_interval);
+ ctx->attrs.aggr_interval);
}
}
_
Patches currently in -mm which might be from sj(a)kernel.org are
mm-damon-sysfs-schemes-fix-wrong-damos-tried-regions-update-timeout-setup.patch
docs-admin-guide-mm-damon-usage-use-sysfs-interface-for-tracepoints-example.patch
mm-damon-rename-config_damon_dbgfs-to-damon_dbgfs_deprecated.patch
mm-damon-dbgfs-implement-deprecation-notice-file.patch
mm-damon-dbgfs-make-debugfs-interface-deprecation-message-a-macro.patch
docs-admin-guide-mm-damon-usage-document-deprecated-file-of-damon-debugfs-interface.patch
selftets-damon-prepare-for-monitor_on-file-renaming.patch
mm-damon-dbgfs-rename-monitor_on-file-to-monitor_on_deprecated.patch
docs-admin-guide-mm-damon-usage-update-for-monitor_on-renaming.patch
docs-translations-damon-usage-update-for-monitor_on-renaming.patch
Hi Greg and Sasha,
On Tue, Jan 30, 2024 at 01:53:37PM +0100, Johan Hovold wrote:
> On Mon, Jan 22, 2024 at 09:54:15PM +0000, Mark Brown wrote:
> > On Mon, 22 Jan 2024 19:18:15 +0100, Johan Hovold wrote:
> > > To reduce the risk of speaker damage the PA gain needs to be limited on
> > > machines like the Lenovo Thinkpad X13s until we have active speaker
> > > protection in place.
> > >
> > > Limit the gain to the current default setting provided by the UCM
> > > configuration which most user have so far been using (due to a bug in
> > > the configuration files which prevented hardware volume control [1]).
> > >
> > > [...]
> >
> > Applied to
> >
> > https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
>
> alsa-ucm-conf 1.2.11 was released yesterday, which means that it is now
> very urgent to get the speaker volume limitation backported to the
> stable trees.
>
> Could you please try to make sure that these fixes get to Linus this
> week?
This series (and a related headphone codec fix) were merged into Linus's
tree yesterday.
I saw that the 6.7.4 stable patches were sent out for review over night,
but could it be possible to squeeze in also the following four fixes in
6.7.4 (and 6.6.16)?
c481016bb4f8 ASoC: qcom: sc8280xp: limit speaker volumes
4d0e8bdfa4a5 ASoC: codecs: wcd938x: fix headphones volume controls
46188db080bd ASoC: codecs: lpass-wsa-macro: fix compander volume hack
b53cc6144a3f ASoC: codecs: wsa883x: fix PA volume control
These are needed for proper volume control and, importantly, to prevent
users of the Lenovo ThinkPad X13s from potentially damaging their
speakers when the distros ship the latest UCM configuration files which
were released on Monday.
Johan
Hi Greg
Kernel does *NOT* boot here on x86_64 (Intel Rocket Lake: i5-11400) and
Fedora 39
just after grub the box is dead; not pingable, etc ...
Thanks
Tested-by: Ronald Warsow <rwarsow(a)gmx.de>
From: Yonghong Song <yonghong.song(a)linux.dev>
[ Upstream commit 56925f389e152dcb8d093435d43b78a310539c23 ]
With previous patch, one of subtests in test_btf_id becomes
flaky and may fail. The following is a failing example:
Error: #26 btf
Error: #26/174 btf/BTF ID
Error: #26/174 btf/BTF ID
btf_raw_create:PASS:check 0 nsec
btf_raw_create:PASS:check 0 nsec
test_btf_id:PASS:check 0 nsec
...
test_btf_id:PASS:check 0 nsec
test_btf_id:FAIL:check BTF lingersdo_test_get_info:FAIL:check failed: -1
The test tries to prove a btf_id not available after the map is closed.
But btf_id is freed only after workqueue and a rcu grace period, compared
to previous case just after a rcu grade period.
Depending on system workload, workqueue could take quite some time
to execute function bpf_map_free_deferred() which may cause the test failure.
Instead of adding arbitrary delays, let us remove the logic to
check btf_id availability after map is closed.
Signed-off-by: Yonghong Song <yonghong.song(a)linux.dev>
Link: https://lore.kernel.org/r/20231214203820.1469402-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast(a)kernel.org>
[Samasth: backport for 6.6.y]
Signed-off-by: Samasth Norway Ananda <samasth.norway.ananda(a)oracle.com>
---
Above patch is a fix for 59e5791f59dd ("bpf: Fix a race condition between
btf_put() and map_free()"). While the commit causing the error is
present in 6.6.y the fix is not present.
---
tools/testing/selftests/bpf/prog_tests/btf.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 92d51f377fe5..0c0881c7eb1a 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -4630,11 +4630,6 @@ static int test_btf_id(unsigned int test_num)
/* The map holds the last ref to BTF and its btf_id */
close(map_fd);
map_fd = -1;
- btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
- if (CHECK(btf_fd[0] >= 0, "BTF lingers")) {
- err = -1;
- goto done;
- }
fprintf(stderr, "OK");
--
2.42.0