Hi,
A number of laptops with Mediatek wifi the wifi doesn't work unless you
turn off fast boot in BIOS setup.
These laptops all ship with fast boot as the default.
It's been fixed by this commit:
09d4d6da1b65 ("wifi: mt76: mt7921e: Set memory space enable in
PCI_COMMAND if unset")
Can you please bring it to 5.15.y and later?
Thanks,
The self-refresh helper framework overloads "disable" to sometimes mean
"go into self-refresh mode," and this mode activates automatically
(e.g., after some period of unchanging display output). In such cases,
the display pipe is still considered "on", and user-space is not aware
that we went into self-refresh mode. Thus, users may expect that
vblank-related features (such as DRM_IOCTL_WAIT_VBLANK) still work
properly.
However, we trigger the WARN_ONCE() here if a CRTC driver tries to leave
vblank enabled.
Add a different expectation: that CRTCs *should* leave vblank enabled
when going into self-refresh.
This patch is preparation for another patch -- "drm/rockchip: vop: Leave
vblank enabled in self-refresh" -- which resolves conflicts between the
above self-refresh behavior and the API tests in IGT's kms_vblank test
module.
== Some alternatives discussed: ==
It's likely that on many display controllers, vblank interrupts will
turn off when the CRTC is disabled, and so in some cases, self-refresh
may not support vblank. To support such cases, we might consider
additions to the generic helpers such that we fire vblank events based
on a timer.
However, there is currently only one driver using the common
self-refresh helpers (i.e., rockchip), and at least as of commit
bed030a49f3e ("drm/rockchip: Don't fully disable vop on self refresh"),
the CRTC hardware is powered enough to continue to generate vblank
interrupts.
So we chose the simpler option of leaving vblank interrupts enabled. We
can reevaluate this decision and perhaps augment the helpers if/when we
gain a second driver that has different requirements.
v3:
* include discussion summary
v2:
* add 'ret != 0' warning case for self-refresh
* describe failing test case and relation to drm/rockchip patch better
Cc: <stable(a)vger.kernel.org> # dependency for "drm/rockchip: vop: Leave
# vblank enabled in self-refresh"
Signed-off-by: Brian Norris <briannorris(a)chromium.org>
---
drivers/gpu/drm/drm_atomic_helper.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index d579fd8f7cb8..a22485e3e924 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1209,7 +1209,16 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
continue;
ret = drm_crtc_vblank_get(crtc);
- WARN_ONCE(ret != -EINVAL, "driver forgot to call drm_crtc_vblank_off()\n");
+ /*
+ * Self-refresh is not a true "disable"; ensure vblank remains
+ * enabled.
+ */
+ if (new_crtc_state->self_refresh_active)
+ WARN_ONCE(ret != 0,
+ "driver disabled vblank in self-refresh\n");
+ else
+ WARN_ONCE(ret != -EINVAL,
+ "driver forgot to call drm_crtc_vblank_off()\n");
if (ret == 0)
drm_crtc_vblank_put(crtc);
}
--
2.39.0.314.g84b9a713c41-goog
Serialize the ath10k implementation of the wake_tx_queue ops.
ath10k_mac_op_wake_tx_queue() must not run concurrent since it's using
ieee80211_txq_schedule_start().
Fixes: bb2edb733586 ("ath10k: migrate to mac80211 txq scheduling")
Reported-by: Felix Fietkau <nbd(a)nbd.name>
Link: https://lore.kernel.org/r/519b5bb9-8899-ae7c-4eff-f3116cdfdb56@nbd.name
CC: <stable(a)vger.kernel.org>
Signed-off-by: Alexander Wetzel <alexander(a)wetzel-home.de>
---
The intend of this patch is to sort out an issue discovered in the discussion
referred to by the Link tag.
I can't test it with real HW and thus just implemented the per-ac queue lock
Felix suggested. One obvious alternative to the per-ac lock would be to
bring back the txqs_lock commit bb2edb733586 ("ath10k: migrate to mac80211 txq
scheduling") dropped.
Alexander
---
drivers/net/wireless/ath/ath10k/core.c | 3 +++
drivers/net/wireless/ath/ath10k/core.h | 3 +++
drivers/net/wireless/ath/ath10k/mac.c | 6 ++++--
3 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 5eb131ab916f..533ed7169e11 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -3643,6 +3643,9 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
mutex_init(&ar->dump_mutex);
spin_lock_init(&ar->data_lock);
+ for (int ac = 0; ac < IEEE80211_NUM_ACS; ac++)
+ spin_lock_init(&ar->queue_lock[ac]);
+
INIT_LIST_HEAD(&ar->peers);
init_waitqueue_head(&ar->peer_mapping_wq);
init_waitqueue_head(&ar->htt.empty_tx_wq);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index f5de8ce8fb45..4b5239de4018 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -1170,6 +1170,9 @@ struct ath10k {
/* protects shared structure data */
spinlock_t data_lock;
+ /* serialize wake_tx_queue calls per ac */
+ spinlock_t queue_lock[IEEE80211_NUM_ACS];
+
struct list_head arvifs;
struct list_head peers;
struct ath10k_peer *peer_map[ATH10K_MAX_NUM_PEER_IDS];
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 7675858f069b..9c4bf2fdbc0f 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4732,13 +4732,14 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
{
struct ath10k *ar = hw->priv;
int ret;
- u8 ac;
+ u8 ac = txq->ac;
ath10k_htt_tx_txq_update(hw, txq);
if (ar->htt.tx_q_state.mode != HTT_TX_MODE_SWITCH_PUSH)
return;
- ac = txq->ac;
+ spin_lock_bh(&ar->queue_lock[ac]);
+
ieee80211_txq_schedule_start(hw, ac);
txq = ieee80211_next_txq(hw, ac);
if (!txq)
@@ -4753,6 +4754,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
ath10k_htt_tx_txq_update(hw, txq);
out:
ieee80211_txq_schedule_end(hw, ac);
+ spin_unlock_bh(&ar->queue_lock[ac]);
}
/* Must not be called with conf_mutex held as workers can use that also. */
--
2.40.0
Remove the acpi_backlight=video quirk for Lenovo ThinkPad W530.
This was intended to help users of the (unsupported) Nvidia binary driver,
but this has been reported to cause backlight control issues for users
who have the gfx configured in hybrid (dual-GPU) mode, so drop this.
The Nvidia binary driver should call acpi_video_register_backlight()
when necessary and this has been reported to Nvidia.
Until this is fixed Nvidia binary driver users can work around this by
passing "acpi_backlight=video" on the kernel commandline (with the latest
6.1.y or newer stable series, kernels < 6.1.y don't need this).
Fixes: a5b2781dcab2 ("ACPI: video: Add acpi_backlight=video quirk for Lenovo ThinkPad W530")
Reported-by: Русев Путин <rockeraliexpress(a)gmail.com>
Link: https://lore.kernel.org/linux-acpi/CAK4BXn0ngZRmzx1bodAF8nmYj0PWdUXzPGHofRr…
Cc: stable(a)vger.kernel.org
Cc: Daniel Dadap <ddadap(a)nvidia.com>
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
---
drivers/acpi/video_detect.c | 14 --------------
1 file changed, 14 deletions(-)
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 69ef2d9710c2..bcc25d457581 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -293,20 +293,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
},
},
- /*
- * Older models with nvidia GPU which need acpi_video backlight
- * control and where the old nvidia binary driver series does not
- * call acpi_video_register_backlight().
- */
- {
- .callback = video_detect_force_video,
- /* ThinkPad W530 */
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W530"),
- },
- },
-
/*
* These models have a working acpi_video backlight control, and using
* native backlight causes a regression where backlight does not work
--
2.39.2
From: Zack Rusin <zackr(a)vmware.com>
Cursor planes on virtualized drivers have special meaning and require
that the clients handle them in specific ways, e.g. the cursor plane
should react to the mouse movement the way a mouse cursor would be
expected to and the client is required to set hotspot properties on it
in order for the mouse events to be routed correctly.
This breaks the contract as specified by the "universal planes". Fix it
by disabling the cursor planes on virtualized drivers while adding
a foundation on top of which it's possible to special case mouse cursor
planes for clients that want it.
Disabling the cursor planes makes some kms compositors which were broken,
e.g. Weston, fallback to software cursor which works fine or at least
better than currently while having no effect on others, e.g. gnome-shell
or kwin, which put virtualized drivers on a deny-list when running in
atomic context to make them fallback to legacy kms and avoid this issue.
Signed-off-by: Zack Rusin <zackr(a)vmware.com>
Fixes: 681e7ec73044 ("drm: Allow userspace to ask for universal plane list (v2)")
Cc: <stable(a)vger.kernel.org> # v5.4+
Cc: Maarten Lankhorst <maarten.lankhorst(a)linux.intel.com>
Cc: Maxime Ripard <mripard(a)kernel.org>
Cc: Thomas Zimmermann <tzimmermann(a)suse.de>
Cc: David Airlie <airlied(a)linux.ie>
Cc: Daniel Vetter <daniel(a)ffwll.ch>
Cc: Dave Airlie <airlied(a)redhat.com>
Cc: Gerd Hoffmann <kraxel(a)redhat.com>
Cc: Hans de Goede <hdegoede(a)redhat.com>
Cc: Gurchetan Singh <gurchetansingh(a)chromium.org>
Cc: Chia-I Wu <olvaffe(a)gmail.com>
Cc: dri-devel(a)lists.freedesktop.org
Cc: virtualization(a)lists.linux-foundation.org
Cc: spice-devel(a)lists.freedesktop.org
---
drivers/gpu/drm/drm_plane.c | 11 +++++++++++
drivers/gpu/drm/qxl/qxl_drv.c | 2 +-
drivers/gpu/drm/vboxvideo/vbox_drv.c | 2 +-
drivers/gpu/drm/virtio/virtgpu_drv.c | 3 ++-
drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 2 +-
include/drm/drm_drv.h | 10 ++++++++++
include/drm/drm_file.h | 12 ++++++++++++
7 files changed, 38 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 726f2f163c26..e1e2a65c7119 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -667,6 +667,17 @@ int drm_mode_getplane_res(struct drm_device *dev, void *data,
!file_priv->universal_planes)
continue;
+ /*
+ * Unless userspace supports virtual cursor plane
+ * then if we're running on virtual driver do not
+ * advertise cursor planes because they'll be broken
+ */
+ if (plane->type == DRM_PLANE_TYPE_CURSOR &&
+ drm_core_check_feature(dev, DRIVER_VIRTUAL) &&
+ file_priv->atomic &&
+ !file_priv->supports_virtual_cursor_plane)
+ continue;
+
if (drm_lease_held(file_priv, plane->base.id)) {
if (count < plane_resp->count_planes &&
put_user(plane->base.id, plane_ptr + count))
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 1cb6f0c224bb..0e4212e05caa 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -281,7 +281,7 @@ static const struct drm_ioctl_desc qxl_ioctls[] = {
};
static struct drm_driver qxl_driver = {
- .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
+ .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_VIRTUAL,
.dumb_create = qxl_mode_dumb_create,
.dumb_map_offset = drm_gem_ttm_dumb_map_offset,
diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.c b/drivers/gpu/drm/vboxvideo/vbox_drv.c
index f4f2bd79a7cb..84e75bcc3384 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_drv.c
+++ b/drivers/gpu/drm/vboxvideo/vbox_drv.c
@@ -176,7 +176,7 @@ DEFINE_DRM_GEM_FOPS(vbox_fops);
static const struct drm_driver driver = {
.driver_features =
- DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC,
+ DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC | DRIVER_VIRTUAL,
.lastclose = drm_fb_helper_lastclose,
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index 5f25a8d15464..3c5bb006159a 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -198,7 +198,8 @@ MODULE_AUTHOR("Alon Levy");
DEFINE_DRM_GEM_FOPS(virtio_gpu_driver_fops);
static const struct drm_driver driver = {
- .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_RENDER | DRIVER_ATOMIC,
+ .driver_features =
+ DRIVER_MODESET | DRIVER_GEM | DRIVER_RENDER | DRIVER_ATOMIC | DRIVER_VIRTUAL,
.open = virtio_gpu_driver_open,
.postclose = virtio_gpu_driver_postclose,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 01a5b47e95f9..712f6ad0b014 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1581,7 +1581,7 @@ static const struct file_operations vmwgfx_driver_fops = {
static const struct drm_driver driver = {
.driver_features =
- DRIVER_MODESET | DRIVER_RENDER | DRIVER_ATOMIC | DRIVER_GEM,
+ DRIVER_MODESET | DRIVER_RENDER | DRIVER_ATOMIC | DRIVER_GEM | DRIVER_VIRTUAL,
.ioctls = vmw_ioctls,
.num_ioctls = ARRAY_SIZE(vmw_ioctls),
.master_set = vmw_master_set,
diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
index f6159acb8856..c4cd7fc350d9 100644
--- a/include/drm/drm_drv.h
+++ b/include/drm/drm_drv.h
@@ -94,6 +94,16 @@ enum drm_driver_feature {
* synchronization of command submission.
*/
DRIVER_SYNCOBJ_TIMELINE = BIT(6),
+ /**
+ * @DRIVER_VIRTUAL:
+ *
+ * Driver is running on top of virtual hardware. The most significant
+ * implication of this is a requirement of special handling of the
+ * cursor plane (e.g. cursor plane has to actually track the mouse
+ * cursor and the clients are required to set hotspot in order for
+ * the cursor planes to work correctly).
+ */
+ DRIVER_VIRTUAL = BIT(7),
/* IMPORTANT: Below are all the legacy flags, add new ones above. */
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index e0a73a1e2df7..3e5c36891161 100644
--- a/include/drm/drm_file.h
+++ b/include/drm/drm_file.h
@@ -223,6 +223,18 @@ struct drm_file {
*/
bool is_master;
+ /**
+ * @supports_virtual_cursor_plane:
+ *
+ * This client is capable of handling the cursor plane with the
+ * restrictions imposed on it by the virtualized drivers.
+ *
+ * The implies that the cursor plane has to behave like a cursor
+ * i.e. track cursor movement. It also requires setting of the
+ * hotspot properties by the client on the cursor plane.
+ */
+ bool supports_virtual_cursor_plane;
+
/**
* @master:
*
--
2.34.1
Hi,
This series of two patches fixes the issue introduced in
cf586021642d80 ("drm/i915/gt: Pipelined page migration") where,
as reported by Matt, in a chain of requests an error is reported
only if happens in the last request.
However Chris noticed that without ensuring exclusivity in the
locking we might end up in some deadlock. That's why patch 1
throttles for the ringspace in order to make sure that no one is
holding it.
Version 1 of this patch has been reviewed by matt and this
version is adding Chris exclusive locking.
Thanks Chris for this work.
Andi
Changelog
=========
v4 -> v5
- add timeline locking also in the copy operation, which was
forgottein in v4.
- rearrange the patches in order to avoid a bisect break.
v3 -> v4
- In v3 the timeline was being locked, but I forgot that also
request_create() and request_add() are locking the timeline
as well. The former does the locking, the latter does the
unlocking. In order to avoid this extra lock/unlock, we need
the "_locked" version of the said functions.
v2 -> v3
- Really lock the timeline before generating all the requests
until the last.
v1 -> v2
- Add patch 1 for ensuring exclusive locking of the timeline
- Reword git commit of patch 2.
Andi Shyti (4):
drm/i915/gt: Add intel_context_timeline_is_locked helper
drm/i915: Create the locked version of the request create
drm/i915: Create the locked version of the request add
drm/i915/gt: Make sure that errors are propagated through request
chains
Chris Wilson (1):
drm/i915: Throttle for ringspace prior to taking the timeline mutex
drivers/gpu/drm/i915/gt/intel_context.c | 41 ++++++++++++++++++
drivers/gpu/drm/i915/gt/intel_context.h | 8 ++++
drivers/gpu/drm/i915/gt/intel_migrate.c | 51 +++++++++++++++++------
drivers/gpu/drm/i915/i915_request.c | 55 +++++++++++++++++++------
drivers/gpu/drm/i915/i915_request.h | 3 ++
5 files changed, 133 insertions(+), 25 deletions(-)
--
2.39.2
Since commit ec6cef9cd98d ("Bluetooth: Fix SMP channel registration for
unconfigured controllers") the debugfs interface for unconfigured
controllers will be created when the controller is configured.
There is however currently nothing preventing a controller from being
configured multiple time (e.g. setting the device address using btmgmt)
which results in failed attempts to register the already registered
debugfs entries:
debugfs: File 'features' in directory 'hci0' already present!
debugfs: File 'manufacturer' in directory 'hci0' already present!
debugfs: File 'hci_version' in directory 'hci0' already present!
...
debugfs: File 'quirk_simultaneous_discovery' in directory 'hci0' already present!
Add a controller flag to avoid trying to register the debugfs interface
more than once.
Fixes: ec6cef9cd98d ("Bluetooth: Fix SMP channel registration for unconfigured controllers")
Cc: stable(a)vger.kernel.org # 4.0
Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org>
---
include/net/bluetooth/hci.h | 1 +
net/bluetooth/hci_sync.c | 3 +++
2 files changed, 4 insertions(+)
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 400f8a7d0c3f..b8bca65bcd79 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -335,6 +335,7 @@ enum {
enum {
HCI_SETUP,
HCI_CONFIG,
+ HCI_DEBUGFS_CREATED,
HCI_AUTO_OFF,
HCI_RFKILLED,
HCI_MGMT,
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 632be1267288..a8785126df75 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4501,6 +4501,9 @@ static int hci_init_sync(struct hci_dev *hdev)
!hci_dev_test_flag(hdev, HCI_CONFIG))
return 0;
+ if (hci_dev_test_and_set_flag(hdev, HCI_DEBUGFS_CREATED))
+ return 0;
+
hci_debugfs_create_common(hdev);
if (lmp_bredr_capable(hdev))
--
2.39.2
KASAN report null-ptr-deref:
==================================================================
BUG: KASAN: null-ptr-deref in bdi_split_work_to_wbs+0x5c5/0x7b0
Write of size 8 at addr 0000000000000000 by task sync/943
CPU: 5 PID: 943 Comm: sync Tainted: 6.3.0-rc5-next-20230406-dirty #461
Call Trace:
<TASK>
dump_stack_lvl+0x7f/0xc0
print_report+0x2ba/0x340
kasan_report+0xc4/0x120
kasan_check_range+0x1b7/0x2e0
__kasan_check_write+0x24/0x40
bdi_split_work_to_wbs+0x5c5/0x7b0
sync_inodes_sb+0x195/0x630
sync_inodes_one_sb+0x3a/0x50
iterate_supers+0x106/0x1b0
ksys_sync+0x98/0x160
[...]
==================================================================
The race that causes the above issue is as follows:
cpu1 cpu2
-------------------------|-------------------------
inode_switch_wbs
INIT_WORK(&isw->work, inode_switch_wbs_work_fn)
queue_rcu_work(isw_wq, &isw->work)
// queue_work async
inode_switch_wbs_work_fn
wb_put_many(old_wb, nr_switched)
percpu_ref_put_many
ref->data->release(ref)
cgwb_release
queue_work(cgwb_release_wq, &wb->release_work)
// queue_work async
&wb->release_work
cgwb_release_workfn
ksys_sync
iterate_supers
sync_inodes_one_sb
sync_inodes_sb
bdi_split_work_to_wbs
kmalloc(sizeof(*work), GFP_ATOMIC)
// alloc memory failed
percpu_ref_exit
ref->data = NULL
kfree(data)
wb_get(wb)
percpu_ref_get(&wb->refcnt)
percpu_ref_get_many(ref, 1)
atomic_long_add(nr, &ref->data->count)
atomic64_add(i, v)
// trigger null-ptr-deref
bdi_split_work_to_wbs() traverses &bdi->wb_list to split work into all wbs.
If the allocation of new work fails, the on-stack fallback will be used and
the reference count of the current wb is increased afterwards. If cgroup
writeback membership switches occur before getting the reference count and
the current wb is released as old_wd, then calling wb_get() or wb_put()
will trigger the null pointer dereference above.
This issue was introduced in v4.3-rc7 (see fix tag1). Both sync_inodes_sb()
and __writeback_inodes_sb_nr() calls to bdi_split_work_to_wbs() can trigger
this issue. For scenarios called via sync_inodes_sb(), originally commit
7fc5854f8c6e ("writeback: synchronize sync(2) against cgroup writeback
membership switches") reduced the possibility of the issue by adding
wb_switch_rwsem, but in v5.14-rc1 (see fix tag2) removed the
"inode_io_list_del_locked(inode, old_wb)" from inode_switch_wbs_work_fn()
so that wb->state contains WB_has_dirty_io, thus old_wb is not skipped
when traversing wbs in bdi_split_work_to_wbs(), and the issue becomes
easily reproducible again.
To solve this problem, percpu_ref_exit() is called under RCU protection
to avoid race between cgwb_release_workfn() and bdi_split_work_to_wbs().
Moreover, replace wb_get() with wb_tryget() in bdi_split_work_to_wbs(),
and skip the current wb if wb_tryget() fails because the wb has already
been shutdown.
Fixes: b817525a4a80 ("writeback: bdi_writeback iteration must not skip dying ones")
Fixes: f3b6a6df38aa ("writeback, cgroup: keep list of inodes attached to bdi_writeback")
Cc: stable(a)vger.kernel.org
Signed-off-by: Baokun Li <libaokun1(a)huawei.com>
---
V1->V2:
Use RCU instead of wb_switch_rwsem to avoid race.
fs/fs-writeback.c | 17 ++++++++++-------
mm/backing-dev.c | 12 ++++++++++--
2 files changed, 20 insertions(+), 9 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 195dc23e0d83..1db3e3c24b43 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -978,6 +978,16 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
continue;
}
+ /*
+ * If wb_tryget fails, the wb has been shutdown, skip it.
+ *
+ * Pin @wb so that it stays on @bdi->wb_list. This allows
+ * continuing iteration from @wb after dropping and
+ * regrabbing rcu read lock.
+ */
+ if (!wb_tryget(wb))
+ continue;
+
/* alloc failed, execute synchronously using on-stack fallback */
work = &fallback_work;
*work = *base_work;
@@ -986,13 +996,6 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
work->done = &fallback_work_done;
wb_queue_work(wb, work);
-
- /*
- * Pin @wb so that it stays on @bdi->wb_list. This allows
- * continuing iteration from @wb after dropping and
- * regrabbing rcu read lock.
- */
- wb_get(wb);
last_wb = wb;
rcu_read_unlock();
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index ad011308cebe..43b48750b491 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -507,6 +507,15 @@ static LIST_HEAD(offline_cgwbs);
static void cleanup_offline_cgwbs_workfn(struct work_struct *work);
static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn);
+static void cgwb_free_rcu(struct rcu_head *rcu_head)
+{
+ struct bdi_writeback *wb = container_of(rcu_head,
+ struct bdi_writeback, rcu);
+
+ percpu_ref_exit(&wb->refcnt);
+ kfree(wb);
+}
+
static void cgwb_release_workfn(struct work_struct *work)
{
struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
@@ -529,11 +538,10 @@ static void cgwb_release_workfn(struct work_struct *work)
list_del(&wb->offline_node);
spin_unlock_irq(&cgwb_lock);
- percpu_ref_exit(&wb->refcnt);
wb_exit(wb);
bdi_put(bdi);
WARN_ON_ONCE(!list_empty(&wb->b_attached));
- kfree_rcu(wb, rcu);
+ call_rcu(&wb->rcu, cgwb_free_rcu);
}
static void cgwb_release(struct percpu_ref *refcnt)
--
2.31.1
From: Felix Fietkau <nbd(a)nbd.name>
Through testing I found out that hardware vlan rx offload support seems to
have some hardware issues. At least when using multiple MACs and when
receiving tagged packets on the secondary MAC, the hardware can sometimes
start to emit wrong tags on the first MAC as well.
In order to avoid such issues, drop the feature configuration and use
the offload feature only for DSA hardware untagging on MT7621/MT7622
devices where this feature works properly.
Fixes: 08666cbb7dd5 ("net: ethernet: mtk_eth_soc: add support for configuring vlan rx offload")
Tested-by: Frank Wunderlich <frank-w(a)public-files.de>
Signed-off-by: Felix Fietkau <nbd(a)nbd.name>
Signed-off-by: Frank Wunderlich <frank-w(a)public-files.de>
Tested-by: Arınç ÜNAL <arinc.unal(a)arinc9.com>
---
v2:
- changed commit message to drop "only one MAC used" phrase based on
Arincs comments
- fixed too long line in commit description and add empty line after
declaration
- add fixes tag
used felix Patch as base and ported up to 6.3-rc6
it basicly reverts changes from vladimirs patch
1a3245fe0cf8 net: ethernet: mtk_eth_soc: fix DSA TX tag hwaccel for switch port 0
tested this on bananapi-r3 on non-dsa gmac1 and dsa eth0 (wan).
on both vlan is working, but maybe it breaks HW-vlan-untagging
---
drivers/net/ethernet/mediatek/mtk_eth_soc.c | 106 ++++++++------------
drivers/net/ethernet/mediatek/mtk_eth_soc.h | 1 -
2 files changed, 40 insertions(+), 67 deletions(-)
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 9e948d091a69..a75fd072082c 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1918,9 +1918,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
while (done < budget) {
unsigned int pktlen, *rxdcsum;
- bool has_hwaccel_tag = false;
struct net_device *netdev;
- u16 vlan_proto, vlan_tci;
dma_addr_t dma_addr;
u32 hash, reason;
int mac = 0;
@@ -2055,31 +2053,16 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
skb_checksum_none_assert(skb);
skb->protocol = eth_type_trans(skb, netdev);
- if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) {
- if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
- if (trxd.rxd3 & RX_DMA_VTAG_V2) {
- vlan_proto = RX_DMA_VPID(trxd.rxd4);
- vlan_tci = RX_DMA_VID(trxd.rxd4);
- has_hwaccel_tag = true;
- }
- } else if (trxd.rxd2 & RX_DMA_VTAG) {
- vlan_proto = RX_DMA_VPID(trxd.rxd3);
- vlan_tci = RX_DMA_VID(trxd.rxd3);
- has_hwaccel_tag = true;
- }
- }
-
/* When using VLAN untagging in combination with DSA, the
* hardware treats the MTK special tag as a VLAN and untags it.
*/
- if (has_hwaccel_tag && netdev_uses_dsa(netdev)) {
- unsigned int port = vlan_proto & GENMASK(2, 0);
+ if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2) &&
+ (trxd.rxd2 & RX_DMA_VTAG) && netdev_uses_dsa(netdev)) {
+ unsigned int port = RX_DMA_VPID(trxd.rxd3) & GENMASK(2, 0);
if (port < ARRAY_SIZE(eth->dsa_meta) &&
eth->dsa_meta[port])
skb_dst_set_noref(skb, ð->dsa_meta[port]->dst);
- } else if (has_hwaccel_tag) {
- __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan_tci);
}
if (reason == MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
@@ -2907,29 +2890,11 @@ static netdev_features_t mtk_fix_features(struct net_device *dev,
static int mtk_set_features(struct net_device *dev, netdev_features_t features)
{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
netdev_features_t diff = dev->features ^ features;
- int i;
if ((diff & NETIF_F_LRO) && !(features & NETIF_F_LRO))
mtk_hwlro_netdev_disable(dev);
- /* Set RX VLAN offloading */
- if (!(diff & NETIF_F_HW_VLAN_CTAG_RX))
- return 0;
-
- mtk_w32(eth, !!(features & NETIF_F_HW_VLAN_CTAG_RX),
- MTK_CDMP_EG_CTRL);
-
- /* sync features with other MAC */
- for (i = 0; i < MTK_MAC_COUNT; i++) {
- if (!eth->netdev[i] || eth->netdev[i] == dev)
- continue;
- eth->netdev[i]->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
- eth->netdev[i]->features |= features & NETIF_F_HW_VLAN_CTAG_RX;
- }
-
return 0;
}
@@ -3247,30 +3212,6 @@ static int mtk_open(struct net_device *dev)
struct mtk_eth *eth = mac->hw;
int i, err;
- if (mtk_uses_dsa(dev) && !eth->prog) {
- for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) {
- struct metadata_dst *md_dst = eth->dsa_meta[i];
-
- if (md_dst)
- continue;
-
- md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
- GFP_KERNEL);
- if (!md_dst)
- return -ENOMEM;
-
- md_dst->u.port_info.port_id = i;
- eth->dsa_meta[i] = md_dst;
- }
- } else {
- /* Hardware special tag parsing needs to be disabled if at least
- * one MAC does not use DSA.
- */
- u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL);
- val &= ~MTK_CDMP_STAG_EN;
- mtk_w32(eth, val, MTK_CDMP_IG_CTRL);
- }
-
err = phylink_of_phy_connect(mac->phylink, mac->of_node, 0);
if (err) {
netdev_err(dev, "%s: could not attach PHY: %d\n", __func__,
@@ -3309,6 +3250,40 @@ static int mtk_open(struct net_device *dev)
phylink_start(mac->phylink);
netif_tx_start_all_queues(dev);
+ if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+ return 0;
+
+ if (mtk_uses_dsa(dev) && !eth->prog) {
+ for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) {
+ struct metadata_dst *md_dst = eth->dsa_meta[i];
+
+ if (md_dst)
+ continue;
+
+ md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+ GFP_KERNEL);
+ if (!md_dst)
+ return -ENOMEM;
+
+ md_dst->u.port_info.port_id = i;
+ eth->dsa_meta[i] = md_dst;
+ }
+ } else {
+ /* Hardware special tag parsing needs to be disabled if at least
+ * one MAC does not use DSA.
+ */
+ u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL);
+
+ val &= ~MTK_CDMP_STAG_EN;
+ mtk_w32(eth, val, MTK_CDMP_IG_CTRL);
+
+ val = mtk_r32(eth, MTK_CDMQ_IG_CTRL);
+ val &= ~MTK_CDMQ_STAG_EN;
+ mtk_w32(eth, val, MTK_CDMQ_IG_CTRL);
+
+ mtk_w32(eth, 0, MTK_CDMP_EG_CTRL);
+ }
+
return 0;
}
@@ -3793,10 +3768,9 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
val = mtk_r32(eth, MTK_CDMP_IG_CTRL);
mtk_w32(eth, val | MTK_CDMP_STAG_EN, MTK_CDMP_IG_CTRL);
- }
- /* Enable RX VLan Offloading */
- mtk_w32(eth, 1, MTK_CDMP_EG_CTRL);
+ mtk_w32(eth, 1, MTK_CDMP_EG_CTRL);
+ }
/* set interrupt delays based on current Net DIM sample */
mtk_dim_rx(ð->rx_dim.work);
@@ -4453,7 +4427,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
eth->netdev[id]->hw_features |= NETIF_F_LRO;
eth->netdev[id]->vlan_features = eth->soc->hw_features &
- ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
+ ~NETIF_F_HW_VLAN_CTAG_TX;
eth->netdev[id]->features |= eth->soc->hw_features;
eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index cdcf8534283e..707445f6bcb1 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -48,7 +48,6 @@
#define MTK_HW_FEATURES (NETIF_F_IP_CSUM | \
NETIF_F_RXCSUM | \
NETIF_F_HW_VLAN_CTAG_TX | \
- NETIF_F_HW_VLAN_CTAG_RX | \
NETIF_F_SG | NETIF_F_TSO | \
NETIF_F_TSO6 | \
NETIF_F_IPV6_CSUM |\
--
2.34.1