Some usb hubs will negotiate DisplayPort Alt mode with the device
but will then negotiate a data role swap after entering the alt
mode. The data role swap causes the device to unregister all alt
modes, however the usb hub will still send Attention messages
even after failing to reregister the Alt Mode. type_altmode_attention
currently does not verify whether or not a device's altmode partner
exists, which results in a NULL pointer error when dereferencing
the typec_altmode and typec_altmode_ops belonging to the altmode
partner.
Verify the presence of a device's altmode partner before sending
the Attention message to the Alt Mode driver.
Fixes: 8a37d87d72f0 ("usb: typec: Bus type for alternate modes")
Cc: stable(a)vger.kernel.org
Signed-off-by: RD Babiera <rdbabiera(a)google.com>
---
Changes since v1:
* Only assigns pdev if altmode partner exists in typec_altmode_attention
* Removed error return in typec_altmode_attention if Alt Mode does
not implement Attention messages.
* Changed tcpm_log message to indicate that altmode partner does not exist,
as it only logs in that case.
---
Changes since v2:
* Changed tcpm_log message to accurately reflect error
* Revised commit message
---
drivers/usb/typec/bus.c | 12 ++++++++++--
drivers/usb/typec/tcpm/tcpm.c | 5 ++++-
include/linux/usb/typec_altmode.h | 2 +-
3 files changed, 15 insertions(+), 4 deletions(-)
diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c
index fe5b9a2e61f5..e95ec7e382bb 100644
--- a/drivers/usb/typec/bus.c
+++ b/drivers/usb/typec/bus.c
@@ -183,12 +183,20 @@ EXPORT_SYMBOL_GPL(typec_altmode_exit);
*
* Notifies the partner of @adev about Attention command.
*/
-void typec_altmode_attention(struct typec_altmode *adev, u32 vdo)
+int typec_altmode_attention(struct typec_altmode *adev, u32 vdo)
{
- struct typec_altmode *pdev = &to_altmode(adev)->partner->adev;
+ struct altmode *partner = to_altmode(adev)->partner;
+ struct typec_altmode *pdev;
+
+ if (!partner)
+ return -ENODEV;
+
+ pdev = &partner->adev;
if (pdev->ops && pdev->ops->attention)
pdev->ops->attention(pdev, vdo);
+
+ return 0;
}
EXPORT_SYMBOL_GPL(typec_altmode_attention);
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 5a7d8cc04628..97b7b22e9cf1 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -1791,6 +1791,7 @@ static void tcpm_handle_vdm_request(struct tcpm_port *port,
u32 p[PD_MAX_PAYLOAD];
u32 response[8] = { };
int i, rlen = 0;
+ int ret;
for (i = 0; i < cnt; i++)
p[i] = le32_to_cpu(payload[i]);
@@ -1877,7 +1878,9 @@ static void tcpm_handle_vdm_request(struct tcpm_port *port,
}
break;
case ADEV_ATTENTION:
- typec_altmode_attention(adev, p[1]);
+ ret = typec_altmode_attention(adev, p[1]);
+ if (ret)
+ tcpm_log(port, "typec_altmode_attention NULL port partner altmode");
break;
}
}
diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h
index 350d49012659..28aeef8f9e7b 100644
--- a/include/linux/usb/typec_altmode.h
+++ b/include/linux/usb/typec_altmode.h
@@ -67,7 +67,7 @@ struct typec_altmode_ops {
int typec_altmode_enter(struct typec_altmode *altmode, u32 *vdo);
int typec_altmode_exit(struct typec_altmode *altmode);
-void typec_altmode_attention(struct typec_altmode *altmode, u32 vdo);
+int typec_altmode_attention(struct typec_altmode *altmode, u32 vdo);
int typec_altmode_vdm(struct typec_altmode *altmode,
const u32 header, const u32 *vdo, int count);
int typec_altmode_notify(struct typec_altmode *altmode, unsigned long conf,
base-commit: f176638af476c6d46257cc3303f5c7cf47d5967d
--
2.41.0.640.ga95def55d0-goog
When a memcg is in the process of being released mem_cgroup_tryget will
fail because its reference count has already reached 0. This can happen
during reclaim if the memcg has already been offlined, and we reclaim
all remaining pages attributed to the offlined memcg. shrink_many
attempts to skip the empty memcg in this case, and continue reclaiming
from the remaining memcgs in the old generation. If there is only one
memcg remaining, or if all remaining memcgs are in the process of being
released then shrink_many will spin until all memcgs have finished
being released. The release occurs through a workqueue, so it can take
a while before kswapd is able to make any further progress.
This fix results in reductions in kswapd activity and direct reclaim in
a test where 28 apps (working set size > total memory) are repeatedly
launched in a random sequence:
A B delta ratio(%)
allocstall_movable 5962 3539 -2423 -40.64
allocstall_normal 2661 2417 -244 -9.17
kswapd_high_wmark_hit_quickly 53152 7594 -45558 -85.71
pageoutrun 57365 11750 -45615 -79.52
Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
Cc: stable(a)vger.kernel.org
Signed-off-by: T.J. Mercier <tjmercier(a)google.com>
---
mm/vmscan.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 157ed68470ee..c7c149cb8d66 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4856,16 +4856,17 @@ void lru_gen_release_memcg(struct mem_cgroup *memcg)
spin_lock_irq(&pgdat->memcg_lru.lock);
- VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list));
+ if (hlist_nulls_unhashed(&lruvec->lrugen.list))
+ goto unlock;
gen = lruvec->lrugen.gen;
- hlist_nulls_del_rcu(&lruvec->lrugen.list);
+ hlist_nulls_del_init_rcu(&lruvec->lrugen.list);
pgdat->memcg_lru.nr_memcgs[gen]--;
if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq))
WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
-
+unlock:
spin_unlock_irq(&pgdat->memcg_lru.lock);
}
}
@@ -5447,8 +5448,10 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
rcu_read_lock();
hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) {
- if (op)
+ if (op) {
lru_gen_rotate_memcg(lruvec, op);
+ op = 0;
+ }
mem_cgroup_put(memcg);
@@ -5456,7 +5459,7 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
memcg = lruvec_memcg(lruvec);
if (!mem_cgroup_tryget(memcg)) {
- op = 0;
+ lru_gen_release_memcg(memcg);
memcg = NULL;
continue;
}
--
2.41.0.640.ga95def55d0-goog
Hi,
Would you be interested in acquiring AWS reinvent/ Amazon Web Services
Attendees Email List- 2023?
List contains: Company Name, Contact Name, Title, Address, Street,
City, Zip code, State, Country, Telephone, Email address and more,
Number of Attendees: 45,369
Attendees List Cost: $2,099
Interested? Email me back; I would love to provide more information on the list.
Kind Regards,
Yenny Miller
Marketing Coordinator
On Mon, Aug 14, 2023 at 05:35:19PM +0300, Александр Офицеров wrote:
>
>
>
> -------- Перенаправленное сообщение --------
> Тема: [PATCH 2/3] mfd: intel-lpss: Add Alder Lake's PCI devices IDs
> Дата: Thu, 10 Aug 2023 14:59:37 +0300
> От: Alexander Ofitserov <oficerovas(a)altlinux.org>
> Кому: oficerovas(a)altlinux.org, Lee Jones <lee.jones(a)linaro.org>
> Копия: linux-kernel(a)vger.kernel.org
>
>
>
> Intel Alder Lake PCH has the same LPSS as Intel Broxton.
> Add the new IDs to the list of supported devices.
>
> Signed-off-by: Alexander Ofitserov <oficerovas(a)altlinux.org>
<formletter>
This is not the correct way to submit patches for inclusion in the
stable kernel tree. Please read:
https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html
for how to do this properly.
</formletter>
On Mon, Aug 14, 2023 at 05:34:27PM +0300, Александр Офицеров wrote:
> I'm sorry, this is my first time I ever send patches, I messed up with git
> send-email, so you received cover letter with no patches.
>
> Now I'm sending you patches, that i wanted to send.
<formletter>
This is not the correct way to submit patches for inclusion in the
stable kernel tree. Please read:
https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html
for how to do this properly.
</formletter>
check_clock doesn't account for vfe_lite which means that vfe_lite will
never get validated by this routine. Add the clock name to the expected set
to remediate.
Fixes: 7319cdf189bb ("media: camss: Add support for VFE hardware version Titan 170")
Cc: stable(a)vger.kernel.org
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org>
---
drivers/media/platform/qcom/camss/camss-vfe.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 938f373bcd1fd..b021f81cef123 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -535,7 +535,8 @@ static int vfe_check_clock_rates(struct vfe_device *vfe)
struct camss_clock *clock = &vfe->clock[i];
if (!strcmp(clock->name, "vfe0") ||
- !strcmp(clock->name, "vfe1")) {
+ !strcmp(clock->name, "vfe1") ||
+ !strcmp(clock->name, "vfe_lite")) {
u64 min_rate = 0;
unsigned long rate;
--
2.41.0
There are two problems with the current vfe_disable_output() routine.
Firstly we rightly use a spinlock to protect output->gen2.active_num
everywhere except for in the IDLE timeout path of vfe_disable_output().
Even if that is not racy "in practice" somehow it is by happenstance not
by design.
Secondly we do not get consistent behaviour from this routine. On
sc8280xp 50% of the time I get "VFE idle timeout - resetting". In this
case the subsequent capture will succeed. The other 50% of the time, we
don't hit the idle timeout, never do the VFE reset and subsequent
captures stall indefinitely.
Rewrite the vfe_disable_output() routine to
- Quiesce write masters with vfe_wm_stop()
- Set active_num = 0
remembering to hold the spinlock when we do so followed by
- Reset the VFE
Testing on sc8280xp and sdm845 shows this to be a valid fix.
Fixes: 7319cdf189bb ("media: camss: Add support for VFE hardware version Titan 170")
Cc: stable(a)vger.kernel.org
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org>
---
.../media/platform/qcom/camss/camss-vfe-170.c | 19 +++----------------
1 file changed, 3 insertions(+), 16 deletions(-)
diff --git a/drivers/media/platform/qcom/camss/camss-vfe-170.c b/drivers/media/platform/qcom/camss/camss-vfe-170.c
index 02494c89da91c..ae9137633c301 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe-170.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe-170.c
@@ -500,28 +500,15 @@ static int vfe_disable_output(struct vfe_line *line)
struct vfe_output *output = &line->output;
unsigned long flags;
unsigned int i;
- bool done;
- int timeout = 0;
-
- do {
- spin_lock_irqsave(&vfe->output_lock, flags);
- done = !output->gen2.active_num;
- spin_unlock_irqrestore(&vfe->output_lock, flags);
- usleep_range(10000, 20000);
-
- if (timeout++ == 100) {
- dev_err(vfe->camss->dev, "VFE idle timeout - resetting\n");
- vfe_reset(vfe);
- output->gen2.active_num = 0;
- return 0;
- }
- } while (!done);
spin_lock_irqsave(&vfe->output_lock, flags);
for (i = 0; i < output->wm_num; i++)
vfe_wm_stop(vfe, output->wm_idx[i]);
+ output->gen2.active_num = 0;
spin_unlock_irqrestore(&vfe->output_lock, flags);
+ vfe_reset(vfe);
+
return 0;
}
--
2.41.0
We need to make sure camss_configure_pd() happens before
camss_register_entities() as the vfe_get() path relies on the pointer
provided by camss_configure_pd().
Fix the ordering sequence in probe to ensure the pointers vfe_get() demands
are present by the time camss_register_entities() runs.
In order to facilitate backporting to stable kernels I've moved the
configure_pd() call pretty early on the probe() function so that
irrespective of the existence of the old error handling jump labels this
patch should still apply to -next circa Aug 2023 to v5.13 inclusive.
Fixes: 2f6f8af67203 ("media: camss: Refactor VFE power domain toggling")
Cc: stable(a)vger.kernel.org
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org>
---
drivers/media/platform/qcom/camss/camss.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
index f11dc59135a5a..75991d849b571 100644
--- a/drivers/media/platform/qcom/camss/camss.c
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -1619,6 +1619,12 @@ static int camss_probe(struct platform_device *pdev)
if (ret < 0)
goto err_cleanup;
+ ret = camss_configure_pd(camss);
+ if (ret < 0) {
+ dev_err(dev, "Failed to configure power domains: %d\n", ret);
+ goto err_cleanup;
+ }
+
ret = camss_init_subdevices(camss);
if (ret < 0)
goto err_cleanup;
@@ -1678,12 +1684,6 @@ static int camss_probe(struct platform_device *pdev)
}
}
- ret = camss_configure_pd(camss);
- if (ret < 0) {
- dev_err(dev, "Failed to configure power domains: %d\n", ret);
- return ret;
- }
-
pm_runtime_enable(dev);
return 0;
--
2.41.0
In the I2C_FUNC_SMBUS_BLOCK_DATA case, the invalid length byte value
(outside of 1-32) of the SMBus block data response from the Slave device
is not correctly handled by the I2C Designware driver.
In case IC_EMPTYFIFO_HOLD_MASTER_EN==1, which cannot be detected
from the registers, the Master can be disabled only if the STOP bit
is set. Without STOP bit set, the Master remains active, holding the bus
until receiving a block data response length. This hangs the bus and
is unrecoverable.
Avoid this by issuing another dump read to reach the stop condition when
an invalid length byte is received.
Cc: stable(a)vger.kernel.org
Signed-off-by: Tam Nguyen <tamnguyenchi(a)os.amperecomputing.com>
---
drivers/i2c/busses/i2c-designware-master.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index e96276d1b002..c51fc1f4b97e 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -528,8 +528,19 @@ i2c_dw_read(struct dw_i2c_dev *dev)
regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
tmp &= DW_IC_DATA_CMD_DAT;
/* Ensure length byte is a valid value */
- if (flags & I2C_M_RECV_LEN &&
- tmp <= I2C_SMBUS_BLOCK_MAX && tmp > 0) {
+ if (flags & I2C_M_RECV_LEN) {
+ /*
+ * if IC_EMPTYFIFO_HOLD_MASTER_EN is set, which cannot be
+ * detected from the registers, the controller can be
+ * disabled if the STOP bit is set. But it is only set
+ * after receiving block data response length in
+ * I2C_FUNC_SMBUS_BLOCK_DATA case. That needs to read
+ * another byte with STOP bit set when the block data
+ * response length is invalid to complete the transaction.
+ */
+ if (!tmp || tmp > I2C_SMBUS_BLOCK_MAX)
+ tmp = 1;
+
len = i2c_dw_recv_len(dev, tmp);
}
*buf++ = tmp;
--
2.25.1
From: Quan Nguyen <quan(a)os.amperecomputing.com>
Commit 0daede80f870 ("i2c: designware: Convert driver to using regmap API")
changes the logic to validate the whole 32-bit return value of
DW_IC_DATA_CMD register instead of 8-bit LSB without reason.
Later, commit f53f15ba5a85 ("i2c: designware: Get right data length"),
introduced partial fix but not enough because the "tmp > 0" still test
tmp as 32-bit value and is wrong in case the IC_DATA_CMD[11] is set.
Revert the logic to just before commit 0daede80f870
("i2c: designware: Convert driver to using regmap API").
Fixes: f53f15ba5a85 ("i2c: designware: Get right data length")
Fixes: 0daede80f870 ("i2c: designware: Convert driver to using regmap API")
Cc: stable(a)vger.kernel.org
Signed-off-by: Tam Nguyen <tamnguyenchi(a)os.amperecomputing.com>
Signed-off-by: Quan Nguyen <quan(a)os.amperecomputing.com>
---
drivers/i2c/busses/i2c-designware-master.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index 55ea91a63382..e96276d1b002 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -526,9 +526,10 @@ i2c_dw_read(struct dw_i2c_dev *dev)
u32 flags = msgs[dev->msg_read_idx].flags;
regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
+ tmp &= DW_IC_DATA_CMD_DAT;
/* Ensure length byte is a valid value */
if (flags & I2C_M_RECV_LEN &&
- (tmp & DW_IC_DATA_CMD_DAT) <= I2C_SMBUS_BLOCK_MAX && tmp > 0) {
+ tmp <= I2C_SMBUS_BLOCK_MAX && tmp > 0) {
len = i2c_dw_recv_len(dev, tmp);
}
*buf++ = tmp;
--
2.25.1
From: Adrien Thierry <athierry(a)redhat.com>
[ Upstream commit 45d89a344eb46db9dce851c28e14f5e3c635c251 ]
In the dwc3 core, both system and runtime suspend end up calling
dwc3_suspend_common(). From there, what happens for the PHYs depends on
the USB mode and whether the controller is entering system or runtime
suspend.
HOST mode:
(1) system suspend on a non-wakeup-capable controller
The [1] if branch is taken. dwc3_core_exit() is called, which ends up
calling phy_power_off() and phy_exit(). Those two functions decrease the
PM runtime count at some point, so they will trigger the PHY runtime
sleep (assuming the count is right).
(2) runtime suspend / system suspend on a wakeup-capable controller
The [1] branch is not taken. dwc3_suspend_common() calls
phy_pm_runtime_put_sync(). Assuming the ref count is right, the PHY
runtime suspend op is called.
DEVICE mode:
dwc3_core_exit() is called on both runtime and system sleep
unless the controller is already runtime suspended.
OTG mode:
(1) system suspend : dwc3_core_exit() is called
(2) runtime suspend : do nothing
In host mode, the code seems to make a distinction between 1) runtime
sleep / system sleep for wakeup-capable controller, and 2) system sleep
for non-wakeup-capable controller, where phy_power_off() and phy_exit()
are only called for the latter. This suggests the PHY is not supposed to
be in a fully powered-off state for runtime sleep and system sleep for
wakeup-capable controller.
Moreover, downstream, cfg_ahb_clk only gets disabled for system suspend.
The clocks are disabled by phy->set_suspend() [2] which is only called
in the system sleep path through dwc3_core_exit() [3].
With that in mind, don't disable the clocks during the femto PHY runtime
suspend callback. The clocks will only be disabled during system suspend
for non-wakeup-capable controllers, through dwc3_core_exit().
[1] https://elixir.bootlin.com/linux/v6.4/source/drivers/usb/dwc3/core.c#L1988
[2] https://git.codelinaro.org/clo/la/kernel/msm-5.4/-/blob/LV.AU.1.2.1.r2-0530…
[3] https://git.codelinaro.org/clo/la/kernel/msm-5.4/-/blob/LV.AU.1.2.1.r2-0530…
Signed-off-by: Adrien Thierry <athierry(a)redhat.com>
Link: https://lore.kernel.org/r/20230629144542.14906-2-athierry@redhat.com
Signed-off-by: Vinod Koul <vkoul(a)kernel.org>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c | 9 ---------
1 file changed, 9 deletions(-)
diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
index 7e61202aa234e..a107f98c662d5 100644
--- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
+++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
@@ -122,22 +122,13 @@ static int qcom_snps_hsphy_suspend(struct qcom_snps_hsphy *hsphy)
0, USB2_AUTO_RESUME);
}
- clk_disable_unprepare(hsphy->cfg_ahb_clk);
return 0;
}
static int qcom_snps_hsphy_resume(struct qcom_snps_hsphy *hsphy)
{
- int ret;
-
dev_dbg(&hsphy->phy->dev, "Resume QCOM SNPS PHY, mode\n");
- ret = clk_prepare_enable(hsphy->cfg_ahb_clk);
- if (ret) {
- dev_err(&hsphy->phy->dev, "failed to enable cfg ahb clock\n");
- return ret;
- }
-
return 0;
}
--
2.40.1
From: Adrien Thierry <athierry(a)redhat.com>
[ Upstream commit 45d89a344eb46db9dce851c28e14f5e3c635c251 ]
In the dwc3 core, both system and runtime suspend end up calling
dwc3_suspend_common(). From there, what happens for the PHYs depends on
the USB mode and whether the controller is entering system or runtime
suspend.
HOST mode:
(1) system suspend on a non-wakeup-capable controller
The [1] if branch is taken. dwc3_core_exit() is called, which ends up
calling phy_power_off() and phy_exit(). Those two functions decrease the
PM runtime count at some point, so they will trigger the PHY runtime
sleep (assuming the count is right).
(2) runtime suspend / system suspend on a wakeup-capable controller
The [1] branch is not taken. dwc3_suspend_common() calls
phy_pm_runtime_put_sync(). Assuming the ref count is right, the PHY
runtime suspend op is called.
DEVICE mode:
dwc3_core_exit() is called on both runtime and system sleep
unless the controller is already runtime suspended.
OTG mode:
(1) system suspend : dwc3_core_exit() is called
(2) runtime suspend : do nothing
In host mode, the code seems to make a distinction between 1) runtime
sleep / system sleep for wakeup-capable controller, and 2) system sleep
for non-wakeup-capable controller, where phy_power_off() and phy_exit()
are only called for the latter. This suggests the PHY is not supposed to
be in a fully powered-off state for runtime sleep and system sleep for
wakeup-capable controller.
Moreover, downstream, cfg_ahb_clk only gets disabled for system suspend.
The clocks are disabled by phy->set_suspend() [2] which is only called
in the system sleep path through dwc3_core_exit() [3].
With that in mind, don't disable the clocks during the femto PHY runtime
suspend callback. The clocks will only be disabled during system suspend
for non-wakeup-capable controllers, through dwc3_core_exit().
[1] https://elixir.bootlin.com/linux/v6.4/source/drivers/usb/dwc3/core.c#L1988
[2] https://git.codelinaro.org/clo/la/kernel/msm-5.4/-/blob/LV.AU.1.2.1.r2-0530…
[3] https://git.codelinaro.org/clo/la/kernel/msm-5.4/-/blob/LV.AU.1.2.1.r2-0530…
Signed-off-by: Adrien Thierry <athierry(a)redhat.com>
Link: https://lore.kernel.org/r/20230629144542.14906-2-athierry@redhat.com
Signed-off-by: Vinod Koul <vkoul(a)kernel.org>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c | 9 ---------
1 file changed, 9 deletions(-)
diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
index 7e61202aa234e..a107f98c662d5 100644
--- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
+++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
@@ -122,22 +122,13 @@ static int qcom_snps_hsphy_suspend(struct qcom_snps_hsphy *hsphy)
0, USB2_AUTO_RESUME);
}
- clk_disable_unprepare(hsphy->cfg_ahb_clk);
return 0;
}
static int qcom_snps_hsphy_resume(struct qcom_snps_hsphy *hsphy)
{
- int ret;
-
dev_dbg(&hsphy->phy->dev, "Resume QCOM SNPS PHY, mode\n");
- ret = clk_prepare_enable(hsphy->cfg_ahb_clk);
- if (ret) {
- dev_err(&hsphy->phy->dev, "failed to enable cfg ahb clock\n");
- return ret;
- }
-
return 0;
}
--
2.40.1
This is the start of the stable review cycle for the 5.4.253 release.
There are 154 patches in this series, all will be posted as a response
to this one. If anyone has any issues with these being applied, please
let me know.
Responses should be made by Fri, 11 Aug 2023 10:36:10 +0000.
Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.4.253-rc…
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.4.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Linux 5.4.253-rc1
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Revert "driver core: Annotate dev_err_probe() with __must_check"
Mauro Carvalho Chehab <mchehab+huawei(a)kernel.org>
drivers: core: fix kernel-doc markup for dev_err_probe()
Michał Mirosław <mirq-linux(a)rere.qmqm.pl>
driver code: print symbolic error code
Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
driver core: Annotate dev_err_probe() with __must_check
Xu Yang <xu.yang_2(a)nxp.com>
ARM: dts: nxp/imx6sll: fix wrong property name in usbphy node
Andreas Kemnade <andreas(a)kemnade.info>
ARM: dts: imx6sll: fixup of operating points
Peng Fan <peng.fan(a)nxp.com>
ARM: dts: imx: add usb alias
Krzysztof Kozlowski <krzk(a)kernel.org>
ARM: dts: imx: Align L2 cache-controller nodename with dtschema
Shengjiu Wang <shengjiu.wang(a)nxp.com>
ARM: dts: imx6sll: Make ssi node name same as other platforms
Dinh Nguyen <dinguyen(a)kernel.org>
arm64: dts: stratix10: fix incorrect I2C property for SCL signal
Xiubo Li <xiubli(a)redhat.com>
ceph: defer stopping mdsc delayed_work
Jeff Layton <jlayton(a)kernel.org>
ceph: use kill_anon_super helper
Jeff Layton <jlayton(a)kernel.org>
ceph: show tasks waiting on caps in debugfs caps file
Johan Hovold <johan+linaro(a)kernel.org>
PM: sleep: wakeirq: fix wake irq arming
Chunfeng Yun <chunfeng.yun(a)mediatek.com>
PM / wakeirq: support enabling wake-up irq after runtime_suspend called
Sean Christopherson <seanjc(a)google.com>
selftests/rseq: Play nice with binaries statically linked against glibc 2.35+
Michael Jeanson <mjeanson(a)efficios.com>
selftests/rseq: check if libc rseq support is registered
Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com>
powerpc/mm/altmap: Fix altmap boundary check
Roger Quadros <rogerq(a)kernel.org>
mtd: rawnand: omap_elm: Fix incorrect type in assignment
Mirsad Goran Todorovac <mirsad.todorovac(a)alu.unizg.hr>
test_firmware: return ENOMEM instead of ENOSPC on failed memory allocation
Mirsad Goran Todorovac <mirsad.todorovac(a)alu.unizg.hr>
test_firmware: prevent race conditions by a correct implementation of locking
Jan Kara <jack(a)suse.cz>
ext2: Drop fragment support
Jan Kara <jack(a)suse.cz>
fs: Protect reconfiguration of sb read-write from racing writes
Alan Stern <stern(a)rowland.harvard.edu>
net: usbnet: Fix WARNING in usbnet_start_xmit/usb_submit_urb
Sungwoo Kim <iam(a)sung-woo.kim>
Bluetooth: L2CAP: Fix use-after-free in l2cap_sock_ready_cb
Prince Kumar Maurya <princekumarmaurya06(a)gmail.com>
fs/sysv: Null check to prevent null-ptr-deref bug
Laszlo Ersek <lersek(a)redhat.com>
net: tap_open(): set sk_uid from current_fsuid()
Laszlo Ersek <lersek(a)redhat.com>
net: tun_chr_open(): set sk_uid from current_fsuid()
Arseniy Krasnov <AVKrasnov(a)sberdevices.ru>
mtd: rawnand: meson: fix OOB available bytes for ECC
Olivier Maignial <olivier.maignial(a)hotmail.fr>
mtd: spinand: toshiba: Fix ecc_get_status
Ross Maynard <bids.7405(a)bigpond.com>
USB: zaurus: Add ID for A-300/B-500/C-700
Ilya Dryomov <idryomov(a)gmail.com>
libceph: fix potential hang in ceph_osdc_notify()
Steffen Maier <maier(a)linux.ibm.com>
scsi: zfcp: Defer fc_rport blocking until after ADISC response
Eric Dumazet <edumazet(a)google.com>
tcp_metrics: fix data-race in tcpm_suck_dst() vs fastopen
Eric Dumazet <edumazet(a)google.com>
tcp_metrics: annotate data-races around tm->tcpm_net
Eric Dumazet <edumazet(a)google.com>
tcp_metrics: annotate data-races around tm->tcpm_vals[]
Eric Dumazet <edumazet(a)google.com>
tcp_metrics: annotate data-races around tm->tcpm_lock
Eric Dumazet <edumazet(a)google.com>
tcp_metrics: annotate data-races around tm->tcpm_stamp
Eric Dumazet <edumazet(a)google.com>
tcp_metrics: fix addr_same() helper
Yue Haibing <yuehaibing(a)huawei.com>
ip6mr: Fix skb_under_panic in ip6mr_cache_report()
Lin Ma <linma(a)zju.edu.cn>
net: dcb: choose correct policy to parse DCB_ATTR_BCN
Dan Carpenter <dan.carpenter(a)linaro.org>
net: ll_temac: fix error checking of irq_of_parse_and_map()
Yang Yingliang <yangyingliang(a)huawei.com>
net: ll_temac: Switch to use dev_err_probe() helper
Andrzej Hajda <a.hajda(a)samsung.com>
driver core: add device probe log helper
Tomas Glozar <tglozar(a)redhat.com>
bpf: sockmap: Remove preempt_disable in sock_map_sk_acquire
valis <sec(a)valis.email>
net/sched: cls_route: No longer copy tcf_result on update to avoid use-after-free
valis <sec(a)valis.email>
net/sched: cls_fw: No longer copy tcf_result on update to avoid use-after-free
valis <sec(a)valis.email>
net/sched: cls_u32: No longer copy tcf_result on update to avoid use-after-free
Eric Dumazet <edumazet(a)google.com>
net: add missing data-race annotation for sk_ll_usec
Eric Dumazet <edumazet(a)google.com>
net: add missing data-race annotations around sk->sk_peek_off
Eric Dumazet <edumazet(a)google.com>
net: add missing READ_ONCE(sk->sk_rcvbuf) annotation
Eric Dumazet <edumazet(a)google.com>
net: add missing READ_ONCE(sk->sk_sndbuf) annotation
Eric Dumazet <edumazet(a)google.com>
net: add missing READ_ONCE(sk->sk_rcvlowat) annotation
Eric Dumazet <edumazet(a)google.com>
net: annotate data-races around sk->sk_max_pacing_rate
Chengfeng Ye <dg573847474(a)gmail.com>
mISDN: hfcpci: Fix potential deadlock on &hc->lock
Jamal Hadi Salim <jhs(a)mojatatu.com>
net: sched: cls_u32: Fix match key mis-addressing
Georg Müller <georgmueller(a)gmx.net>
perf test uprobe_from_different_cu: Skip if there is no gcc
Lin Ma <linma(a)zju.edu.cn>
rtnetlink: let rtnl_bridge_setlink checks IFLA_BRIDGE_MODE length
Yuanjun Gong <ruc_gongyuanjun(a)163.com>
net/mlx5e: fix return value check in mlx5e_ipsec_remove_trailer()
Zhengchao Shao <shaozhengchao(a)huawei.com>
net/mlx5: DR, fix memory leak in mlx5dr_cmd_create_reformat_ctx
Heiko Carstens <hca(a)linux.ibm.com>
KVM: s390: fix sthyi error handling
ndesaulniers(a)google.com <ndesaulniers(a)google.com>
word-at-a-time: use the same return type for has_zero regardless of endianness
Bart Van Assche <bvanassche(a)acm.org>
loop: Select I/O scheduler 'none' from inside add_disk()
Peter Zijlstra <peterz(a)infradead.org>
perf: Fix function pointer case
D Scott Phillips <scott(a)os.amperecomputing.com>
arm64: Fix bit-shifting UB in the MIDR_CPU_MODEL() macro
D Scott Phillips <scott(a)os.amperecomputing.com>
arm64: Add AMPERE1 to the Spectre-BHB affected list
Thomas Petazzoni <thomas.petazzoni(a)bootlin.com>
ASoC: cs42l51: fix driver to properly autoload with automatic module loading
Pedro Tammela <pctammela(a)mojatatu.com>
net/sched: sch_qfq: account for stab overhead in qfq_enqueue
Filipe Manana <fdmanana(a)suse.com>
btrfs: fix race between quota disable and quota assign ioctls
Marcos Paulo de Souza <mpdesouza(a)suse.com>
btrfs: qgroup: return ENOTCONN instead of EINVAL when quotas are not enabled
Marcos Paulo de Souza <mpdesouza(a)suse.com>
btrfs: qgroup: remove one-time use variables for quota_root checks
Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
cpufreq: intel_pstate: Drop ACPI _PSS states table patching
Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
ACPI: processor: perflib: Avoid updating frequency QoS unnecessarily
Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
ACPI: processor: perflib: Use the "no limit" frequency QoS
Joe Thornber <ejt(a)redhat.com>
dm cache policy smq: ensure IO doesn't prevent cleaner policy progress
Mark Brown <broonie(a)kernel.org>
ASoC: wm8904: Fill the cache for WM8904_ADC_TEST_0 register
Stefan Haberland <sth(a)linux.ibm.com>
s390/dasd: fix hanging device after quiesce/resume
Jason Wang <jasowang(a)redhat.com>
virtio-net: fix race between set queues and probe
Filipe Manana <fdmanana(a)suse.com>
btrfs: check if the transaction was aborted at btrfs_wait_for_commit()
Jonas Gorski <jonas.gorski(a)gmail.com>
irq-bcm6345-l1: Do not assume a fixed block to cpu mapping
Alexander Steffen <Alexander.Steffen(a)infineon.com>
tpm_tis: Explicitly check for error code
Filipe Manana <fdmanana(a)suse.com>
btrfs: check for commit error at btrfs_attach_transaction_barrier()
Gilles Buloz <Gilles.Buloz(a)kontron.com>
hwmon: (nct7802) Fix for temp6 (PECI1) processed even if PECI1 disabled
Zhang Shurong <zhang_shurong(a)foxmail.com>
staging: ks7010: potential buffer overflow in ks_wlan_set_encode_ext()
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Documentation: security-bugs.rst: clarify CVE handling
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Documentation: security-bugs.rst: update preferences when dealing with the linux-distros group
Dan Carpenter <dan.carpenter(a)linaro.org>
Revert "usb: xhci: tegra: Fix error check"
Ricardo Ribalda <ribalda(a)chromium.org>
usb: xhci-mtk: set the dma max_seg_size
Łukasz Bartosik <lb(a)semihalf.com>
USB: quirks: add quirk for Focusrite Scarlett
Guiting Shen <aarongt.shen(a)gmail.com>
usb: ohci-at91: Fix the unhandle interrupt when resume
Jisheng Zhang <jszhang(a)kernel.org>
usb: dwc3: don't reset device side if dwc3 was configured as host-only
Gratian Crisan <gratian.crisan(a)ni.com>
usb: dwc3: pci: skip BYT GPIO lookup table for hardwired phy
Jakub Vanek <linuxtardis(a)gmail.com>
Revert "usb: dwc3: core: Enable AutoRetry feature in the controller"
Marc Kleine-Budde <mkl(a)pengutronix.de>
can: gs_usb: gs_can_close(): add missing set of CAN state to CAN_STATE_STOPPED
Johan Hovold <johan(a)kernel.org>
USB: serial: simple: sort driver entries
Oliver Neukum <oneukum(a)suse.com>
USB: serial: simple: add Kaufmann RKS+CAN VCP
Mohsen Tahmasebi <moh53n(a)moh53n.ir>
USB: serial: option: add Quectel EC200A module support
Jerry Meng <jerry-meng(a)foxmail.com>
USB: serial: option: support Quectel EM060K_128
Samuel Holland <samuel.holland(a)sifive.com>
serial: sifive: Fix sifive_serial_console_setup() section
Ruihong Luo <colorsu1922(a)gmail.com>
serial: 8250_dw: Preserve original value of DLF register
Zheng Yejian <zhengyejian1(a)huawei.com>
tracing: Fix warning in trace_buffered_event_disable()
Zheng Yejian <zhengyejian1(a)huawei.com>
ring-buffer: Fix wrong stat of cpu_buffer->read
Arnd Bergmann <arnd(a)arndb.de>
ata: pata_ns87415: mark ns87560_tf_read static
Yu Kuai <yukuai3(a)huawei.com>
dm raid: fix missing reconfig_mutex unlock in raid_ctr() error paths
Bart Van Assche <bvanassche(a)acm.org>
block: Fix a source code comment in include/uapi/linux/blkzoned.h
Matus Gajdos <matuszpd(a)gmail.com>
ASoC: fsl_spdif: Silence output on stop
Gaosheng Cui <cuigaosheng1(a)huawei.com>
drm/msm: Fix IS_ERR_OR_NULL() vs NULL check in a5xx_submit_in_rb()
Rob Clark <robdclark(a)chromium.org>
drm/msm/adreno: Fix snapshot BINDLESS_DATA size
Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org>
drm/msm/dpu: drop enum dpu_core_perf_data_bus_id
Dan Carpenter <dan.carpenter(a)linaro.org>
RDMA/mlx4: Make check for invalid flags stricter
Yuanjun Gong <ruc_gongyuanjun(a)163.com>
benet: fix return value check in be_lancer_xmit_workarounds()
Lin Ma <linma(a)zju.edu.cn>
net/sched: mqprio: Add length check for TCA_MQPRIO_{MAX/MIN}_RATE64
Vladimir Oltean <vladimir.oltean(a)nxp.com>
net/sched: mqprio: add extack to mqprio_parse_nlattr()
Vladimir Oltean <vladimir.oltean(a)nxp.com>
net/sched: mqprio: refactor nlattr parsing to a separate function
Maxim Mikityanskiy <maxtram95(a)gmail.com>
platform/x86: msi-laptop: Fix rfkill out-of-sync on MSI Wind U100
Hangbin Liu <liuhangbin(a)gmail.com>
team: reset team's flags when down link is P2P device
Hangbin Liu <liuhangbin(a)gmail.com>
bonding: reset bond's flags when down link is P2P device
Stewart Smith <trawets(a)amazon.com>
tcp: Reduce chance of collisions in inet6_hashfn().
Maciej Żenczykowski <maze(a)google.com>
ipv6 addrconf: fix bug where deleting a mngtmpaddr can create a new temporary address
Yuanjun Gong <ruc_gongyuanjun(a)163.com>
ethernet: atheros: fix return value check in atl1e_tso_csum()
Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com>
phy: hisilicon: Fix an out of bounds check in hisi_inno_phy_probe()
Jiri Benc <jbenc(a)redhat.com>
vxlan: calculate correct header length for GPE
Wang Ming <machel(a)vivo.com>
i40e: Fix an NULL vs IS_ERR() bug for debugfs_create_dir()
Chao Yu <chao(a)kernel.org>
ext4: fix to check return value of freeze_bdev() in ext4_shutdown()
Petr Pavlu <petr.pavlu(a)suse.com>
keys: Fix linking a duplicate key to a keyring's assoc_array
David Howells <dhowells(a)redhat.com>
uapi: General notification queue definitions
Nilesh Javali <njavali(a)marvell.com>
scsi: qla2xxx: Array index may go out of bound
Ye Bin <yebin10(a)huawei.com>
scsi: qla2xxx: Fix inconsistent format argument type in qla_os.c
Heiner Kallweit <hkallweit1(a)gmail.com>
pwm: meson: fix handling of period/duty if greater than UINT_MAX
Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de>
pwm: meson: Simplify duplicated per-channel tracking
Colin Ian King <colin.king(a)canonical.com>
pwm: meson: Remove redundant assignment to variable fin_freq
Zheng Yejian <zhengyejian1(a)huawei.com>
ftrace: Fix possible warning on checking all pages used in ftrace_process_locs()
Linus Torvalds <torvalds(a)linux-foundation.org>
ftrace: Store the order of pages allocated in ftrace_page
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
ftrace: Check if pages were allocated before calling free_pages()
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
ftrace: Add information on number of page groups allocated
Alexander Aring <aahringo(a)redhat.com>
fs: dlm: interrupt posix locks only when process is killed
Alexander Aring <aahringo(a)redhat.com>
dlm: rearrange async condition return
Alexander Aring <aahringo(a)redhat.com>
dlm: cleanup plock_op vs plock_xop
Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
PCI/ASPM: Avoid link retraining race
Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
PCI/ASPM: Factor out pcie_wait_for_retrain()
Bjorn Helgaas <bhelgaas(a)google.com>
PCI/ASPM: Return 0 or -ETIMEDOUT from pcie_retrain_link()
Zhihao Cheng <chengzhihao1(a)huawei.com>
ext4: Fix reusing stale buffer heads from last failed mounting
Chunguang Xu <brookxu(a)tencent.com>
ext4: rename journal_dev to s_journal_dev inside ext4_sb_info
Filipe Manana <fdmanana(a)suse.com>
btrfs: fix extent buffer leak after tree mod log failure at split_node()
Filipe Manana <fdmanana(a)suse.com>
btrfs: fix race between quota disable and relocation
Qu Wenruo <wqu(a)suse.com>
btrfs: qgroup: catch reserved space leaks at unmount time
Zheng Wang <zyytlz.wz(a)163.com>
bcache: Fix __bch_btree_node_alloc to make the failure behavior consistent
Coly Li <colyli(a)suse.de>
bcache: remove 'int n' from parameter list of bch_bucket_alloc_set()
Hans de Goede <hdegoede(a)redhat.com>
gpio: tps68470: Make tps68470_gpio_output() always set the initial value
Zhihao Cheng <chengzhihao1(a)huawei.com>
jbd2: Fix wrongly judgement for buffer head removing while doing checkpoint
Zhang Yi <yi.zhang(a)huawei.com>
jbd2: recheck chechpointing non-dirty buffer
Zhang Yi <yi.zhang(a)huawei.com>
jbd2: remove redundant buffer io error checks
Mauro Carvalho Chehab <mchehab+huawei(a)kernel.org>
jbd2: fix kernel-doc markups
Xianting Tian <xianting_tian(a)126.com>
jbd2: fix incorrect code style
-------------
Diffstat:
Documentation/admin-guide/security-bugs.rst | 37 +++---
Makefile | 4 +-
arch/arm/boot/dts/imx35.dtsi | 2 +-
arch/arm/boot/dts/imx6qdl.dtsi | 6 +-
arch/arm/boot/dts/imx6sl.dtsi | 5 +-
arch/arm/boot/dts/imx6sll.dtsi | 34 ++---
arch/arm/boot/dts/imx6sx.dtsi | 5 +-
arch/arm/boot/dts/imx6ul.dtsi | 2 +
arch/arm/boot/dts/imx7d.dtsi | 6 +
arch/arm/boot/dts/imx7s.dtsi | 2 +
.../boot/dts/altera/socfpga_stratix10_socdk.dts | 2 +-
arch/arm64/include/asm/cputype.h | 6 +-
arch/arm64/kernel/cpu_errata.c | 6 +
arch/powerpc/include/asm/word-at-a-time.h | 2 +-
arch/powerpc/mm/init_64.c | 3 +-
arch/s390/kernel/sthyi.c | 6 +-
arch/s390/kvm/intercept.c | 9 +-
drivers/acpi/processor_perflib.c | 42 ++++--
drivers/ata/pata_ns87415.c | 2 +-
drivers/base/core.c | 44 +++++++
drivers/base/power/power.h | 8 +-
drivers/base/power/runtime.c | 6 +-
drivers/base/power/wakeirq.c | 111 ++++++++++++----
drivers/block/loop.c | 2 +-
drivers/char/tpm/tpm_tis_core.c | 10 +-
drivers/cpufreq/intel_pstate.c | 14 --
drivers/gpio/gpio-tps68470.c | 6 +-
drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 2 +-
drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h | 2 +-
drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h | 13 --
drivers/hwmon/nct7802.c | 2 +-
drivers/infiniband/hw/mlx4/qp.c | 18 +--
drivers/irqchip/irq-bcm6345-l1.c | 14 +-
drivers/isdn/hardware/mISDN/hfcpci.c | 10 +-
drivers/md/bcache/alloc.c | 35 +++--
drivers/md/bcache/bcache.h | 4 +-
drivers/md/bcache/btree.c | 6 +-
drivers/md/bcache/super.c | 2 +-
drivers/md/dm-cache-policy-smq.c | 28 ++--
drivers/md/dm-raid.c | 9 +-
drivers/mtd/nand/raw/meson_nand.c | 3 +-
drivers/mtd/nand/raw/omap_elm.c | 24 ++--
drivers/mtd/nand/spi/toshiba.c | 4 +-
drivers/net/bonding/bond_main.c | 5 +
drivers/net/can/usb/gs_usb.c | 2 +
drivers/net/ethernet/atheros/atl1e/atl1e_main.c | 7 +-
drivers/net/ethernet/emulex/benet/be_main.c | 3 +-
drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 2 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +-
.../mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 4 +-
.../ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 5 +-
drivers/net/ethernet/xilinx/ll_temac_main.c | 16 +--
drivers/net/tap.c | 2 +-
drivers/net/team/team.c | 9 ++
drivers/net/tun.c | 2 +-
drivers/net/usb/cdc_ether.c | 21 +++
drivers/net/usb/usbnet.c | 6 +
drivers/net/usb/zaurus.c | 21 +++
drivers/net/virtio_net.c | 4 +-
drivers/net/vxlan.c | 22 ++--
drivers/pci/pcie/aspm.c | 55 +++++---
drivers/phy/hisilicon/phy-hisi-inno-usb2.c | 2 +-
drivers/platform/x86/msi-laptop.c | 8 +-
drivers/pwm/pwm-meson.c | 27 ++--
drivers/s390/block/dasd_ioctl.c | 1 +
drivers/s390/scsi/zfcp_fc.c | 6 +-
drivers/scsi/qla2xxx/qla_os.c | 5 +-
drivers/staging/ks7010/ks_wlan_net.c | 6 +-
drivers/tty/serial/8250/8250_dwlib.c | 6 +-
drivers/tty/serial/sifive.c | 2 +-
drivers/usb/core/quirks.c | 4 +
drivers/usb/dwc3/core.c | 20 +--
drivers/usb/dwc3/core.h | 3 -
drivers/usb/dwc3/dwc3-pci.c | 6 +-
drivers/usb/host/ohci-at91.c | 8 +-
drivers/usb/host/xhci-mtk.c | 1 +
drivers/usb/host/xhci-tegra.c | 8 +-
drivers/usb/serial/option.c | 6 +
drivers/usb/serial/usb-serial-simple.c | 73 ++++++-----
fs/btrfs/ctree.c | 2 +
fs/btrfs/disk-io.c | 5 +
fs/btrfs/ioctl.c | 2 +
fs/btrfs/qgroup.c | 116 ++++++++++++-----
fs/btrfs/qgroup.h | 1 +
fs/btrfs/transaction.c | 10 +-
fs/ceph/caps.c | 17 +++
fs/ceph/debugfs.c | 13 ++
fs/ceph/mds_client.c | 5 +-
fs/ceph/mds_client.h | 14 ++
fs/ceph/super.c | 14 +-
fs/dlm/plock.c | 100 ++++++++------
fs/ext2/ext2.h | 12 --
fs/ext2/super.c | 23 +---
fs/ext4/ext4.h | 2 +-
fs/ext4/fsmap.c | 8 +-
fs/ext4/ioctl.c | 5 +-
fs/ext4/super.c | 25 ++--
fs/jbd2/checkpoint.c | 137 ++++++--------------
fs/jbd2/journal.c | 42 +++---
fs/jbd2/transaction.c | 31 ++---
fs/super.c | 11 +-
fs/sysv/itree.c | 4 +
include/asm-generic/word-at-a-time.h | 2 +-
include/linux/device.h | 3 +
include/linux/jbd2.h | 2 +-
include/linux/pm_wakeirq.h | 9 +-
include/net/ipv6.h | 8 +-
include/net/vxlan.h | 13 +-
include/uapi/linux/blkzoned.h | 10 +-
include/uapi/linux/watch_queue.h | 55 ++++++++
kernel/events/core.c | 8 +-
kernel/trace/ftrace.c | 75 ++++++++---
kernel/trace/ring_buffer.c | 22 ++--
kernel/trace/trace.c | 21 ++-
kernel/trace/trace.h | 2 +
kernel/trace/trace_events.c | 14 +-
lib/test_firmware.c | 49 ++++---
net/bluetooth/l2cap_sock.c | 2 +
net/ceph/osd_client.c | 20 ++-
net/core/rtnetlink.c | 8 +-
net/core/sock.c | 21 +--
net/core/sock_map.c | 2 -
net/dcb/dcbnl.c | 2 +-
net/ipv4/tcp_metrics.c | 70 ++++++----
net/ipv6/addrconf.c | 14 +-
net/ipv6/ip6mr.c | 2 +-
net/sched/cls_fw.c | 1 -
net/sched/cls_route.c | 1 -
net/sched/cls_u32.c | 57 +++++++-
net/sched/sch_mqprio.c | 144 +++++++++++++--------
net/sched/sch_qfq.c | 7 +-
net/unix/af_unix.c | 2 +-
security/keys/request_key.c | 35 +++--
sound/soc/codecs/cs42l51-i2c.c | 6 +
sound/soc/codecs/cs42l51.c | 7 -
sound/soc/codecs/cs42l51.h | 1 -
sound/soc/codecs/wm8904.c | 3 +
sound/soc/fsl/fsl_spdif.c | 2 +
.../tests/shell/test_uprobe_from_different_cu.sh | 8 +-
tools/testing/selftests/rseq/rseq.c | 31 ++++-
140 files changed, 1444 insertions(+), 832 deletions(-)
Currently the ExpressKey Remote battery will persist indefinitely in
/sys/class/power_supply. Remove the battery when we stop getting
reports from the device.
Also remove some unneccessary code and make an EKR struct name more
descriptive.
Only the bugfix in the first patch will be sent to stable.
Aaron Armstrong Skomra (3):
HID: wacom: remove the battery when the EKR is off
HID: wacom: remove unnecessary 'connected' variable from EKR
HID: wacom: struct name cleanup
drivers/hid/wacom.h | 1 +
drivers/hid/wacom_sys.c | 44 +++++++++++++++++++++++++++++------------
drivers/hid/wacom_wac.c | 7 +++----
drivers/hid/wacom_wac.h | 4 ++--
4 files changed, 37 insertions(+), 19 deletions(-)
--
2.34.1
The following commit has been merged into the x86/urgent branch of tip:
Commit-ID: ba5ca5e5e6a1d55923e88b4a83da452166f5560e
Gitweb: https://git.kernel.org/tip/ba5ca5e5e6a1d55923e88b4a83da452166f5560e
Author: Sean Christopherson <seanjc(a)google.com>
AuthorDate: Fri, 11 Aug 2023 08:52:55 -07:00
Committer: Borislav Petkov (AMD) <bp(a)alien8.de>
CommitterDate: Mon, 14 Aug 2023 10:47:55 +02:00
x86/retpoline: Don't clobber RFLAGS during srso_safe_ret()
Use LEA instead of ADD when adjusting %rsp in srso_safe_ret{,_alias}()
so as to avoid clobbering flags. Drop one of the INT3 instructions to
account for the LEA consuming one more byte than the ADD.
KVM's emulator makes indirect calls into a jump table of sorts, where
the destination of each call is a small blob of code that performs fast
emulation by executing the target instruction with fixed operands.
E.g. to emulate ADC, fastop() invokes adcb_al_dl():
adcb_al_dl:
<+0>: adc %dl,%al
<+2>: jmp <__x86_return_thunk>
A major motivation for doing fast emulation is to leverage the CPU to
handle consumption and manipulation of arithmetic flags, i.e. RFLAGS is
both an input and output to the target of the call. fastop() collects
the RFLAGS result by pushing RFLAGS onto the stack and popping them back
into a variable (held in %rdi in this case):
asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n"
<+71>: mov 0xc0(%r8),%rdx
<+78>: mov 0x100(%r8),%rcx
<+85>: push %rdi
<+86>: popf
<+87>: call *%rsi
<+89>: nop
<+90>: nop
<+91>: nop
<+92>: pushf
<+93>: pop %rdi
and then propagating the arithmetic flags into the vCPU's emulator state:
ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
<+64>: and $0xfffffffffffff72a,%r9
<+94>: and $0x8d5,%edi
<+109>: or %rdi,%r9
<+122>: mov %r9,0x10(%r8)
The failures can be most easily reproduced by running the "emulator"
test in KVM-Unit-Tests.
If you're feeling a bit of deja vu, see commit b63f20a778c8
("x86/retpoline: Don't clobber RFLAGS during CALL_NOSPEC on i386").
In addition, this breaks booting of clang-compiled guest on
a gcc-compiled host where the host contains the %rsp-modifying SRSO
mitigations.
[ bp: Massage commit message, extend, remove addresses. ]
Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation")
Closes: https://lore.kernel.org/all/de474347-122d-54cd-eabf-9dcc95ab9eae@amd.com
Reported-by: Srikanth Aithal <sraithal(a)amd.com>
Reported-by: Nathan Chancellor <nathan(a)kernel.org>
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de>
Tested-by: Nathan Chancellor <nathan(a)kernel.org>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/20230810013334.GA5354@dev-arch.thelio-3990X/
Link: https://lore.kernel.org/r/20230811155255.250835-1-seanjc@google.com
---
arch/x86/lib/retpoline.S | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 2cff585..132cedb 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -164,7 +164,7 @@ __EXPORT_THUNK(srso_untrain_ret_alias)
/* Needs a definition for the __x86_return_thunk alternative below. */
SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE)
#ifdef CONFIG_CPU_SRSO
- add $8, %_ASM_SP
+ lea 8(%_ASM_SP), %_ASM_SP
UNWIND_HINT_FUNC
#endif
ANNOTATE_UNRET_SAFE
@@ -239,7 +239,7 @@ __EXPORT_THUNK(zen_untrain_ret)
* SRSO untraining sequence for Zen1/2, similar to zen_untrain_ret()
* above. On kernel entry, srso_untrain_ret() is executed which is a
*
- * movabs $0xccccccc308c48348,%rax
+ * movabs $0xccccc30824648d48,%rax
*
* and when the return thunk executes the inner label srso_safe_ret()
* later, it is a stack manipulation and a RET which is mispredicted and
@@ -252,11 +252,10 @@ SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
.byte 0x48, 0xb8
SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
- add $8, %_ASM_SP
+ lea 8(%_ASM_SP), %_ASM_SP
ret
int3
int3
- int3
lfence
call srso_safe_ret
int3
From: Pu Wen <puwen(a)hygon.cn>
Hygon updated processors have CPUID leaf 0xB correctly populated and don't
need the fixed package ID shift workaround. The fixup is also incorrect
when running in a guest.
Fixes: e0ceeae708ce ("x86/CPU/hygon: Fix phys_proc_id calculation logic for multi-die processors")
Signed-off-by: Pu Wen <puwen(a)hygon.cn>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: <stable(a)vger.kernel.org>
Link: https://lore.kernel.org/r/tencent_594804A808BD93A4EBF50A994F228E3A7F07@qq.c…
---
arch/x86/kernel/cpu/hygon.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -87,8 +87,12 @@ static void hygon_get_topology(struct cp
if (!err)
c->x86_coreid_bits = get_count_order(c->x86_max_cores);
- /* Socket ID is ApicId[6] for these processors. */
- c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
+ /*
+ * Socket ID is ApicId[6] for the processors with model <= 0x3
+ * when running on host.
+ */
+ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && c->x86_model <= 0x3)
+ c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
cacheinfo_hygon_init_llc_id(c, cpu);
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
Device connected to usb otg port of GXL-based boards can not be
recognised after resumption, doesn't recover even if disconnect and
reconnect the device. dmesg shows it disconnects during resumption.
[ 41.492911] usb 1-2: USB disconnect, device number 3
[ 41.499346] usb 1-2: unregistering device
[ 41.511939] usb 1-2: unregistering interface 1-2:1.0
Calling usb_post_init() will fix this issue, and it's tested and
verified on libretech's aml-s905x-cc board.
Cc: stable(a)vger.kernel.org # v5.8+
Fixes: c99993376f72 ("usb: dwc3: Add Amlogic G12A DWC3 glue")
Signed-off-by: Luke Lu <luke.lu(a)libre.computer>
---
Note here, the commmit of Fixes tag is the first patch which bring
suspend/resume function, so let's use it as the fix tag.
As commit 5b0ba0caaf3a: (usb: dwc3: meson-g12a: refactor usb init)"
introduced the use_post_init() function, and this patch will explicitly
depend on it, so let's set kernel version higher or equal to v5.8.
Changes since v1:
- add Fixes tag and Cc stable tree
---
drivers/usb/dwc3/dwc3-meson-g12a.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c
index e99c7489dba0..2c07c038b584 100644
--- a/drivers/usb/dwc3/dwc3-meson-g12a.c
+++ b/drivers/usb/dwc3/dwc3-meson-g12a.c
@@ -926,6 +926,12 @@ static int __maybe_unused dwc3_meson_g12a_resume(struct device *dev)
return ret;
}
+ if (priv->drvdata->usb_post_init) {
+ ret = priv->drvdata->usb_post_init(priv);
+ if (ret)
+ return ret;
+ }
+
return 0;
}
--
2.40.1
From: Joel Fernandes <joel(a)joelfernandes.org>
[ Upstream commit d52d3a2bf408ff86f3a79560b5cce80efb340239 ]
During shutdown of rcutorture, the shutdown thread in
rcu_torture_cleanup() calls torture_cleanup_begin() which sets fullstop
to FULLSTOP_RMMOD. This is enough to cause the rcutorture threads for
readers and fakewriters to breakout of their main while loop and start
shutting down.
Once out of their main loop, they then call torture_kthread_stopping()
which in turn waits for kthread_stop() to be called, however
rcu_torture_cleanup() has not even called kthread_stop() on those
threads yet, it does that a bit later. However, before it gets a chance
to do so, torture_kthread_stopping() calls
schedule_timeout_interruptible(1) in a tight loop. Tracing confirmed
this makes the timer softirq constantly execute timer callbacks, while
never returning back to the softirq exit path and is essentially "locked
up" because of that. If the softirq preempts the shutdown thread,
kthread_stop() may never be called.
This commit improves the situation dramatically, by increasing timeout
passed to schedule_timeout_interruptible() 1/20th of a second. This
causes the timer softirq to not lock up a CPU and everything works fine.
Testing has shown 100 runs of TREE07 passing reliably, which was not the
case before because of RCU stalls.
Cc: Paul McKenney <paulmck(a)kernel.org>
Cc: Frederic Weisbecker <fweisbec(a)gmail.com>
Cc: Zhouyi Zhou <zhouzhouyi(a)gmail.com>
Cc: <stable(a)vger.kernel.org> # 6.0.x
Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org>
Reviewed-by: Davidlohr Bueso <dave(a)stgolabs.net>
Tested-by: Zhouyi Zhou <zhouzhouyi(a)gmail.com>
---
kernel/torture.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/torture.c b/kernel/torture.c
index 1061492f14bd..477d9b601438 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -788,7 +788,7 @@ void torture_kthread_stopping(char *title)
VERBOSE_TOROUT_STRING(buf);
while (!kthread_should_stop()) {
torture_shutdown_absorb(title);
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ/20);
}
}
EXPORT_SYMBOL_GPL(torture_kthread_stopping);
--
2.41.0.640.ga95def55d0-goog
From: Joel Fernandes <joel(a)joelfernandes.org>
During shutdown of rcutorture, the shutdown thread in
rcu_torture_cleanup() calls torture_cleanup_begin() which sets fullstop
to FULLSTOP_RMMOD. This is enough to cause the rcutorture threads for
readers and fakewriters to breakout of their main while loop and start
shutting down.
Once out of their main loop, they then call torture_kthread_stopping()
which in turn waits for kthread_stop() to be called, however
rcu_torture_cleanup() has not even called kthread_stop() on those
threads yet, it does that a bit later. However, before it gets a chance
to do so, torture_kthread_stopping() calls
schedule_timeout_interruptible(1) in a tight loop. Tracing confirmed
this makes the timer softirq constantly execute timer callbacks, while
never returning back to the softirq exit path and is essentially "locked
up" because of that. If the softirq preempts the shutdown thread,
kthread_stop() may never be called.
This commit improves the situation dramatically, by increasing timeout
passed to schedule_timeout_interruptible() 1/20th of a second. This
causes the timer softirq to not lock up a CPU and everything works fine.
Testing has shown 100 runs of TREE07 passing reliably, which was not the
case before because of RCU stalls.
Cc: Paul McKenney <paulmck(a)kernel.org>
Cc: Frederic Weisbecker <fweisbec(a)gmail.com>
Cc: Zhouyi Zhou <zhouzhouyi(a)gmail.com>
Cc: <stable(a)vger.kernel.org> # 6.0.x
Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org>
Reviewed-by: Davidlohr Bueso <dave(a)stgolabs.net>
Tested-by: Zhouyi Zhou <zhouzhouyi(a)gmail.com>
---
kernel/torture.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/torture.c b/kernel/torture.c
index 1061492f14bd..477d9b601438 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -788,7 +788,7 @@ void torture_kthread_stopping(char *title)
VERBOSE_TOROUT_STRING(buf);
while (!kthread_should_stop()) {
torture_shutdown_absorb(title);
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ/20);
}
}
EXPORT_SYMBOL_GPL(torture_kthread_stopping);
--
2.41.0.640.ga95def55d0-goog
From: Frederic Weisbecker <frederic(a)kernel.org>
[ Upstream commit a1ff03cd6fb9c501fff63a4a2bface9adcfa81cd ]
tick: Detect and fix jiffies update stall
On some rare cases, the timekeeper CPU may be delaying its jiffies
update duty for a while. Known causes include:
* The timekeeper is waiting on stop_machine in a MULTI_STOP_DISABLE_IRQ
or MULTI_STOP_RUN state. Disabled interrupts prevent from timekeeping
updates while waiting for the target CPU to complete its
stop_machine() callback.
* The timekeeper vcpu has VMEXIT'ed for a long while due to some overload
on the host.
Detect and fix these situations with emergency timekeeping catchups.
Original-patch-by: Paul E. McKenney <paulmck(a)kernel.org>
Signed-off-by: Frederic Weisbecker <frederic(a)kernel.org>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org>
---
kernel/time/tick-sched.c | 17 +++++++++++++++++
kernel/time/tick-sched.h | 4 ++++
2 files changed, 21 insertions(+)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f42d0776bc84..7701c720dc1f 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -180,6 +180,8 @@ static ktime_t tick_init_jiffy_update(void)
return period;
}
+#define MAX_STALLED_JIFFIES 5
+
static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
{
int cpu = smp_processor_id();
@@ -207,6 +209,21 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
if (tick_do_timer_cpu == cpu)
tick_do_update_jiffies64(now);
+ /*
+ * If jiffies update stalled for too long (timekeeper in stop_machine()
+ * or VMEXIT'ed for several msecs), force an update.
+ */
+ if (ts->last_tick_jiffies != jiffies) {
+ ts->stalled_jiffies = 0;
+ ts->last_tick_jiffies = READ_ONCE(jiffies);
+ } else {
+ if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) {
+ tick_do_update_jiffies64(now);
+ ts->stalled_jiffies = 0;
+ ts->last_tick_jiffies = READ_ONCE(jiffies);
+ }
+ }
+
if (ts->inidle)
ts->got_idle_tick = 1;
}
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index d952ae393423..504649513399 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -49,6 +49,8 @@ enum tick_nohz_mode {
* @timer_expires_base: Base time clock monotonic for @timer_expires
* @next_timer: Expiry time of next expiring timer for debugging purpose only
* @tick_dep_mask: Tick dependency mask - is set, if someone needs the tick
+ * @last_tick_jiffies: Value of jiffies seen on last tick
+ * @stalled_jiffies: Number of stalled jiffies detected across ticks
*/
struct tick_sched {
struct hrtimer sched_timer;
@@ -77,6 +79,8 @@ struct tick_sched {
u64 next_timer;
ktime_t idle_expires;
atomic_t tick_dep_mask;
+ unsigned long last_tick_jiffies;
+ unsigned int stalled_jiffies;
};
extern struct tick_sched *tick_get_tick_sched(int cpu);
--
2.41.0.640.ga95def55d0-goog
Commit 2174a08db80d ("sch_netem: acquire qdisc lock in netem_change()")
was backported to older stables where it is causing 'sleeping in invalid
context' bug. The following patch fixes the problem and can be cleanly
applied to the stable branches affected. It was backported to 6.4.y about
a month ago.
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x ef222f551e7c4e2008fc442ffc9edcd1a7fd8f63
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081353-arguably-darkness-ec85@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
ef222f551e7c ("scsi: qedf: Fix firmware halt over suspend and resume")
f6b172f21999 ("scsi: qedf: Add schedule recovery handler")
6e7c8eea929e ("scsi: qedf: Implement callback for bw_update")
31696204c44c ("scsi: qedf: Add shutdown callback handler")
5f85942c2ea2 ("Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ef222f551e7c4e2008fc442ffc9edcd1a7fd8f63 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali(a)marvell.com>
Date: Mon, 7 Aug 2023 15:07:24 +0530
Subject: [PATCH] scsi: qedf: Fix firmware halt over suspend and resume
While performing certain power-off sequences, PCI drivers are called to
suspend and resume their underlying devices through PCI PM (power
management) interface. However the hardware does not support PCI PM
suspend/resume operations so system wide suspend/resume leads to bad MFW
(management firmware) state which causes various follow-up errors in driver
when communicating with the device/firmware.
To fix this driver implements PCI PM suspend handler to indicate
unsupported operation to the PCI subsystem explicitly, thus avoiding system
to go into suspended/standby mode.
Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.")
Signed-off-by: Saurav Kashyap <skashyap(a)marvell.com>
Signed-off-by: Nilesh Javali <njavali(a)marvell.com>
Link: https://lore.kernel.org/r/20230807093725.46829-1-njavali@marvell.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 2a31ddc99dde..7825765c936c 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -31,6 +31,7 @@ static void qedf_remove(struct pci_dev *pdev);
static void qedf_shutdown(struct pci_dev *pdev);
static void qedf_schedule_recovery_handler(void *dev);
static void qedf_recovery_handler(struct work_struct *work);
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state);
/*
* Driver module parameters.
@@ -3271,6 +3272,7 @@ static struct pci_driver qedf_pci_driver = {
.probe = qedf_probe,
.remove = qedf_remove,
.shutdown = qedf_shutdown,
+ .suspend = qedf_suspend,
};
static int __qedf_probe(struct pci_dev *pdev, int mode)
@@ -4000,6 +4002,22 @@ static void qedf_shutdown(struct pci_dev *pdev)
__qedf_remove(pdev, QEDF_MODE_NORMAL);
}
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct qedf_ctx *qedf;
+
+ if (!pdev) {
+ QEDF_ERR(NULL, "pdev is NULL.\n");
+ return -ENODEV;
+ }
+
+ qedf = pci_get_drvdata(pdev);
+
+ QEDF_ERR(&qedf->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+ return -EPERM;
+}
+
/*
* Recovery handler code
*/
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x ef222f551e7c4e2008fc442ffc9edcd1a7fd8f63
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081352-pouncing-speller-9684@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
ef222f551e7c ("scsi: qedf: Fix firmware halt over suspend and resume")
f6b172f21999 ("scsi: qedf: Add schedule recovery handler")
6e7c8eea929e ("scsi: qedf: Implement callback for bw_update")
31696204c44c ("scsi: qedf: Add shutdown callback handler")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ef222f551e7c4e2008fc442ffc9edcd1a7fd8f63 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali(a)marvell.com>
Date: Mon, 7 Aug 2023 15:07:24 +0530
Subject: [PATCH] scsi: qedf: Fix firmware halt over suspend and resume
While performing certain power-off sequences, PCI drivers are called to
suspend and resume their underlying devices through PCI PM (power
management) interface. However the hardware does not support PCI PM
suspend/resume operations so system wide suspend/resume leads to bad MFW
(management firmware) state which causes various follow-up errors in driver
when communicating with the device/firmware.
To fix this driver implements PCI PM suspend handler to indicate
unsupported operation to the PCI subsystem explicitly, thus avoiding system
to go into suspended/standby mode.
Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.")
Signed-off-by: Saurav Kashyap <skashyap(a)marvell.com>
Signed-off-by: Nilesh Javali <njavali(a)marvell.com>
Link: https://lore.kernel.org/r/20230807093725.46829-1-njavali@marvell.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 2a31ddc99dde..7825765c936c 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -31,6 +31,7 @@ static void qedf_remove(struct pci_dev *pdev);
static void qedf_shutdown(struct pci_dev *pdev);
static void qedf_schedule_recovery_handler(void *dev);
static void qedf_recovery_handler(struct work_struct *work);
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state);
/*
* Driver module parameters.
@@ -3271,6 +3272,7 @@ static struct pci_driver qedf_pci_driver = {
.probe = qedf_probe,
.remove = qedf_remove,
.shutdown = qedf_shutdown,
+ .suspend = qedf_suspend,
};
static int __qedf_probe(struct pci_dev *pdev, int mode)
@@ -4000,6 +4002,22 @@ static void qedf_shutdown(struct pci_dev *pdev)
__qedf_remove(pdev, QEDF_MODE_NORMAL);
}
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct qedf_ctx *qedf;
+
+ if (!pdev) {
+ QEDF_ERR(NULL, "pdev is NULL.\n");
+ return -ENODEV;
+ }
+
+ qedf = pci_get_drvdata(pdev);
+
+ QEDF_ERR(&qedf->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+ return -EPERM;
+}
+
/*
* Recovery handler code
*/
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x ef222f551e7c4e2008fc442ffc9edcd1a7fd8f63
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081351-dreamlike-morale-ab08@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
ef222f551e7c ("scsi: qedf: Fix firmware halt over suspend and resume")
f6b172f21999 ("scsi: qedf: Add schedule recovery handler")
6e7c8eea929e ("scsi: qedf: Implement callback for bw_update")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ef222f551e7c4e2008fc442ffc9edcd1a7fd8f63 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali(a)marvell.com>
Date: Mon, 7 Aug 2023 15:07:24 +0530
Subject: [PATCH] scsi: qedf: Fix firmware halt over suspend and resume
While performing certain power-off sequences, PCI drivers are called to
suspend and resume their underlying devices through PCI PM (power
management) interface. However the hardware does not support PCI PM
suspend/resume operations so system wide suspend/resume leads to bad MFW
(management firmware) state which causes various follow-up errors in driver
when communicating with the device/firmware.
To fix this driver implements PCI PM suspend handler to indicate
unsupported operation to the PCI subsystem explicitly, thus avoiding system
to go into suspended/standby mode.
Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.")
Signed-off-by: Saurav Kashyap <skashyap(a)marvell.com>
Signed-off-by: Nilesh Javali <njavali(a)marvell.com>
Link: https://lore.kernel.org/r/20230807093725.46829-1-njavali@marvell.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 2a31ddc99dde..7825765c936c 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -31,6 +31,7 @@ static void qedf_remove(struct pci_dev *pdev);
static void qedf_shutdown(struct pci_dev *pdev);
static void qedf_schedule_recovery_handler(void *dev);
static void qedf_recovery_handler(struct work_struct *work);
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state);
/*
* Driver module parameters.
@@ -3271,6 +3272,7 @@ static struct pci_driver qedf_pci_driver = {
.probe = qedf_probe,
.remove = qedf_remove,
.shutdown = qedf_shutdown,
+ .suspend = qedf_suspend,
};
static int __qedf_probe(struct pci_dev *pdev, int mode)
@@ -4000,6 +4002,22 @@ static void qedf_shutdown(struct pci_dev *pdev)
__qedf_remove(pdev, QEDF_MODE_NORMAL);
}
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct qedf_ctx *qedf;
+
+ if (!pdev) {
+ QEDF_ERR(NULL, "pdev is NULL.\n");
+ return -ENODEV;
+ }
+
+ qedf = pci_get_drvdata(pdev);
+
+ QEDF_ERR(&qedf->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+ return -EPERM;
+}
+
/*
* Recovery handler code
*/
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 1516ee035df32115197cd93ae3619dba7b020986
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081337-splendor-opal-8b0b@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
1516ee035df3 ("scsi: qedi: Fix firmware halt over suspend and resume")
96a766a789eb ("scsi: qedi: Add support for handling PCIe errors")
f4ba4e55db6d ("scsi: qedi: Add firmware error recovery invocation support")
5c35e4646566 ("scsi: qedi: Skip firmware connection termination for PCI shutdown handler")
e4020e0835ed ("scsi: qedi: Remove 2 set but unused variables")
4f93c4bf0f74 ("scsi: qedi: Add PCI shutdown handler support")
4b1068f5d74b ("scsi: qedi: Add MFW error recovery process")
2bfbc570586e ("qedi: Use hwfns and affin_hwfn_idx to get MSI-X vector index")
13b99d3d3907 ("Revert "scsi: qedi: Allocate IRQs based on msix_cnt"")
dcceeeb71fb7 ("scsi: qedi: add module param to set ping packet size")
1a291bce5eaf ("scsi: qedi: Allocate IRQs based on msix_cnt")
3fb5a21fd008 ("scsi: qedi: Cleanup redundant QEDI_PAGE_SIZE macro definition")
a3440d0d2f57 ("scsi: qedi: Send driver state to MFW")
534bbdf8832a ("qedi: Add support for populating ethernet TLVs.")
da09091732ae ("qed*: Utilize FW 8.33.1.0")
21dd79e82f00 ("qed*: HSI renaming for different types of HW")
a2e7699eb50f ("qed*: Refactoring and rearranging FW API with no functional impact")
ed468ebee04f ("qed: Add ll2 ability of opening a secondary queue")
d1abfd0b4ee2 ("qed: Add iWARP out of order support")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 1516ee035df32115197cd93ae3619dba7b020986 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali(a)marvell.com>
Date: Mon, 7 Aug 2023 15:07:25 +0530
Subject: [PATCH] scsi: qedi: Fix firmware halt over suspend and resume
While performing certain power-off sequences, PCI drivers are called to
suspend and resume their underlying devices through PCI PM (power
management) interface. However the hardware does not support PCI PM
suspend/resume operations so system wide suspend/resume leads to bad MFW
(management firmware) state which causes various follow-up errors in driver
when communicating with the device/firmware.
To fix this driver implements PCI PM suspend handler to indicate
unsupported operation to the PCI subsystem explicitly, thus avoiding system
to go into suspended/standby mode.
Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.")
Signed-off-by: Nilesh Javali <njavali(a)marvell.com>
Link: https://lore.kernel.org/r/20230807093725.46829-2-njavali@marvell.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 77a56a136678..cd0180b1f5b9 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -69,6 +69,7 @@ static struct nvm_iscsi_block *qedi_get_nvram_block(struct qedi_ctx *qedi);
static void qedi_recovery_handler(struct work_struct *work);
static void qedi_schedule_hw_err_handler(void *dev,
enum qed_hw_err_type err_type);
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state);
static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle)
{
@@ -2511,6 +2512,22 @@ static void qedi_shutdown(struct pci_dev *pdev)
__qedi_remove(pdev, QEDI_MODE_SHUTDOWN);
}
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct qedi_ctx *qedi;
+
+ if (!pdev) {
+ QEDI_ERR(NULL, "pdev is NULL.\n");
+ return -ENODEV;
+ }
+
+ qedi = pci_get_drvdata(pdev);
+
+ QEDI_ERR(&qedi->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+ return -EPERM;
+}
+
static int __qedi_probe(struct pci_dev *pdev, int mode)
{
struct qedi_ctx *qedi;
@@ -2869,6 +2886,7 @@ static struct pci_driver qedi_pci_driver = {
.remove = qedi_remove,
.shutdown = qedi_shutdown,
.err_handler = &qedi_err_handler,
+ .suspend = qedi_suspend,
};
static int __init qedi_init(void)
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 1516ee035df32115197cd93ae3619dba7b020986
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081336-cameo-challenge-c72b@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
1516ee035df3 ("scsi: qedi: Fix firmware halt over suspend and resume")
96a766a789eb ("scsi: qedi: Add support for handling PCIe errors")
f4ba4e55db6d ("scsi: qedi: Add firmware error recovery invocation support")
5c35e4646566 ("scsi: qedi: Skip firmware connection termination for PCI shutdown handler")
e4020e0835ed ("scsi: qedi: Remove 2 set but unused variables")
4f93c4bf0f74 ("scsi: qedi: Add PCI shutdown handler support")
4b1068f5d74b ("scsi: qedi: Add MFW error recovery process")
2bfbc570586e ("qedi: Use hwfns and affin_hwfn_idx to get MSI-X vector index")
13b99d3d3907 ("Revert "scsi: qedi: Allocate IRQs based on msix_cnt"")
dcceeeb71fb7 ("scsi: qedi: add module param to set ping packet size")
1a291bce5eaf ("scsi: qedi: Allocate IRQs based on msix_cnt")
3fb5a21fd008 ("scsi: qedi: Cleanup redundant QEDI_PAGE_SIZE macro definition")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 1516ee035df32115197cd93ae3619dba7b020986 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali(a)marvell.com>
Date: Mon, 7 Aug 2023 15:07:25 +0530
Subject: [PATCH] scsi: qedi: Fix firmware halt over suspend and resume
While performing certain power-off sequences, PCI drivers are called to
suspend and resume their underlying devices through PCI PM (power
management) interface. However the hardware does not support PCI PM
suspend/resume operations so system wide suspend/resume leads to bad MFW
(management firmware) state which causes various follow-up errors in driver
when communicating with the device/firmware.
To fix this driver implements PCI PM suspend handler to indicate
unsupported operation to the PCI subsystem explicitly, thus avoiding system
to go into suspended/standby mode.
Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.")
Signed-off-by: Nilesh Javali <njavali(a)marvell.com>
Link: https://lore.kernel.org/r/20230807093725.46829-2-njavali@marvell.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 77a56a136678..cd0180b1f5b9 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -69,6 +69,7 @@ static struct nvm_iscsi_block *qedi_get_nvram_block(struct qedi_ctx *qedi);
static void qedi_recovery_handler(struct work_struct *work);
static void qedi_schedule_hw_err_handler(void *dev,
enum qed_hw_err_type err_type);
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state);
static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle)
{
@@ -2511,6 +2512,22 @@ static void qedi_shutdown(struct pci_dev *pdev)
__qedi_remove(pdev, QEDI_MODE_SHUTDOWN);
}
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct qedi_ctx *qedi;
+
+ if (!pdev) {
+ QEDI_ERR(NULL, "pdev is NULL.\n");
+ return -ENODEV;
+ }
+
+ qedi = pci_get_drvdata(pdev);
+
+ QEDI_ERR(&qedi->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+ return -EPERM;
+}
+
static int __qedi_probe(struct pci_dev *pdev, int mode)
{
struct qedi_ctx *qedi;
@@ -2869,6 +2886,7 @@ static struct pci_driver qedi_pci_driver = {
.remove = qedi_remove,
.shutdown = qedi_shutdown,
.err_handler = &qedi_err_handler,
+ .suspend = qedi_suspend,
};
static int __init qedi_init(void)
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 1516ee035df32115197cd93ae3619dba7b020986
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081335-disperser-acting-9c76@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
1516ee035df3 ("scsi: qedi: Fix firmware halt over suspend and resume")
96a766a789eb ("scsi: qedi: Add support for handling PCIe errors")
f4ba4e55db6d ("scsi: qedi: Add firmware error recovery invocation support")
5c35e4646566 ("scsi: qedi: Skip firmware connection termination for PCI shutdown handler")
e4020e0835ed ("scsi: qedi: Remove 2 set but unused variables")
4f93c4bf0f74 ("scsi: qedi: Add PCI shutdown handler support")
4b1068f5d74b ("scsi: qedi: Add MFW error recovery process")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 1516ee035df32115197cd93ae3619dba7b020986 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali(a)marvell.com>
Date: Mon, 7 Aug 2023 15:07:25 +0530
Subject: [PATCH] scsi: qedi: Fix firmware halt over suspend and resume
While performing certain power-off sequences, PCI drivers are called to
suspend and resume their underlying devices through PCI PM (power
management) interface. However the hardware does not support PCI PM
suspend/resume operations so system wide suspend/resume leads to bad MFW
(management firmware) state which causes various follow-up errors in driver
when communicating with the device/firmware.
To fix this driver implements PCI PM suspend handler to indicate
unsupported operation to the PCI subsystem explicitly, thus avoiding system
to go into suspended/standby mode.
Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.")
Signed-off-by: Nilesh Javali <njavali(a)marvell.com>
Link: https://lore.kernel.org/r/20230807093725.46829-2-njavali@marvell.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 77a56a136678..cd0180b1f5b9 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -69,6 +69,7 @@ static struct nvm_iscsi_block *qedi_get_nvram_block(struct qedi_ctx *qedi);
static void qedi_recovery_handler(struct work_struct *work);
static void qedi_schedule_hw_err_handler(void *dev,
enum qed_hw_err_type err_type);
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state);
static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle)
{
@@ -2511,6 +2512,22 @@ static void qedi_shutdown(struct pci_dev *pdev)
__qedi_remove(pdev, QEDI_MODE_SHUTDOWN);
}
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct qedi_ctx *qedi;
+
+ if (!pdev) {
+ QEDI_ERR(NULL, "pdev is NULL.\n");
+ return -ENODEV;
+ }
+
+ qedi = pci_get_drvdata(pdev);
+
+ QEDI_ERR(&qedi->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+ return -EPERM;
+}
+
static int __qedi_probe(struct pci_dev *pdev, int mode)
{
struct qedi_ctx *qedi;
@@ -2869,6 +2886,7 @@ static struct pci_driver qedi_pci_driver = {
.remove = qedi_remove,
.shutdown = qedi_shutdown,
.err_handler = &qedi_err_handler,
+ .suspend = qedi_suspend,
};
static int __init qedi_init(void)
From: Ming Lei <ming.lei(a)redhat.com>
Move start_freeze into nvme_tcp_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Tested-by: Yi Zhang <yi.zhang(a)redhat.com>
Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me>
Signed-off-by: Keith Busch <kbusch(a)kernel.org>
---
drivers/nvme/host/tcp.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 96d8d7844e84..c2e037644ad1 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1882,6 +1882,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
goto out_cleanup_connect_q;
if (!new) {
+ nvme_start_freeze(ctrl);
nvme_start_queues(ctrl);
if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -1890,6 +1891,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -2008,7 +2010,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
if (ctrl->queue_count <= 1)
return;
blk_mq_quiesce_queue(ctrl->admin_q);
- nvme_start_freeze(ctrl);
nvme_stop_queues(ctrl);
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
--
2.41.0
From: Ming Lei <ming.lei(a)redhat.com>
Move start_freeze into nvme_tcp_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Tested-by: Yi Zhang <yi.zhang(a)redhat.com>
Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me>
Signed-off-by: Keith Busch <kbusch(a)kernel.org>
---
drivers/nvme/host/tcp.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 1dc7c733c7e3..8d67cdd844f5 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1884,6 +1884,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
goto out_cleanup_connect_q;
if (!new) {
+ nvme_start_freeze(ctrl);
nvme_start_queues(ctrl);
if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -1892,6 +1893,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -1996,7 +1998,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
if (ctrl->queue_count <= 1)
return;
nvme_stop_admin_queue(ctrl);
- nvme_start_freeze(ctrl);
nvme_stop_queues(ctrl);
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
--
2.41.0
From: Dominique Martinet <asmadeus(a)codewreck.org>
[ Upstream commit 4a73edab69d3a6623f03817fe950a2d9585f80e4 ]
Similarly to the previous patch: offs can be used in handle_rerrors
without initializing on small payloads; in this case handle_rerrors will
not use it because of the size check, but it doesn't hurt to make sure
it is zero to please scan-build.
This fixes the following warning:
net/9p/trans_virtio.c:539:3: warning: 3rd function call argument is an uninitialized value [core.CallAndMessage]
handle_rerror(req, in_hdr_len, offs, in_pages);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Reviewed-by: Simon Horman <simon.horman(a)corigine.com>
Signed-off-by: Dominique Martinet <asmadeus(a)codewreck.org>
Signed-off-by: Eric Van Hensbergen <ericvh(a)kernel.org>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
net/9p/trans_virtio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index f7cd8e018bde0..6b3357a77d992 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -409,7 +409,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
struct page **in_pages = NULL, **out_pages = NULL;
struct virtio_chan *chan = client->trans;
struct scatterlist *sgs[4];
- size_t offs;
+ size_t offs = 0;
int need_drop = 0;
int kicked = 0;
--
2.40.1
From: Dominique Martinet <asmadeus(a)codewreck.org>
[ Upstream commit 4a73edab69d3a6623f03817fe950a2d9585f80e4 ]
Similarly to the previous patch: offs can be used in handle_rerrors
without initializing on small payloads; in this case handle_rerrors will
not use it because of the size check, but it doesn't hurt to make sure
it is zero to please scan-build.
This fixes the following warning:
net/9p/trans_virtio.c:539:3: warning: 3rd function call argument is an uninitialized value [core.CallAndMessage]
handle_rerror(req, in_hdr_len, offs, in_pages);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Reviewed-by: Simon Horman <simon.horman(a)corigine.com>
Signed-off-by: Dominique Martinet <asmadeus(a)codewreck.org>
Signed-off-by: Eric Van Hensbergen <ericvh(a)kernel.org>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
net/9p/trans_virtio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index f582351d84ecb..36b5f72e2165c 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -394,7 +394,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
struct page **in_pages = NULL, **out_pages = NULL;
struct virtio_chan *chan = client->trans;
struct scatterlist *sgs[4];
- size_t offs;
+ size_t offs = 0;
int need_drop = 0;
int kicked = 0;
--
2.40.1
From: Adrien Thierry <athierry(a)redhat.com>
[ Upstream commit 45d89a344eb46db9dce851c28e14f5e3c635c251 ]
In the dwc3 core, both system and runtime suspend end up calling
dwc3_suspend_common(). From there, what happens for the PHYs depends on
the USB mode and whether the controller is entering system or runtime
suspend.
HOST mode:
(1) system suspend on a non-wakeup-capable controller
The [1] if branch is taken. dwc3_core_exit() is called, which ends up
calling phy_power_off() and phy_exit(). Those two functions decrease the
PM runtime count at some point, so they will trigger the PHY runtime
sleep (assuming the count is right).
(2) runtime suspend / system suspend on a wakeup-capable controller
The [1] branch is not taken. dwc3_suspend_common() calls
phy_pm_runtime_put_sync(). Assuming the ref count is right, the PHY
runtime suspend op is called.
DEVICE mode:
dwc3_core_exit() is called on both runtime and system sleep
unless the controller is already runtime suspended.
OTG mode:
(1) system suspend : dwc3_core_exit() is called
(2) runtime suspend : do nothing
In host mode, the code seems to make a distinction between 1) runtime
sleep / system sleep for wakeup-capable controller, and 2) system sleep
for non-wakeup-capable controller, where phy_power_off() and phy_exit()
are only called for the latter. This suggests the PHY is not supposed to
be in a fully powered-off state for runtime sleep and system sleep for
wakeup-capable controller.
Moreover, downstream, cfg_ahb_clk only gets disabled for system suspend.
The clocks are disabled by phy->set_suspend() [2] which is only called
in the system sleep path through dwc3_core_exit() [3].
With that in mind, don't disable the clocks during the femto PHY runtime
suspend callback. The clocks will only be disabled during system suspend
for non-wakeup-capable controllers, through dwc3_core_exit().
[1] https://elixir.bootlin.com/linux/v6.4/source/drivers/usb/dwc3/core.c#L1988
[2] https://git.codelinaro.org/clo/la/kernel/msm-5.4/-/blob/LV.AU.1.2.1.r2-0530…
[3] https://git.codelinaro.org/clo/la/kernel/msm-5.4/-/blob/LV.AU.1.2.1.r2-0530…
Signed-off-by: Adrien Thierry <athierry(a)redhat.com>
Link: https://lore.kernel.org/r/20230629144542.14906-2-athierry@redhat.com
Signed-off-by: Vinod Koul <vkoul(a)kernel.org>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c | 9 ---------
1 file changed, 9 deletions(-)
diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
index a590635962140..1d45029b19cd5 100644
--- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
+++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c
@@ -165,22 +165,13 @@ static int qcom_snps_hsphy_suspend(struct qcom_snps_hsphy *hsphy)
0, USB2_AUTO_RESUME);
}
- clk_disable_unprepare(hsphy->cfg_ahb_clk);
return 0;
}
static int qcom_snps_hsphy_resume(struct qcom_snps_hsphy *hsphy)
{
- int ret;
-
dev_dbg(&hsphy->phy->dev, "Resume QCOM SNPS PHY, mode\n");
- ret = clk_prepare_enable(hsphy->cfg_ahb_clk);
- if (ret) {
- dev_err(&hsphy->phy->dev, "failed to enable cfg ahb clock\n");
- return ret;
- }
-
return 0;
}
--
2.40.1
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 99dc264014d5aed66ee37ddf136a38b5a2b1b529
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081226-oak-cartoon-6115@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
99dc264014d5 ("nvme-tcp: fix potential unbalanced freeze & unfreeze")
9f27bd701d18 ("nvme: rename the queue quiescing helpers")
91c11d5f3254 ("nvme-rdma: stop auth work after tearing down queues in error recovery")
1f1a4f89562d ("nvme-tcp: stop auth work after tearing down queues in error recovery")
eac3ef262941 ("nvme-pci: split the initial probe from the rest path")
a6ee7f19ebfd ("nvme-pci: call nvme_pci_configure_admin_queue from nvme_pci_enable")
3f30a79c2e2c ("nvme-pci: set constant paramters in nvme_pci_alloc_ctrl")
2e87570be9d2 ("nvme-pci: factor out a nvme_pci_alloc_dev helper")
081a7d958ce4 ("nvme-pci: factor the iod mempool creation into a helper")
94cc781f69f4 ("nvme: move OPAL setup from PCIe to core")
cd50f9b24726 ("nvme: split nvme_kill_queues")
6bcd5089ee13 ("nvme: don't unquiesce the admin queue in nvme_kill_queues")
0ffc7e98bfaa ("nvme-pci: refactor the tagset handling in nvme_reset_work")
71b26083d59c ("block: set the disk capacity to 0 in blk_mark_disk_dead")
6dfba1c09c10 ("nvme-fc: use the tagset alloc/free helpers")
1864ea46155c ("nvme-fc: store the generic nvme_ctrl in set->driver_data")
cefa1032f111 ("nvme-rdma: use the tagset alloc/free helpers")
2d60738c8f80 ("nvme-rdma: store the generic nvme_ctrl in set->driver_data")
fe60e8c53411 ("nvme: add common helpers to allocate and free tagsets")
61ce339f19fa ("nvme-pci: set min_align_mask before calculating max_hw_sectors")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 99dc264014d5aed66ee37ddf136a38b5a2b1b529 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei(a)redhat.com>
Date: Tue, 11 Jul 2023 17:40:40 +0800
Subject: [PATCH] nvme-tcp: fix potential unbalanced freeze & unfreeze
Move start_freeze into nvme_tcp_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Tested-by: Yi Zhang <yi.zhang(a)redhat.com>
Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me>
Signed-off-by: Keith Busch <kbusch(a)kernel.org>
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 3e7dd6f91832..fb24cd8ac46c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1868,6 +1868,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
goto out_cleanup_connect_q;
if (!new) {
+ nvme_start_freeze(ctrl);
nvme_unquiesce_io_queues(ctrl);
if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -1876,6 +1877,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -1980,7 +1982,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
if (ctrl->queue_count <= 1)
return;
nvme_quiesce_admin_queue(ctrl);
- nvme_start_freeze(ctrl);
nvme_quiesce_io_queues(ctrl);
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 29b434d1e49252b3ad56ad3197e47fafff5356a1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081243-sleet-native-6d03@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
29b434d1e492 ("nvme-rdma: fix potential unbalanced freeze & unfreeze")
9f27bd701d18 ("nvme: rename the queue quiescing helpers")
91c11d5f3254 ("nvme-rdma: stop auth work after tearing down queues in error recovery")
1f1a4f89562d ("nvme-tcp: stop auth work after tearing down queues in error recovery")
eac3ef262941 ("nvme-pci: split the initial probe from the rest path")
a6ee7f19ebfd ("nvme-pci: call nvme_pci_configure_admin_queue from nvme_pci_enable")
3f30a79c2e2c ("nvme-pci: set constant paramters in nvme_pci_alloc_ctrl")
2e87570be9d2 ("nvme-pci: factor out a nvme_pci_alloc_dev helper")
081a7d958ce4 ("nvme-pci: factor the iod mempool creation into a helper")
94cc781f69f4 ("nvme: move OPAL setup from PCIe to core")
cd50f9b24726 ("nvme: split nvme_kill_queues")
6bcd5089ee13 ("nvme: don't unquiesce the admin queue in nvme_kill_queues")
0ffc7e98bfaa ("nvme-pci: refactor the tagset handling in nvme_reset_work")
71b26083d59c ("block: set the disk capacity to 0 in blk_mark_disk_dead")
6dfba1c09c10 ("nvme-fc: use the tagset alloc/free helpers")
1864ea46155c ("nvme-fc: store the generic nvme_ctrl in set->driver_data")
cefa1032f111 ("nvme-rdma: use the tagset alloc/free helpers")
2d60738c8f80 ("nvme-rdma: store the generic nvme_ctrl in set->driver_data")
fe60e8c53411 ("nvme: add common helpers to allocate and free tagsets")
61ce339f19fa ("nvme-pci: set min_align_mask before calculating max_hw_sectors")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 29b434d1e49252b3ad56ad3197e47fafff5356a1 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei(a)redhat.com>
Date: Tue, 11 Jul 2023 17:40:41 +0800
Subject: [PATCH] nvme-rdma: fix potential unbalanced freeze & unfreeze
Move start_freeze into nvme_rdma_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 9f98772ba307 ("nvme-rdma: fix controller reset hang during traffic")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Tested-by: Yi Zhang <yi.zhang(a)redhat.com>
Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me>
Signed-off-by: Keith Busch <kbusch(a)kernel.org>
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index d433b2ec07a6..337a624a537c 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -883,6 +883,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
goto out_cleanup_tagset;
if (!new) {
+ nvme_start_freeze(&ctrl->ctrl);
nvme_unquiesce_io_queues(&ctrl->ctrl);
if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -891,6 +892,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(&ctrl->ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
@@ -940,7 +942,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
if (ctrl->ctrl.queue_count > 1) {
- nvme_start_freeze(&ctrl->ctrl);
nvme_quiesce_io_queues(&ctrl->ctrl);
nvme_sync_io_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 29b434d1e49252b3ad56ad3197e47fafff5356a1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081242-sage-caddy-ebf9@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
29b434d1e492 ("nvme-rdma: fix potential unbalanced freeze & unfreeze")
9f27bd701d18 ("nvme: rename the queue quiescing helpers")
91c11d5f3254 ("nvme-rdma: stop auth work after tearing down queues in error recovery")
1f1a4f89562d ("nvme-tcp: stop auth work after tearing down queues in error recovery")
eac3ef262941 ("nvme-pci: split the initial probe from the rest path")
a6ee7f19ebfd ("nvme-pci: call nvme_pci_configure_admin_queue from nvme_pci_enable")
3f30a79c2e2c ("nvme-pci: set constant paramters in nvme_pci_alloc_ctrl")
2e87570be9d2 ("nvme-pci: factor out a nvme_pci_alloc_dev helper")
081a7d958ce4 ("nvme-pci: factor the iod mempool creation into a helper")
94cc781f69f4 ("nvme: move OPAL setup from PCIe to core")
cd50f9b24726 ("nvme: split nvme_kill_queues")
6bcd5089ee13 ("nvme: don't unquiesce the admin queue in nvme_kill_queues")
0ffc7e98bfaa ("nvme-pci: refactor the tagset handling in nvme_reset_work")
71b26083d59c ("block: set the disk capacity to 0 in blk_mark_disk_dead")
6dfba1c09c10 ("nvme-fc: use the tagset alloc/free helpers")
1864ea46155c ("nvme-fc: store the generic nvme_ctrl in set->driver_data")
cefa1032f111 ("nvme-rdma: use the tagset alloc/free helpers")
2d60738c8f80 ("nvme-rdma: store the generic nvme_ctrl in set->driver_data")
fe60e8c53411 ("nvme: add common helpers to allocate and free tagsets")
61ce339f19fa ("nvme-pci: set min_align_mask before calculating max_hw_sectors")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 29b434d1e49252b3ad56ad3197e47fafff5356a1 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei(a)redhat.com>
Date: Tue, 11 Jul 2023 17:40:41 +0800
Subject: [PATCH] nvme-rdma: fix potential unbalanced freeze & unfreeze
Move start_freeze into nvme_rdma_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 9f98772ba307 ("nvme-rdma: fix controller reset hang during traffic")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Tested-by: Yi Zhang <yi.zhang(a)redhat.com>
Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me>
Signed-off-by: Keith Busch <kbusch(a)kernel.org>
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index d433b2ec07a6..337a624a537c 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -883,6 +883,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
goto out_cleanup_tagset;
if (!new) {
+ nvme_start_freeze(&ctrl->ctrl);
nvme_unquiesce_io_queues(&ctrl->ctrl);
if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -891,6 +892,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(&ctrl->ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
@@ -940,7 +942,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
if (ctrl->ctrl.queue_count > 1) {
- nvme_start_freeze(&ctrl->ctrl);
nvme_quiesce_io_queues(&ctrl->ctrl);
nvme_sync_io_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 29b434d1e49252b3ad56ad3197e47fafff5356a1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081240-wharf-throwing-7cf7@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
29b434d1e492 ("nvme-rdma: fix potential unbalanced freeze & unfreeze")
9f27bd701d18 ("nvme: rename the queue quiescing helpers")
91c11d5f3254 ("nvme-rdma: stop auth work after tearing down queues in error recovery")
1f1a4f89562d ("nvme-tcp: stop auth work after tearing down queues in error recovery")
eac3ef262941 ("nvme-pci: split the initial probe from the rest path")
a6ee7f19ebfd ("nvme-pci: call nvme_pci_configure_admin_queue from nvme_pci_enable")
3f30a79c2e2c ("nvme-pci: set constant paramters in nvme_pci_alloc_ctrl")
2e87570be9d2 ("nvme-pci: factor out a nvme_pci_alloc_dev helper")
081a7d958ce4 ("nvme-pci: factor the iod mempool creation into a helper")
94cc781f69f4 ("nvme: move OPAL setup from PCIe to core")
cd50f9b24726 ("nvme: split nvme_kill_queues")
6bcd5089ee13 ("nvme: don't unquiesce the admin queue in nvme_kill_queues")
0ffc7e98bfaa ("nvme-pci: refactor the tagset handling in nvme_reset_work")
71b26083d59c ("block: set the disk capacity to 0 in blk_mark_disk_dead")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 29b434d1e49252b3ad56ad3197e47fafff5356a1 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei(a)redhat.com>
Date: Tue, 11 Jul 2023 17:40:41 +0800
Subject: [PATCH] nvme-rdma: fix potential unbalanced freeze & unfreeze
Move start_freeze into nvme_rdma_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 9f98772ba307 ("nvme-rdma: fix controller reset hang during traffic")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Tested-by: Yi Zhang <yi.zhang(a)redhat.com>
Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me>
Signed-off-by: Keith Busch <kbusch(a)kernel.org>
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index d433b2ec07a6..337a624a537c 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -883,6 +883,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
goto out_cleanup_tagset;
if (!new) {
+ nvme_start_freeze(&ctrl->ctrl);
nvme_unquiesce_io_queues(&ctrl->ctrl);
if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -891,6 +892,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(&ctrl->ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
@@ -940,7 +942,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
if (ctrl->ctrl.queue_count > 1) {
- nvme_start_freeze(&ctrl->ctrl);
nvme_quiesce_io_queues(&ctrl->ctrl);
nvme_sync_io_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 99dc264014d5aed66ee37ddf136a38b5a2b1b529
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081227-freeing-squeak-4a28@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
99dc264014d5 ("nvme-tcp: fix potential unbalanced freeze & unfreeze")
9f27bd701d18 ("nvme: rename the queue quiescing helpers")
91c11d5f3254 ("nvme-rdma: stop auth work after tearing down queues in error recovery")
1f1a4f89562d ("nvme-tcp: stop auth work after tearing down queues in error recovery")
eac3ef262941 ("nvme-pci: split the initial probe from the rest path")
a6ee7f19ebfd ("nvme-pci: call nvme_pci_configure_admin_queue from nvme_pci_enable")
3f30a79c2e2c ("nvme-pci: set constant paramters in nvme_pci_alloc_ctrl")
2e87570be9d2 ("nvme-pci: factor out a nvme_pci_alloc_dev helper")
081a7d958ce4 ("nvme-pci: factor the iod mempool creation into a helper")
94cc781f69f4 ("nvme: move OPAL setup from PCIe to core")
cd50f9b24726 ("nvme: split nvme_kill_queues")
6bcd5089ee13 ("nvme: don't unquiesce the admin queue in nvme_kill_queues")
0ffc7e98bfaa ("nvme-pci: refactor the tagset handling in nvme_reset_work")
71b26083d59c ("block: set the disk capacity to 0 in blk_mark_disk_dead")
6dfba1c09c10 ("nvme-fc: use the tagset alloc/free helpers")
1864ea46155c ("nvme-fc: store the generic nvme_ctrl in set->driver_data")
cefa1032f111 ("nvme-rdma: use the tagset alloc/free helpers")
2d60738c8f80 ("nvme-rdma: store the generic nvme_ctrl in set->driver_data")
fe60e8c53411 ("nvme: add common helpers to allocate and free tagsets")
61ce339f19fa ("nvme-pci: set min_align_mask before calculating max_hw_sectors")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 99dc264014d5aed66ee37ddf136a38b5a2b1b529 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei(a)redhat.com>
Date: Tue, 11 Jul 2023 17:40:40 +0800
Subject: [PATCH] nvme-tcp: fix potential unbalanced freeze & unfreeze
Move start_freeze into nvme_tcp_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Tested-by: Yi Zhang <yi.zhang(a)redhat.com>
Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me>
Signed-off-by: Keith Busch <kbusch(a)kernel.org>
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 3e7dd6f91832..fb24cd8ac46c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1868,6 +1868,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
goto out_cleanup_connect_q;
if (!new) {
+ nvme_start_freeze(ctrl);
nvme_unquiesce_io_queues(ctrl);
if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -1876,6 +1877,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -1980,7 +1982,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
if (ctrl->queue_count <= 1)
return;
nvme_quiesce_admin_queue(ctrl);
- nvme_start_freeze(ctrl);
nvme_quiesce_io_queues(ctrl);
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 99dc264014d5aed66ee37ddf136a38b5a2b1b529
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081225-impotence-uncurious-0ad9@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
99dc264014d5 ("nvme-tcp: fix potential unbalanced freeze & unfreeze")
9f27bd701d18 ("nvme: rename the queue quiescing helpers")
91c11d5f3254 ("nvme-rdma: stop auth work after tearing down queues in error recovery")
1f1a4f89562d ("nvme-tcp: stop auth work after tearing down queues in error recovery")
eac3ef262941 ("nvme-pci: split the initial probe from the rest path")
a6ee7f19ebfd ("nvme-pci: call nvme_pci_configure_admin_queue from nvme_pci_enable")
3f30a79c2e2c ("nvme-pci: set constant paramters in nvme_pci_alloc_ctrl")
2e87570be9d2 ("nvme-pci: factor out a nvme_pci_alloc_dev helper")
081a7d958ce4 ("nvme-pci: factor the iod mempool creation into a helper")
94cc781f69f4 ("nvme: move OPAL setup from PCIe to core")
cd50f9b24726 ("nvme: split nvme_kill_queues")
6bcd5089ee13 ("nvme: don't unquiesce the admin queue in nvme_kill_queues")
0ffc7e98bfaa ("nvme-pci: refactor the tagset handling in nvme_reset_work")
71b26083d59c ("block: set the disk capacity to 0 in blk_mark_disk_dead")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 99dc264014d5aed66ee37ddf136a38b5a2b1b529 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei(a)redhat.com>
Date: Tue, 11 Jul 2023 17:40:40 +0800
Subject: [PATCH] nvme-tcp: fix potential unbalanced freeze & unfreeze
Move start_freeze into nvme_tcp_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Tested-by: Yi Zhang <yi.zhang(a)redhat.com>
Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me>
Signed-off-by: Keith Busch <kbusch(a)kernel.org>
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 3e7dd6f91832..fb24cd8ac46c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1868,6 +1868,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
goto out_cleanup_connect_q;
if (!new) {
+ nvme_start_freeze(ctrl);
nvme_unquiesce_io_queues(ctrl);
if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -1876,6 +1877,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -1980,7 +1982,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
if (ctrl->queue_count <= 1)
return;
nvme_quiesce_admin_queue(ctrl);
- nvme_start_freeze(ctrl);
nvme_quiesce_io_queues(ctrl);
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
The lenovo-ymc driver is causing the keyboard + touchpad to stop working
on some regular laptop models such as the Lenovo ThinkBook 13s G2 ITL 20V9.
The problem is that there are YMC WMI GUID methods in the ACPI tables
of these laptops, despite them not being Yogas and lenovo-ymc loading
causes libinput to see a SW_TABLET_MODE switch with state 1.
This in turn causes libinput to ignore events from the builtin keyboard
and touchpad, since it filters those out for a Yoga in tablet mode.
Similar issues with false-positive SW_TABLET_MODE=1 reporting have
been seen with the intel-hid driver.
Copy the intel-hid driver approach to fix this and only bind to the WMI
device on machines where the DMI chassis-type indicates the machine
is a convertible.
Add a 'force' module parameter to allow overriding the chassis-type check
so that users can easily test if the YMC interface works on models which
report an unexpected chassis-type.
Fixes: e82882cdd241 ("platform/x86: Add driver for Yoga Tablet Mode switch")
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2229373
Cc: Gergo Koteles <soyer(a)irl.hu>
Cc: Andrew Kallmeyer <kallmeyeras(a)gmail.com>
Cc: André Apitzsch <git(a)apitzsch.eu>
Cc: stable(a)vger.kernel.org
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
---
Note: The chassis-type can be checked by doing:
cat /sys/class/dmi/id/chassis_type
if this reports 31 or 32 then this patch should not have any impact
on your machine.
---
drivers/platform/x86/lenovo-ymc.c | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/drivers/platform/x86/lenovo-ymc.c b/drivers/platform/x86/lenovo-ymc.c
index 41676188b373..f360370d5002 100644
--- a/drivers/platform/x86/lenovo-ymc.c
+++ b/drivers/platform/x86/lenovo-ymc.c
@@ -24,6 +24,10 @@ static bool ec_trigger __read_mostly;
module_param(ec_trigger, bool, 0444);
MODULE_PARM_DESC(ec_trigger, "Enable EC triggering work-around to force emitting tablet mode events");
+static bool force;
+module_param(force, bool, 0444);
+MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type");
+
static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = {
{
/* Lenovo Yoga 7 14ARB7 */
@@ -35,6 +39,20 @@ static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = {
{ }
};
+static const struct dmi_system_id allowed_chasis_types_dmi_table[] = {
+ {
+ .matches = {
+ DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "31" /* Convertible */),
+ },
+ },
+ {
+ .matches = {
+ DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "32" /* Detachable */),
+ },
+ },
+ { }
+};
+
struct lenovo_ymc_private {
struct input_dev *input_dev;
struct acpi_device *ec_acpi_dev;
@@ -111,6 +129,13 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx)
struct input_dev *input_dev;
int err;
+ if (!dmi_check_system(allowed_chasis_types_dmi_table)) {
+ if (force)
+ dev_info(&wdev->dev, "Force loading Lenovo YMC support\n");
+ else
+ return -ENODEV;
+ }
+
ec_trigger |= dmi_check_system(ec_trigger_quirk_dmi_table);
priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL);
--
2.41.0
From: Josef Bacik <josef(a)toxicpanda.com>
Recently we've been having mysterious hangs while running generic/475 on
the CI system. This turned out to be something like this:
Task 1
dmsetup suspend --nolockfs
-> __dm_suspend
-> dm_wait_for_completion
-> dm_wait_for_bios_completion
-> Unable to complete because of IO's on a plug in Task 2
Task 2
wb_workfn
-> wb_writeback
-> blk_start_plug
-> writeback_sb_inodes
-> Infinite loop unable to make an allocation
Task 3
cache_block_group
->read_extent_buffer_pages
->Waiting for IO to complete that can't be submitted because Task 1
suspended the DM device
The problem here is that we need Task 2 to be scheduled completely for
the blk plug to flush. Normally this would happen, we normally wait for
the block group caching to finish (Task 3), and this schedule would
result in the block plug flushing.
However if there's enough free space available from the current caching
to satisfy the allocation we won't actually wait for the caching to
complete. This check however just checks that we have enough space, not
that we can make the allocation. In this particular case we were trying
to allocate 9MiB, and we had 10MiB of free space, but we didn't have
9MiB of contiguous space to allocate, and thus the allocation failed and
we looped.
We specifically don't cycle through the FFE loop until we stop finding
cached block groups because we don't want to allocate new block groups
just because we're caching, so we short circuit the normal loop once we
hit LOOP_CACHING_WAIT and we found a caching block group.
This is normally fine, except in this particular case where the caching
thread can't make progress because the DM device has been suspended.
Fix this by not only waiting for free space to >= the amount of space we
want to allocate, but also that we make some progress in caching from
the time we start waiting. This will keep us from busy looping when the
caching is taking a while but still theoretically has enough space for
us to allocate from, and fixes this particular case by forcing us to
actually sleep and wait for forward progress, which will flush the plug.
With this fix we're no longer hanging with generic/475.
CC: stable(a)vger.kernel.org # 6.1+
Reviewed-by: Boris Burkov <boris(a)bur.io>
Signed-off-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: Luhao Liu <liuluhao0000(a)gmail.com>
---
fs/btrfs/block-group.c | 17 +++++++++++++++--
fs/btrfs/block-group.h | 2 ++
2 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 63c3b7172ba5..1e4b70f5280d 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -441,13 +441,23 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
u64 num_bytes)
{
struct btrfs_caching_control *caching_ctl;
+ int progress;
caching_ctl = btrfs_get_caching_control(cache);
if (!caching_ctl)
return;
+ /*
+ * We've already failed to allocate from this block group, so even if
+ * there's enough space in the block group it isn't contiguous enough to
+ * allow for an allocation, so wait for at least the next wakeup tick,
+ * or for the thing to be done.
+ */
+ progress = atomic_read(&caching_ctl->progress);
+
wait_event(caching_ctl->wait, btrfs_block_group_done(cache) ||
- (cache->free_space_ctl->free_space >= num_bytes));
+ (progress != atomic_read(&caching_ctl->progress) &&
+ (cache->free_space_ctl->free_space >= num_bytes)));
btrfs_put_caching_control(caching_ctl);
}
@@ -802,8 +812,10 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
if (total_found > CACHING_CTL_WAKE_UP) {
total_found = 0;
- if (wakeup)
+ if (wakeup) {
+ atomic_inc(&caching_ctl->progress);
wake_up(&caching_ctl->wait);
+ }
}
}
path->slots[0]++;
@@ -910,6 +922,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait)
init_waitqueue_head(&caching_ctl->wait);
caching_ctl->block_group = cache;
refcount_set(&caching_ctl->count, 2);
+ atomic_set(&caching_ctl->progress, 0);
btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
spin_lock(&cache->lock);
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index aba5dff66c19..74b61e663028 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -90,6 +90,8 @@ struct btrfs_caching_control {
wait_queue_head_t wait;
struct btrfs_work work;
struct btrfs_block_group *block_group;
+ /* Track progress of caching during allocation. */
+ atomic_t progress;
refcount_t count;
};
--
2.41.0
From: Hao Chen <chenhao418(a)huawei.com>
hns3_dbg_fill_content()/hclge_dbg_fill_content() is aim to integrate some
items to a string for content, and we add '\n' and '\0' in the last
two bytes of content.
strscpy() will add '\0' in the last byte of destination buffer(one of
items), it result in finishing content print ahead of schedule and some
dump content truncation.
One Error log shows as below:
cat mac_list/uc
UC MAC_LIST:
Expected:
UC MAC_LIST:
FUNC_ID MAC_ADDR STATE
pf 00:2b:19:05:03:00 ACTIVE
The destination buffer is length-bounded and not required to be
NUL-terminated, so just change strscpy() to memcpy() to fix it.
Fixes: 1cf3d5567f27 ("net: hns3: fix strncpy() not using dest-buf length as length issue")
Signed-off-by: Hao Chen <chenhao418(a)huawei.com>
Signed-off-by: Jijie Shao <shaojijie(a)huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 4 ++--
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 52546f625c8b..f276b5ecb431 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -464,9 +464,9 @@ static void hns3_dbg_fill_content(char *content, u16 len,
if (result) {
if (item_len < strlen(result[i]))
break;
- strscpy(pos, result[i], strlen(result[i]));
+ memcpy(pos, result[i], strlen(result[i]));
} else {
- strscpy(pos, items[i].name, strlen(items[i].name));
+ memcpy(pos, items[i].name, strlen(items[i].name));
}
pos += item_len;
len -= item_len;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 409db2e70965..0fb2eaee3e8a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -111,9 +111,9 @@ static void hclge_dbg_fill_content(char *content, u16 len,
if (result) {
if (item_len < strlen(result[i]))
break;
- strscpy(pos, result[i], strlen(result[i]));
+ memcpy(pos, result[i], strlen(result[i]));
} else {
- strscpy(pos, items[i].name, strlen(items[i].name));
+ memcpy(pos, items[i].name, strlen(items[i].name));
}
pos += item_len;
len -= item_len;
--
2.30.0
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 72dbde0f2afbe4af8e8595a89c650ae6b9d9c36f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081258-sturdy-retying-2572@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
72dbde0f2afb ("io_uring: correct check for O_TMPFILE")
0ffae640ad83 ("io_uring: always go async for unsupported open flags")
cd40cae29ef8 ("io_uring: split out open/close operations")
453b329be5ea ("io_uring: separate out file table handling code")
f4c163dd7d4b ("io_uring: split out fadvise/madvise operations")
0d5847274037 ("io_uring: split out fs related sync/fallocate functions")
531113bbd5bf ("io_uring: split out splice related operations")
11aeb71406dd ("io_uring: split out filesystem related operations")
e28683bdfc2f ("io_uring: move nop into its own file")
5e2a18d93fec ("io_uring: move xattr related opcodes to its own file")
97b388d70b53 ("io_uring: handle completions in the core")
de23077eda61 ("io_uring: set completion results upfront")
e27f928ee1cb ("io_uring: add io_uring_types.h")
4d4c9cff4f70 ("io_uring: define a request type cleanup handler")
890968dc0336 ("io_uring: unify struct io_symlink and io_hardlink")
9a3a11f977f9 ("io_uring: convert iouring_cmd to io_cmd_type")
ceb452e1b4ba ("io_uring: convert xattr to use io_cmd_type")
ea5af87d29cf ("io_uring: convert rsrc_update to io_cmd_type")
c1ee55950155 ("io_uring: convert msg and nop to io_cmd_type")
2511d3030c5e ("io_uring: convert splice to use io_cmd_type")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 72dbde0f2afbe4af8e8595a89c650ae6b9d9c36f Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar(a)cyphar.com>
Date: Mon, 7 Aug 2023 12:24:15 +1000
Subject: [PATCH] io_uring: correct check for O_TMPFILE
O_TMPFILE is actually __O_TMPFILE|O_DIRECTORY. This means that the old
check for whether RESOLVE_CACHED can be used would incorrectly think
that O_DIRECTORY could not be used with RESOLVE_CACHED.
Cc: stable(a)vger.kernel.org # v5.12+
Fixes: 3a81fd02045c ("io_uring: enable LOOKUP_CACHED path resolution for filename lookups")
Signed-off-by: Aleksa Sarai <cyphar(a)cyphar.com>
Link: https://lore.kernel.org/r/20230807-resolve_cached-o_tmpfile-v3-1-e49323e1ef…
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/io_uring/openclose.c b/io_uring/openclose.c
index 10ca57f5bd24..e3fae26e025d 100644
--- a/io_uring/openclose.c
+++ b/io_uring/openclose.c
@@ -35,9 +35,11 @@ static bool io_openat_force_async(struct io_open *open)
{
/*
* Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open,
- * it'll always -EAGAIN
+ * it'll always -EAGAIN. Note that we test for __O_TMPFILE because
+ * O_TMPFILE includes O_DIRECTORY, which isn't a flag we need to force
+ * async for.
*/
- return open->how.flags & (O_TRUNC | O_CREAT | O_TMPFILE);
+ return open->how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE);
}
static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 92fb94b69c6accf1e49fff699640fa0ce03dc910
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081201-unmoving-diameter-8fa3@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 92fb94b69c6accf1e49fff699640fa0ce03dc910 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef(a)toxicpanda.com>
Date: Wed, 2 Aug 2023 09:20:24 -0400
Subject: [PATCH] btrfs: set cache_block_group_error if we find an error
We set cache_block_group_error if btrfs_cache_block_group() returns an
error, this is because we could end up not finding space to allocate and
mistakenly return -ENOSPC, and which could then abort the transaction
with the incorrect errno, and in the case of ENOSPC result in a
WARN_ON() that will trip up tests like generic/475.
However there's the case where multiple threads can be racing, one
thread gets the proper error, and the other thread doesn't actually call
btrfs_cache_block_group(), it instead sees ->cached ==
BTRFS_CACHE_ERROR. Again the result is the same, we fail to allocate
our space and return -ENOSPC. Instead we need to set
cache_block_group_error to -EIO in this case to make sure that if we do
not make our allocation we get the appropriate error returned back to
the caller.
CC: stable(a)vger.kernel.org # 4.14+
Signed-off-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 911908ea5f6f..f396a9afa403 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4310,8 +4310,11 @@ static noinline int find_free_extent(struct btrfs_root *root,
ret = 0;
}
- if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
+ if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) {
+ if (!cache_block_group_error)
+ cache_block_group_error = -EIO;
goto loop;
+ }
if (!find_free_extent_check_size_class(ffe_ctl, block_group))
goto loop;
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 92fb94b69c6accf1e49fff699640fa0ce03dc910
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081259-hammock-private-d316@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 92fb94b69c6accf1e49fff699640fa0ce03dc910 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef(a)toxicpanda.com>
Date: Wed, 2 Aug 2023 09:20:24 -0400
Subject: [PATCH] btrfs: set cache_block_group_error if we find an error
We set cache_block_group_error if btrfs_cache_block_group() returns an
error, this is because we could end up not finding space to allocate and
mistakenly return -ENOSPC, and which could then abort the transaction
with the incorrect errno, and in the case of ENOSPC result in a
WARN_ON() that will trip up tests like generic/475.
However there's the case where multiple threads can be racing, one
thread gets the proper error, and the other thread doesn't actually call
btrfs_cache_block_group(), it instead sees ->cached ==
BTRFS_CACHE_ERROR. Again the result is the same, we fail to allocate
our space and return -ENOSPC. Instead we need to set
cache_block_group_error to -EIO in this case to make sure that if we do
not make our allocation we get the appropriate error returned back to
the caller.
CC: stable(a)vger.kernel.org # 4.14+
Signed-off-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 911908ea5f6f..f396a9afa403 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4310,8 +4310,11 @@ static noinline int find_free_extent(struct btrfs_root *root,
ret = 0;
}
- if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
+ if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) {
+ if (!cache_block_group_error)
+ cache_block_group_error = -EIO;
goto loop;
+ }
if (!find_free_extent_check_size_class(ffe_ctl, block_group))
goto loop;
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 5c25699871112853f231e52d51c576d5c759a020
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081248-stuffed-rematch-3c0b@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5c25699871112853f231e52d51c576d5c759a020 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch(a)lst.de>
Date: Mon, 24 Jul 2023 06:26:54 -0700
Subject: [PATCH] btrfs: don't wait for writeback on clean pages in
extent_write_cache_pages
__extent_writepage could have started on more pages than the one it was
called for. This happens regularly for zoned file systems, and in theory
could happen for compressed I/O if the worker thread was executed very
quickly. For such pages extent_write_cache_pages waits for writeback
to complete before moving on to the next page, which is highly inefficient
as it blocks the flusher thread.
Port over the PageDirty check that was added to write_cache_pages in
commit 515f4a037fb ("mm: write_cache_pages optimise page cleaning") to
fix this.
CC: stable(a)vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: Christoph Hellwig <hch(a)lst.de>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c36eb4956f81..ca765d62324f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2145,6 +2145,12 @@ static int extent_write_cache_pages(struct address_space *mapping,
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 5c25699871112853f231e52d51c576d5c759a020
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081247-fiddling-guise-6829@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5c25699871112853f231e52d51c576d5c759a020 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch(a)lst.de>
Date: Mon, 24 Jul 2023 06:26:54 -0700
Subject: [PATCH] btrfs: don't wait for writeback on clean pages in
extent_write_cache_pages
__extent_writepage could have started on more pages than the one it was
called for. This happens regularly for zoned file systems, and in theory
could happen for compressed I/O if the worker thread was executed very
quickly. For such pages extent_write_cache_pages waits for writeback
to complete before moving on to the next page, which is highly inefficient
as it blocks the flusher thread.
Port over the PageDirty check that was added to write_cache_pages in
commit 515f4a037fb ("mm: write_cache_pages optimise page cleaning") to
fix this.
CC: stable(a)vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: Christoph Hellwig <hch(a)lst.de>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c36eb4956f81..ca765d62324f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2145,6 +2145,12 @@ static int extent_write_cache_pages(struct address_space *mapping,
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 5c25699871112853f231e52d51c576d5c759a020
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081246-grandson-evasive-6acf@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5c25699871112853f231e52d51c576d5c759a020 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch(a)lst.de>
Date: Mon, 24 Jul 2023 06:26:54 -0700
Subject: [PATCH] btrfs: don't wait for writeback on clean pages in
extent_write_cache_pages
__extent_writepage could have started on more pages than the one it was
called for. This happens regularly for zoned file systems, and in theory
could happen for compressed I/O if the worker thread was executed very
quickly. For such pages extent_write_cache_pages waits for writeback
to complete before moving on to the next page, which is highly inefficient
as it blocks the flusher thread.
Port over the PageDirty check that was added to write_cache_pages in
commit 515f4a037fb ("mm: write_cache_pages optimise page cleaning") to
fix this.
CC: stable(a)vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: Christoph Hellwig <hch(a)lst.de>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c36eb4956f81..ca765d62324f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2145,6 +2145,12 @@ static int extent_write_cache_pages(struct address_space *mapping,
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 5c25699871112853f231e52d51c576d5c759a020
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081245-skyline-foster-b420@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5c25699871112853f231e52d51c576d5c759a020 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch(a)lst.de>
Date: Mon, 24 Jul 2023 06:26:54 -0700
Subject: [PATCH] btrfs: don't wait for writeback on clean pages in
extent_write_cache_pages
__extent_writepage could have started on more pages than the one it was
called for. This happens regularly for zoned file systems, and in theory
could happen for compressed I/O if the worker thread was executed very
quickly. For such pages extent_write_cache_pages waits for writeback
to complete before moving on to the next page, which is highly inefficient
as it blocks the flusher thread.
Port over the PageDirty check that was added to write_cache_pages in
commit 515f4a037fb ("mm: write_cache_pages optimise page cleaning") to
fix this.
CC: stable(a)vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: Christoph Hellwig <hch(a)lst.de>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c36eb4956f81..ca765d62324f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2145,6 +2145,12 @@ static int extent_write_cache_pages(struct address_space *mapping,
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 5c25699871112853f231e52d51c576d5c759a020
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081244-snagged-daylight-c23f@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5c25699871112853f231e52d51c576d5c759a020 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch(a)lst.de>
Date: Mon, 24 Jul 2023 06:26:54 -0700
Subject: [PATCH] btrfs: don't wait for writeback on clean pages in
extent_write_cache_pages
__extent_writepage could have started on more pages than the one it was
called for. This happens regularly for zoned file systems, and in theory
could happen for compressed I/O if the worker thread was executed very
quickly. For such pages extent_write_cache_pages waits for writeback
to complete before moving on to the next page, which is highly inefficient
as it blocks the flusher thread.
Port over the PageDirty check that was added to write_cache_pages in
commit 515f4a037fb ("mm: write_cache_pages optimise page cleaning") to
fix this.
CC: stable(a)vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: Christoph Hellwig <hch(a)lst.de>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c36eb4956f81..ca765d62324f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2145,6 +2145,12 @@ static int extent_write_cache_pages(struct address_space *mapping,
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 5c25699871112853f231e52d51c576d5c759a020
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023081243-resolute-juggle-2b21@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5c25699871112853f231e52d51c576d5c759a020 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch(a)lst.de>
Date: Mon, 24 Jul 2023 06:26:54 -0700
Subject: [PATCH] btrfs: don't wait for writeback on clean pages in
extent_write_cache_pages
__extent_writepage could have started on more pages than the one it was
called for. This happens regularly for zoned file systems, and in theory
could happen for compressed I/O if the worker thread was executed very
quickly. For such pages extent_write_cache_pages waits for writeback
to complete before moving on to the next page, which is highly inefficient
as it blocks the flusher thread.
Port over the PageDirty check that was added to write_cache_pages in
commit 515f4a037fb ("mm: write_cache_pages optimise page cleaning") to
fix this.
CC: stable(a)vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef(a)toxicpanda.com>
Signed-off-by: Christoph Hellwig <hch(a)lst.de>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c36eb4956f81..ca765d62324f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2145,6 +2145,12 @@ static int extent_write_cache_pages(struct address_space *mapping,
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);