From: Kory Maincent <kory.maincent(a)bootlin.com>
A bitset without mask in a _SET request means we want exactly the bits in
the bitset to be set. This works correctly for compact format but when
verbose format is parsed, ethnl_update_bitset32_verbose() only sets the
bits present in the request bitset but does not clear the rest. The commit
6699170376ab fixes this issue by clearing the whole target bitmap before we
start iterating. The solution proposed brought an issue with the behavior
of the mod variable. As the bitset is always cleared the old val will
always differ to the new val.
Fix it by adding a new temporary variable which save the state of the old
bitmap.
Fixes: 6699170376ab ("ethtool: fix application of verbose no_mask bitset")
Signed-off-by: Kory Maincent <kory.maincent(a)bootlin.com>
Cc: stable(a)vger.kernel.org
---
net/ethtool/bitset.c | 25 +++++++++++++++++++------
1 file changed, 19 insertions(+), 6 deletions(-)
diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c
index 0515d6604b3b..95f11b0a38b4 100644
--- a/net/ethtool/bitset.c
+++ b/net/ethtool/bitset.c
@@ -432,7 +432,9 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
struct netlink_ext_ack *extack, bool *mod)
{
struct nlattr *bit_attr;
+ u32 *tmp = NULL;
bool no_mask;
+ bool dummy;
int rem;
int ret;
@@ -448,8 +450,11 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
}
no_mask = tb[ETHTOOL_A_BITSET_NOMASK];
- if (no_mask)
- ethnl_bitmap32_clear(bitmap, 0, nbits, mod);
+ if (no_mask) {
+ tmp = kcalloc(nbits, sizeof(u32), GFP_KERNEL);
+ memcpy(tmp, bitmap, nbits);
+ ethnl_bitmap32_clear(bitmap, 0, nbits, &dummy);
+ }
nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) {
bool old_val, new_val;
@@ -458,13 +463,18 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
if (nla_type(bit_attr) != ETHTOOL_A_BITSET_BITS_BIT) {
NL_SET_ERR_MSG_ATTR(extack, bit_attr,
"only ETHTOOL_A_BITSET_BITS_BIT allowed in ETHTOOL_A_BITSET_BITS");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
ret = ethnl_parse_bit(&idx, &new_val, nbits, bit_attr, no_mask,
names, extack);
if (ret < 0)
- return ret;
- old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32));
+ goto out;
+ if (no_mask)
+ old_val = tmp[idx / 32] & ((u32)1 << (idx % 32));
+ else
+ old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32));
+
if (new_val != old_val) {
if (new_val)
bitmap[idx / 32] |= ((u32)1 << (idx % 32));
@@ -474,7 +484,10 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
}
}
- return 0;
+ ret = 0;
+out:
+ kfree(tmp);
+ return ret;
}
static int ethnl_compact_sanity_checks(unsigned int nbits,
--
2.25.1
While searching for possible refactor of napi_schedule_prep and
__napi_schedule it was notice that the mtk eth driver disable the
interrupt for rx and tx AFTER napi is scheduled.
While this is a very hard to repro case it might happen to have
situation where the interrupt is disabled and never enabled again as the
napi completes and the interrupt is enabled before.
This is caused by the fact that a napi driven by interrupt expect a
logic with:
1. interrupt received. napi prepared -> interrupt disabled -> napi
scheduled
2. napi triggered. ring cleared -> interrupt enabled -> wait for new
interrupt
To prevent this case, disable the interrupt BEFORE the napi is
scheduled.
Fixes: 656e705243fd ("net-next: mediatek: add support for MT7623 ethernet")
Cc: stable(a)vger.kernel.org
Signed-off-by: Christian Marangi <ansuelsmth(a)gmail.com>
---
drivers/net/ethernet/mediatek/mtk_eth_soc.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 82b51072aad8..7669b446915a 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -3172,8 +3172,8 @@ static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth)
eth->rx_events++;
if (likely(napi_schedule_prep(ð->rx_napi))) {
- __napi_schedule(ð->rx_napi);
mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask);
+ __napi_schedule(ð->rx_napi);
}
return IRQ_HANDLED;
@@ -3185,8 +3185,8 @@ static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth)
eth->tx_events++;
if (likely(napi_schedule_prep(ð->tx_napi))) {
- __napi_schedule(ð->tx_napi);
mtk_tx_irq_disable(eth, MTK_TX_DONE_INT);
+ __napi_schedule(ð->tx_napi);
}
return IRQ_HANDLED;
--
2.40.1
From: Miquel Raynal <miquel.raynal(a)bootlin.com>
Upstream commit 717c6ec241b5 ("can: sja1000: Prevent overrun stalls with
a soft reset on Renesas SoCs") fixes an issue with Renesas own SJA1000
CAN controller reception: the Rx buffer is only 5 messages long, so when
the bus loaded (eg. a message every 50us), overrun may easily
happen. Upon an overrun situation, due to a possible internal crosstalk
situation, the controller enters a frozen state which only can be
unlocked with a soft reset (experimentally). The solution was to offload
a call to sja1000_start() in a threaded handler. This needs to happen in
process context as this operation requires to sleep. sja1000_start()
basically enters "reset mode", performs a proper software reset and
returns back into "normal mode".
Since this fix was introduced, we no longer observe any stalls in
reception. However it was sporadically observed that the transmit path
would now freeze. Further investigation blamed the fix mentioned above,
and especially the reset operation. Reproducing the reset in a loop
helped identifying what could possibly go wrong. The sja1000 is a single
Tx queue device, which leverages the netdev helpers to process one Tx
message at a time. The logic is: the queue is stopped, the message sent
to the transceiver, once properly transmitted the controller sets a
status bit which triggers an interrupt, in the interrupt handler the
transmission status is checked and the queue woken up. Unfortunately, if
an overrun happens, we might perform the soft reset precisely between
the transmission of the buffer to the transceiver and the advent of the
transmission status bit. We would then stop the transmission operation
without re-enabling the queue, leading to all further transmissions to
be ignored.
The reset interrupt can only happen while the device is "open", and
after a reset we anyway want to resume normal operations, no matter if a
packet to transmit got dropped in the process, so we shall wake up the
queue. Restarting the device and waking-up the queue is exactly what
sja1000_set_mode(CAN_MODE_START) does. In order to be consistent about
the queue state, we must acquire a lock both in the reset handler and in
the transmit path to ensure serialization of both operations. It turns
out, a lock is already held when entering the transmit path, so we can
just acquire/release it as well with the regular net helpers inside the
threaded interrupt handler and this way we should be safe. As the
reset handler might still be called after the transmission of a frame to
the transceiver but before it actually gets transmitted, we must ensure
we don't leak the skb, so we free it (the behavior is consistent, no
matter if there was an skb on the stack or not).
Fixes: 717c6ec241b5 ("can: sja1000: Prevent overrun stalls with a soft reset on Renesas SoCs")
Cc: stable(a)vger.kernel.org
Signed-off-by: Miquel Raynal <miquel.raynal(a)bootlin.com>
Link: https://lore.kernel.org/all/20231002160206.190953-1-miquel.raynal@bootlin.c…
[mkl: fixed call to can_free_echo_skb()]
Signed-off-by: Marc Kleine-Budde <mkl(a)pengutronix.de>
---
drivers/net/can/sja1000/sja1000.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 0ada0e160e93..743c2eb62b87 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -392,7 +392,13 @@ static irqreturn_t sja1000_reset_interrupt(int irq, void *dev_id)
struct net_device *dev = (struct net_device *)dev_id;
netdev_dbg(dev, "performing a soft reset upon overrun\n");
- sja1000_start(dev);
+
+ netif_tx_lock(dev);
+
+ can_free_echo_skb(dev, 0, NULL);
+ sja1000_set_mode(dev, CAN_MODE_START);
+
+ netif_tx_unlock(dev);
return IRQ_HANDLED;
}
--
2.40.1
Fix three issues with resctrl selftests.
The signal handling fix became necessary after the mount/umount fixes.
The other two came up when I ran resctrl selftests across the server
fleet in our lab to validate the upcoming CAT test rewrite (the rewrite
is not part of this series).
These are developed and should apply cleanly at least on top the
benchmark cleanup series (might apply cleanly also w/o the benchmark
series, I didn't test).
v2:
- Include patch to move _GNU_SOURCE to Makefile to allow normal #include
placement
- Rework the signal register/unregister into patch to use helpers
- Fixed incorrect function parameter description
- Use return !!res to avoid confusing implicit boolean conversion
- Improve MBA/MBM success bound patch's changelog
- Tweak Cc: stable dependencies (make it a chain).
Ilpo Järvinen (6):
selftests/resctrl: Extend signal handler coverage to unmount on
receiving signal
selftests/resctrl: Remove duplicate feature check from CMT test
selftests/resctrl: Move _GNU_SOURCE define into Makefile
selftests/resctrl: Refactor feature check to use resource and feature
name
selftests/resctrl: Fix feature checks
selftests/resctrl: Reduce failures due to outliers in MBA/MBM tests
tools/testing/selftests/resctrl/Makefile | 2 +-
tools/testing/selftests/resctrl/cat_test.c | 8 --
tools/testing/selftests/resctrl/cmt_test.c | 3 -
tools/testing/selftests/resctrl/mba_test.c | 2 +-
tools/testing/selftests/resctrl/mbm_test.c | 2 +-
tools/testing/selftests/resctrl/resctrl.h | 7 +-
.../testing/selftests/resctrl/resctrl_tests.c | 78 +++++++++++--------
tools/testing/selftests/resctrl/resctrl_val.c | 22 +++---
tools/testing/selftests/resctrl/resctrlfs.c | 69 +++++++---------
9 files changed, 88 insertions(+), 105 deletions(-)
--
2.30.2
The patch below does not apply to the 6.5-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-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x 8b4d9469d0b0e553208ee6f62f2807111fde18b9
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100443-freewill-shanty-0f05@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 8b4d9469d0b0e553208ee6f62f2807111fde18b9 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal(a)kernel.org>
Date: Tue, 5 Sep 2023 09:06:23 +0900
Subject: [PATCH] ata: libata-scsi: Fix delayed scsi_rescan_device() execution
Commit 6aa0365a3c85 ("ata: libata-scsi: Avoid deadlock on rescan after
device resume") modified ata_scsi_dev_rescan() to check the scsi device
"is_suspended" power field to ensure that the scsi device associated
with an ATA device is fully resumed when scsi_rescan_device() is
executed. However, this fix is problematic as:
1) It relies on a PM internal field that should not be used without PM
device locking protection.
2) The check for is_suspended and the call to scsi_rescan_device() are
not atomic and a suspend PM event may be triggered between them,
casuing scsi_rescan_device() to be called on a suspended device and
in that function blocking while holding the scsi device lock. This
would deadlock a following resume operation.
These problems can trigger PM deadlocks on resume, especially with
resume operations triggered quickly after or during suspend operations.
E.g., a simple bash script like:
for (( i=0; i<10; i++ )); do
echo "+2 > /sys/class/rtc/rtc0/wakealarm
echo mem > /sys/power/state
done
that triggers a resume 2 seconds after starting suspending a system can
quickly lead to a PM deadlock preventing the system from correctly
resuming.
Fix this by replacing the check on is_suspended with a check on the
return value given by scsi_rescan_device() as that function will fail if
called against a suspended device. Also make sure rescan tasks already
scheduled are first cancelled before suspending an ata port.
Fixes: 6aa0365a3c85 ("ata: libata-scsi: Avoid deadlock on rescan after device resume")
Cc: stable(a)vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal(a)kernel.org>
Reviewed-by: Hannes Reinecke <hare(a)suse.de>
Reviewed-by: Niklas Cassel <niklas.cassel(a)wdc.com>
Tested-by: Geert Uytterhoeven <geert+renesas(a)glider.be>
Reviewed-by: Martin K. Petersen <martin.petersen(a)oracle.com>
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index a0bc01606b30..092372334e92 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -5168,11 +5168,27 @@ static const unsigned int ata_port_suspend_ehi = ATA_EHI_QUIET
static void ata_port_suspend(struct ata_port *ap, pm_message_t mesg)
{
+ /*
+ * We are about to suspend the port, so we do not care about
+ * scsi_rescan_device() calls scheduled by previous resume operations.
+ * The next resume will schedule the rescan again. So cancel any rescan
+ * that is not done yet.
+ */
+ cancel_delayed_work_sync(&ap->scsi_rescan_task);
+
ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, false);
}
static void ata_port_suspend_async(struct ata_port *ap, pm_message_t mesg)
{
+ /*
+ * We are about to suspend the port, so we do not care about
+ * scsi_rescan_device() calls scheduled by previous resume operations.
+ * The next resume will schedule the rescan again. So cancel any rescan
+ * that is not done yet.
+ */
+ cancel_delayed_work_sync(&ap->scsi_rescan_task);
+
ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, true);
}
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index a0e58d22d222..6850cac803c1 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -4756,7 +4756,7 @@ void ata_scsi_dev_rescan(struct work_struct *work)
struct ata_link *link;
struct ata_device *dev;
unsigned long flags;
- bool delay_rescan = false;
+ int ret = 0;
mutex_lock(&ap->scsi_scan_mutex);
spin_lock_irqsave(ap->lock, flags);
@@ -4765,37 +4765,34 @@ void ata_scsi_dev_rescan(struct work_struct *work)
ata_for_each_dev(dev, link, ENABLED) {
struct scsi_device *sdev = dev->sdev;
+ /*
+ * If the port was suspended before this was scheduled,
+ * bail out.
+ */
+ if (ap->pflags & ATA_PFLAG_SUSPENDED)
+ goto unlock;
+
if (!sdev)
continue;
if (scsi_device_get(sdev))
continue;
- /*
- * If the rescan work was scheduled because of a resume
- * event, the port is already fully resumed, but the
- * SCSI device may not yet be fully resumed. In such
- * case, executing scsi_rescan_device() may cause a
- * deadlock with the PM code on device_lock(). Prevent
- * this by giving up and retrying rescan after a short
- * delay.
- */
- delay_rescan = sdev->sdev_gendev.power.is_suspended;
- if (delay_rescan) {
- scsi_device_put(sdev);
- break;
- }
-
spin_unlock_irqrestore(ap->lock, flags);
- scsi_rescan_device(sdev);
+ ret = scsi_rescan_device(sdev);
scsi_device_put(sdev);
spin_lock_irqsave(ap->lock, flags);
+
+ if (ret)
+ goto unlock;
}
}
+unlock:
spin_unlock_irqrestore(ap->lock, flags);
mutex_unlock(&ap->scsi_scan_mutex);
- if (delay_rescan)
+ /* Reschedule with a delay if scsi_rescan_device() returned an error */
+ if (ret)
schedule_delayed_work(&ap->scsi_rescan_task,
msecs_to_jiffies(5));
}
The patch below does not apply to the 6.5-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-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x ff48b37802e5c134e2dfc4d091f10b2eb5065a72
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100454-hamper-falsify-595d@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ff48b37802e5c134e2dfc4d091f10b2eb5065a72 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal(a)kernel.org>
Date: Fri, 15 Sep 2023 15:00:13 +0900
Subject: [PATCH] scsi: Do not attempt to rescan suspended devices
scsi_rescan_device() takes a scsi device lock before executing a device
handler and device driver rescan methods. Waiting for the completion of
any command issued to the device by these methods will thus be done with
the device lock held. As a result, there is a risk of deadlocking within
the power management code if scsi_rescan_device() is called to handle a
device resume with the associated scsi device not yet resumed.
Avoid such situation by checking that the target scsi device is in the
running state, that is, fully capable of executing commands, before
proceeding with the rescan and bailout returning -EWOULDBLOCK otherwise.
With this error return, the caller can retry rescaning the device after
a delay.
The state check is done with the device lock held and is thus safe
against incoming suspend power management operations.
Fixes: 6aa0365a3c85 ("ata: libata-scsi: Avoid deadlock on rescan after device resume")
Cc: stable(a)vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal(a)kernel.org>
Reviewed-by: Hannes Reinecke <hare(a)suse.de>
Reviewed-by: Niklas Cassel <niklas.cassel(a)wdc.com>
Tested-by: Geert Uytterhoeven <geert+renesas(a)glider.be>
Reviewed-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Reviewed-by: Bart Van Assche <bvanassche(a)acm.org>
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 52014b2d39e1..3db4d31a03a1 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -1619,12 +1619,24 @@ int scsi_add_device(struct Scsi_Host *host, uint channel,
}
EXPORT_SYMBOL(scsi_add_device);
-void scsi_rescan_device(struct scsi_device *sdev)
+int scsi_rescan_device(struct scsi_device *sdev)
{
struct device *dev = &sdev->sdev_gendev;
+ int ret = 0;
device_lock(dev);
+ /*
+ * Bail out if the device is not running. Otherwise, the rescan may
+ * block waiting for commands to be executed, with us holding the
+ * device lock. This can result in a potential deadlock in the power
+ * management core code when system resume is on-going.
+ */
+ if (sdev->sdev_state != SDEV_RUNNING) {
+ ret = -EWOULDBLOCK;
+ goto unlock;
+ }
+
scsi_attach_vpd(sdev);
scsi_cdl_check(sdev);
@@ -1638,7 +1650,11 @@ void scsi_rescan_device(struct scsi_device *sdev)
drv->rescan(dev);
module_put(dev->driver->owner);
}
+
+unlock:
device_unlock(dev);
+
+ return ret;
}
EXPORT_SYMBOL(scsi_rescan_device);
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 49f768d0ff37..4c2dc8150c6d 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -764,7 +764,7 @@ scsi_template_proc_dir(const struct scsi_host_template *sht);
#define scsi_template_proc_dir(sht) NULL
#endif
extern void scsi_scan_host(struct Scsi_Host *);
-extern void scsi_rescan_device(struct scsi_device *);
+extern int scsi_rescan_device(struct scsi_device *sdev);
extern void scsi_remove_host(struct Scsi_Host *);
extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *);
extern int scsi_host_busy(struct Scsi_Host *shost);