From: Justin Tee <justin.tee(a)broadcom.com>
[ Upstream commit bb011631435c705cdeddca68d5c85fd40a4320f9 ]
Typically when an out of resource CQE status is detected, the
lpfc_ramp_down_queue_handler() logic is called to help reduce I/O load by
reducing an sdev's queue_depth.
However, the current lpfc_rampdown_queue_depth() logic does not help reduce
queue_depth. num_cmd_success is never updated and is always zero, which
means new_queue_depth will always be set to sdev->queue_depth. So,
new_queue_depth = sdev->queue_depth - new_queue_depth always sets
new_queue_depth to zero. And, scsi_change_queue_depth(sdev, 0) is
essentially a no-op.
Change the lpfc_ramp_down_queue_handler() logic to set new_queue_depth
equal to sdev->queue_depth subtracted from number of times num_rsrc_err was
incremented. If num_rsrc_err is >= sdev->queue_depth, then set
new_queue_depth equal to 1. Eventually, the frequency of Good_Status
frames will signal SCSI upper layer to auto increase the queue_depth back
to the driver default of 64 via scsi_handle_queue_ramp_up().
Signed-off-by: Justin Tee <justin.tee(a)broadcom.com>
Link: https://lore.kernel.org/r/20240305200503.57317-5-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/scsi/lpfc/lpfc.h | 1 -
drivers/scsi/lpfc/lpfc_scsi.c | 13 ++++---------
2 files changed, 4 insertions(+), 10 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 53b661793268f..5698928d8029c 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -989,7 +989,6 @@ struct lpfc_hba {
unsigned long bit_flags;
#define FABRIC_COMANDS_BLOCKED 0
atomic_t num_rsrc_err;
- atomic_t num_cmd_success;
unsigned long last_rsrc_error_time;
unsigned long last_ramp_down_time;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 425b83618a2e5..02d067e1fc45c 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -303,11 +303,10 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
struct Scsi_Host *shost;
struct scsi_device *sdev;
unsigned long new_queue_depth;
- unsigned long num_rsrc_err, num_cmd_success;
+ unsigned long num_rsrc_err;
int i;
num_rsrc_err = atomic_read(&phba->num_rsrc_err);
- num_cmd_success = atomic_read(&phba->num_cmd_success);
/*
* The error and success command counters are global per
@@ -322,20 +321,16 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
shost = lpfc_shost_from_vport(vports[i]);
shost_for_each_device(sdev, shost) {
- new_queue_depth =
- sdev->queue_depth * num_rsrc_err /
- (num_rsrc_err + num_cmd_success);
- if (!new_queue_depth)
- new_queue_depth = sdev->queue_depth - 1;
+ if (num_rsrc_err >= sdev->queue_depth)
+ new_queue_depth = 1;
else
new_queue_depth = sdev->queue_depth -
- new_queue_depth;
+ num_rsrc_err;
scsi_change_queue_depth(sdev, new_queue_depth);
}
}
lpfc_destroy_vport_work_array(phba, vports);
atomic_set(&phba->num_rsrc_err, 0);
- atomic_set(&phba->num_cmd_success, 0);
}
/**
--
2.43.0
From: Justin Tee <justin.tee(a)broadcom.com>
[ Upstream commit bb011631435c705cdeddca68d5c85fd40a4320f9 ]
Typically when an out of resource CQE status is detected, the
lpfc_ramp_down_queue_handler() logic is called to help reduce I/O load by
reducing an sdev's queue_depth.
However, the current lpfc_rampdown_queue_depth() logic does not help reduce
queue_depth. num_cmd_success is never updated and is always zero, which
means new_queue_depth will always be set to sdev->queue_depth. So,
new_queue_depth = sdev->queue_depth - new_queue_depth always sets
new_queue_depth to zero. And, scsi_change_queue_depth(sdev, 0) is
essentially a no-op.
Change the lpfc_ramp_down_queue_handler() logic to set new_queue_depth
equal to sdev->queue_depth subtracted from number of times num_rsrc_err was
incremented. If num_rsrc_err is >= sdev->queue_depth, then set
new_queue_depth equal to 1. Eventually, the frequency of Good_Status
frames will signal SCSI upper layer to auto increase the queue_depth back
to the driver default of 64 via scsi_handle_queue_ramp_up().
Signed-off-by: Justin Tee <justin.tee(a)broadcom.com>
Link: https://lore.kernel.org/r/20240305200503.57317-5-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/scsi/lpfc/lpfc.h | 1 -
drivers/scsi/lpfc/lpfc_scsi.c | 13 ++++---------
2 files changed, 4 insertions(+), 10 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 7ce0d94cdc018..98ab07c3774ed 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -1039,7 +1039,6 @@ struct lpfc_hba {
unsigned long bit_flags;
#define FABRIC_COMANDS_BLOCKED 0
atomic_t num_rsrc_err;
- atomic_t num_cmd_success;
unsigned long last_rsrc_error_time;
unsigned long last_ramp_down_time;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 816235ccd2992..f238e0f41f07c 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -246,11 +246,10 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
struct Scsi_Host *shost;
struct scsi_device *sdev;
unsigned long new_queue_depth;
- unsigned long num_rsrc_err, num_cmd_success;
+ unsigned long num_rsrc_err;
int i;
num_rsrc_err = atomic_read(&phba->num_rsrc_err);
- num_cmd_success = atomic_read(&phba->num_cmd_success);
/*
* The error and success command counters are global per
@@ -265,20 +264,16 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
shost = lpfc_shost_from_vport(vports[i]);
shost_for_each_device(sdev, shost) {
- new_queue_depth =
- sdev->queue_depth * num_rsrc_err /
- (num_rsrc_err + num_cmd_success);
- if (!new_queue_depth)
- new_queue_depth = sdev->queue_depth - 1;
+ if (num_rsrc_err >= sdev->queue_depth)
+ new_queue_depth = 1;
else
new_queue_depth = sdev->queue_depth -
- new_queue_depth;
+ num_rsrc_err;
scsi_change_queue_depth(sdev, new_queue_depth);
}
}
lpfc_destroy_vport_work_array(phba, vports);
atomic_set(&phba->num_rsrc_err, 0);
- atomic_set(&phba->num_cmd_success, 0);
}
/**
--
2.43.0
From: Justin Tee <justin.tee(a)broadcom.com>
[ Upstream commit bb011631435c705cdeddca68d5c85fd40a4320f9 ]
Typically when an out of resource CQE status is detected, the
lpfc_ramp_down_queue_handler() logic is called to help reduce I/O load by
reducing an sdev's queue_depth.
However, the current lpfc_rampdown_queue_depth() logic does not help reduce
queue_depth. num_cmd_success is never updated and is always zero, which
means new_queue_depth will always be set to sdev->queue_depth. So,
new_queue_depth = sdev->queue_depth - new_queue_depth always sets
new_queue_depth to zero. And, scsi_change_queue_depth(sdev, 0) is
essentially a no-op.
Change the lpfc_ramp_down_queue_handler() logic to set new_queue_depth
equal to sdev->queue_depth subtracted from number of times num_rsrc_err was
incremented. If num_rsrc_err is >= sdev->queue_depth, then set
new_queue_depth equal to 1. Eventually, the frequency of Good_Status
frames will signal SCSI upper layer to auto increase the queue_depth back
to the driver default of 64 via scsi_handle_queue_ramp_up().
Signed-off-by: Justin Tee <justin.tee(a)broadcom.com>
Link: https://lore.kernel.org/r/20240305200503.57317-5-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/scsi/lpfc/lpfc.h | 1 -
drivers/scsi/lpfc/lpfc_scsi.c | 13 ++++---------
2 files changed, 4 insertions(+), 10 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index cf69f831a7253..8f1b5b0ee8cd8 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -1065,7 +1065,6 @@ struct lpfc_hba {
unsigned long bit_flags;
#define FABRIC_COMANDS_BLOCKED 0
atomic_t num_rsrc_err;
- atomic_t num_cmd_success;
unsigned long last_rsrc_error_time;
unsigned long last_ramp_down_time;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index b4b87e5d8b291..2121534838747 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -246,11 +246,10 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
struct Scsi_Host *shost;
struct scsi_device *sdev;
unsigned long new_queue_depth;
- unsigned long num_rsrc_err, num_cmd_success;
+ unsigned long num_rsrc_err;
int i;
num_rsrc_err = atomic_read(&phba->num_rsrc_err);
- num_cmd_success = atomic_read(&phba->num_cmd_success);
/*
* The error and success command counters are global per
@@ -265,20 +264,16 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
shost = lpfc_shost_from_vport(vports[i]);
shost_for_each_device(sdev, shost) {
- new_queue_depth =
- sdev->queue_depth * num_rsrc_err /
- (num_rsrc_err + num_cmd_success);
- if (!new_queue_depth)
- new_queue_depth = sdev->queue_depth - 1;
+ if (num_rsrc_err >= sdev->queue_depth)
+ new_queue_depth = 1;
else
new_queue_depth = sdev->queue_depth -
- new_queue_depth;
+ num_rsrc_err;
scsi_change_queue_depth(sdev, new_queue_depth);
}
}
lpfc_destroy_vport_work_array(phba, vports);
atomic_set(&phba->num_rsrc_err, 0);
- atomic_set(&phba->num_cmd_success, 0);
}
/**
--
2.43.0
From: Justin Tee <justin.tee(a)broadcom.com>
[ Upstream commit 4ddf01f2f1504fa08b766e8cfeec558e9f8eef6c ]
There are cases after NPIV deletion where the fabric switch still believes
the NPIV is logged into the fabric. This occurs when a vport is
unregistered before the Remove All DA_ID CT and LOGO ELS are sent to the
fabric.
Currently fc_remove_host(), which calls dev_loss_tmo for all D_IDs including
the fabric D_ID, removes the last ndlp reference and frees the ndlp rport
object. This sometimes causes the race condition where the final DA_ID and
LOGO are skipped from being sent to the fabric switch.
Fix by moving the fc_remove_host() and scsi_remove_host() calls after DA_ID
and LOGO are sent.
Signed-off-by: Justin Tee <justin.tee(a)broadcom.com>
Link: https://lore.kernel.org/r/20240305200503.57317-3-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/scsi/lpfc/lpfc_vport.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index da9a1f72d9383..b1071226e27fb 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -651,10 +651,6 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
lpfc_free_sysfs_attr(vport);
lpfc_debugfs_terminate(vport);
- /* Remove FC host to break driver binding. */
- fc_remove_host(shost);
- scsi_remove_host(shost);
-
/* Send the DA_ID and Fabric LOGO to cleanup Nameserver entries. */
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (!ndlp)
@@ -700,6 +696,10 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
skip_logo:
+ /* Remove FC host to break driver binding. */
+ fc_remove_host(shost);
+ scsi_remove_host(shost);
+
lpfc_cleanup(vport);
/* Remove scsi host now. The nodes are cleaned up. */
--
2.43.0
From: Justin Tee <justin.tee(a)broadcom.com>
[ Upstream commit 4ddf01f2f1504fa08b766e8cfeec558e9f8eef6c ]
There are cases after NPIV deletion where the fabric switch still believes
the NPIV is logged into the fabric. This occurs when a vport is
unregistered before the Remove All DA_ID CT and LOGO ELS are sent to the
fabric.
Currently fc_remove_host(), which calls dev_loss_tmo for all D_IDs including
the fabric D_ID, removes the last ndlp reference and frees the ndlp rport
object. This sometimes causes the race condition where the final DA_ID and
LOGO are skipped from being sent to the fabric switch.
Fix by moving the fc_remove_host() and scsi_remove_host() calls after DA_ID
and LOGO are sent.
Signed-off-by: Justin Tee <justin.tee(a)broadcom.com>
Link: https://lore.kernel.org/r/20240305200503.57317-3-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/scsi/lpfc/lpfc_vport.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 4d171f5c213f7..6b4259894584f 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -693,10 +693,6 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
lpfc_free_sysfs_attr(vport);
lpfc_debugfs_terminate(vport);
- /* Remove FC host to break driver binding. */
- fc_remove_host(shost);
- scsi_remove_host(shost);
-
/* Send the DA_ID and Fabric LOGO to cleanup Nameserver entries. */
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (!ndlp)
@@ -740,6 +736,10 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
skip_logo:
+ /* Remove FC host to break driver binding. */
+ fc_remove_host(shost);
+ scsi_remove_host(shost);
+
lpfc_cleanup(vport);
/* Remove scsi host now. The nodes are cleaned up. */
--
2.43.0
From: Rohit Ner <rohitner(a)google.com>
[ Upstream commit 767712f91de76abd22a45184e6e3440120b8bfce ]
As per JEDEC Standard No. 223E Section 5.9.2, the max # active commands
value programmed by the host sw in MCQConfig.MAC should be one less than
the actual value.
Signed-off-by: Rohit Ner <rohitner(a)google.com>
Link: https://lore.kernel.org/r/20240220095637.2900067-1-rohitner@google.com
Reviewed-by: Peter Wang <peter.wang(a)mediatek.com>
Reviewed-by: Can Guo <quic_cang(a)quicinc.com>
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/ufs/core/ufs-mcq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 0787456c2b892..c873fd8239427 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -94,7 +94,7 @@ void ufshcd_mcq_config_mac(struct ufs_hba *hba, u32 max_active_cmds)
val = ufshcd_readl(hba, REG_UFS_MCQ_CFG);
val &= ~MCQ_CFG_MAC_MASK;
- val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds);
+ val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds - 1);
ufshcd_writel(hba, val, REG_UFS_MCQ_CFG);
}
EXPORT_SYMBOL_GPL(ufshcd_mcq_config_mac);
--
2.43.0
From: Rohit Ner <rohitner(a)google.com>
[ Upstream commit 767712f91de76abd22a45184e6e3440120b8bfce ]
As per JEDEC Standard No. 223E Section 5.9.2, the max # active commands
value programmed by the host sw in MCQConfig.MAC should be one less than
the actual value.
Signed-off-by: Rohit Ner <rohitner(a)google.com>
Link: https://lore.kernel.org/r/20240220095637.2900067-1-rohitner@google.com
Reviewed-by: Peter Wang <peter.wang(a)mediatek.com>
Reviewed-by: Can Guo <quic_cang(a)quicinc.com>
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/ufs/core/ufs-mcq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 0787456c2b892..c873fd8239427 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -94,7 +94,7 @@ void ufshcd_mcq_config_mac(struct ufs_hba *hba, u32 max_active_cmds)
val = ufshcd_readl(hba, REG_UFS_MCQ_CFG);
val &= ~MCQ_CFG_MAC_MASK;
- val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds);
+ val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds - 1);
ufshcd_writel(hba, val, REG_UFS_MCQ_CFG);
}
EXPORT_SYMBOL_GPL(ufshcd_mcq_config_mac);
--
2.43.0
I'm announcing the release of the 6.8.4 kernel.
All users of the 6.8 kernel series must upgrade.
The updated 6.8.y git tree can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git linux-6.8.y
and can be browsed at the normal kernel.org git web browser:
https://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git;a=summary
thanks,
greg k-h
------------
Makefile | 2
include/linux/workqueue.h | 35 --
kernel/workqueue.c | 757 +++++++---------------------------------------
3 files changed, 131 insertions(+), 663 deletions(-)
Greg Kroah-Hartman (12):
Revert "workqueue: Shorten events_freezable_power_efficient name"
Revert "workqueue: Don't call cpumask_test_cpu() with -1 CPU in wq_update_node_max_active()"
Revert "workqueue: Implement system-wide nr_active enforcement for unbound workqueues"
Revert "workqueue: Introduce struct wq_node_nr_active"
Revert "workqueue: RCU protect wq->dfl_pwq and implement accessors for it"
Revert "workqueue: Make wq_adjust_max_active() round-robin pwqs while activating"
Revert "workqueue: Move nr_active handling into helpers"
Revert "workqueue: Replace pwq_activate_inactive_work() with [__]pwq_activate_work()"
Revert "workqueue: Factor out pwq_is_empty()"
Revert "workqueue: Move pwq->max_active to wq->max_active"
Revert "workqueue.c: Increase workqueue name length"
Linux 6.8.4
[cc stable to see if they have any ideas about fixing this]
On Sat, 2024-04-06 at 12:16 -0400, John David Anglin wrote:
> On 2024-04-06 11:06 a.m., James Bottomley wrote:
> > On Sat, 2024-04-06 at 10:30 -0400, John David Anglin wrote:
> > > On 2024-04-05 3:36 p.m., Bart Van Assche wrote:
> > > > On 4/4/24 13:07, John David Anglin wrote:
> > > > > On 2024-04-04 12:32 p.m., Bart Van Assche wrote:
> > > > > > Can you please help with verifying whether this kernel warn
> > > > > > ing is only triggered by the 6.1 stable kernel series or
> > > > > > whether it is also
> > > > > > triggered by a vanilla kernel, e.g. kernel v6.8? That will
> > > > > > tell us whether we
> > > > > > need to review the upstream changes or the backp
> > > > > > orts on the v6.1 branch.
> > > > > Stable kernel v6.8.3 is okay.
> > > > Would it be possible to bisect this issue on the linux-6.1.y
> > > > branch? That probably will be faster than reviewing all
> > > > backports
> > > > of SCSI patches on that branch.
> > > The warning triggers with v6.1.81. It doesn't trigger with
> > > v6.1.80.
> > It's this patch:
> >
> > https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=…
> >
> > The specific problem being that the update to scsi_execute doesn't
> > set the sense_len that the WARN_ON is checking.
> >
> > This isn't a problem in mainline because we've converted all uses
> > of scsi_execute. Stable needs to either complete the conversion or
> > back out the inital patch. This change depends on the above change:
> https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=…
>
> Thus, more than just the initial patch needs to be backed out.
OK, so the reason the bad patch got pulled in is because it's a
precursor of this fixes tagged backport:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=…
Which is presumably the other patch you had to back out to fix the
issue.
The problem is that Mike's series updating and then removing
scsi_execute() went into the tree as one series, so no-one notice the
first patch had this bug because the buggy routine got removed at the
end of the series. This also means there's nothing to fix and backport
in upstream.
The bug is also more widely spread than simply domain validation,
because every use of scsi_execute in the current stable tree will trip
this.
I'm not sure what the best fix is. I can certainly come up with a one
line fix for stable adding the missing length in the #define, but it
can't come from upstream as stated above. We could back the two
patches out then do a stable specific fix for the UAS problem (I don't
think we can leave the UAS patch backed out because the problem was
pretty serious).
What does stable want to do?
James
From: Ville Syrjälä <ville.syrjala(a)linux.intel.com>
The modes[] array contains pointers to modes on the connectors'
mode lists, which are protected by dev->mode_config.mutex.
Thus we need to extend modes[] the same protection or by the
time we use it the elements may already be pointing to
freed/reused memory.
Cc: stable(a)vger.kernel.org
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/10583
Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com>
---
drivers/gpu/drm/drm_client_modeset.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 871e4e2129d6..0683a129b362 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -777,6 +777,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width,
unsigned int total_modes_count = 0;
struct drm_client_offset *offsets;
unsigned int connector_count = 0;
+ /* points to modes protected by mode_config.mutex */
struct drm_display_mode **modes;
struct drm_crtc **crtcs;
int i, ret = 0;
@@ -845,7 +846,6 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width,
drm_client_pick_crtcs(client, connectors, connector_count,
crtcs, modes, 0, width, height);
}
- mutex_unlock(&dev->mode_config.mutex);
drm_client_modeset_release(client);
@@ -875,6 +875,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width,
modeset->y = offset->y;
}
}
+ mutex_unlock(&dev->mode_config.mutex);
mutex_unlock(&client->modeset_mutex);
out:
--
2.43.2
On 04.04.2024 19:02, Ritesh Harjani (IBM) wrote:
> It will be good to know what was the test which identified this though?
>
> -ritesh
Unfortunately syzkaller was not able to generate a reproducer for this
issue.
- Ukhin Mikhail.
There is code in the SCSI core that sets the SCMD_FAIL_IF_RECOVERING
flag but there is no code that clears this flag. Instead of only clearing
SCMD_INITIALIZED in scsi_end_request(), clear all flags. It is never
necessary to preserve any command flags inside scsi_end_request().
Cc: stable(a)vger.kernel.org
Fixes: 310bcaef6d7e ("scsi: core: Support failing requests while recovering")
Signed-off-by: Bart Van Assche <bvanassche(a)acm.org>
---
drivers/scsi/scsi_lib.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ca48ba9a229a..2fc2b97777ca 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -633,10 +633,9 @@ static bool scsi_end_request(struct request *req, blk_status_t error,
if (blk_queue_add_random(q))
add_disk_randomness(req->q->disk);
- if (!blk_rq_is_passthrough(req)) {
- WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED));
- cmd->flags &= ~SCMD_INITIALIZED;
- }
+ WARN_ON_ONCE(!blk_rq_is_passthrough(req) &&
+ !(cmd->flags & SCMD_INITIALIZED));
+ cmd->flags = 0;
/*
* Calling rcu_barrier() is not necessary here because the
Fuzzing reports a possible deadlock in jbd2_log_wait_commit.
The problem occurs in ext4_ind_migrate due to an incorrect order of
unlocking of the journal and write semaphores - the order of unlocking
must be the reverse of the order of locking.
Found by Linux Verification Center (linuxtesting.org) with syzkaller.
Signed-off-by: Artem Sadovnikov <ancowi69(a)gmail.com>
---
fs/ext4/migrate.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index d98ac2af8199..a5e1492bbaaa 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -663,8 +663,8 @@ int ext4_ind_migrate(struct inode *inode)
if (unlikely(ret2 && !ret))
ret = ret2;
errout:
- ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);
+ ext4_journal_stop(handle);
out_unlock:
ext4_writepages_up_write(inode->i_sb, alloc_ctx);
return ret;
--
2.25.1
The quilt patch titled
Subject: x86/mm/pat: fix VM_PAT handling in COW mappings
has been removed from the -mm tree. Its filename was
x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch
This patch was dropped because it was merged into the mm-hotfixes-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: David Hildenbrand <david(a)redhat.com>
Subject: x86/mm/pat: fix VM_PAT handling in COW mappings
Date: Wed, 3 Apr 2024 23:21:30 +0200
PAT handling won't do the right thing in COW mappings: the first PTE (or,
in fact, all PTEs) can be replaced during write faults to point at anon
folios. Reliably recovering the correct PFN and cachemode using
follow_phys() from PTEs will not work in COW mappings.
Using follow_phys(), we might just get the address+protection of the anon
folio (which is very wrong), or fail on swap/nonswap entries, failing
follow_phys() and triggering a WARN_ON_ONCE() in untrack_pfn() and
track_pfn_copy(), not properly calling free_pfn_range().
In free_pfn_range(), we either wouldn't call memtype_free() or would call
it with the wrong range, possibly leaking memory.
To fix that, let's update follow_phys() to refuse returning anon folios,
and fallback to using the stored PFN inside vma->vm_pgoff for COW mappings
if we run into that.
We will now properly handle untrack_pfn() with COW mappings, where we
don't need the cachemode. We'll have to fail fork()->track_pfn_copy() if
the first page was replaced by an anon folio, though: we'd have to store
the cachemode in the VMA to make this work, likely growing the VMA size.
For now, lets keep it simple and let track_pfn_copy() just fail in that
case: it would have failed in the past with swap/nonswap entries already,
and it would have done the wrong thing with anon folios.
Simple reproducer to trigger the WARN_ON_ONCE() in untrack_pfn():
<--- C reproducer --->
#include <stdio.h>
#include <sys/mman.h>
#include <unistd.h>
#include <liburing.h>
int main(void)
{
struct io_uring_params p = {};
int ring_fd;
size_t size;
char *map;
ring_fd = io_uring_setup(1, &p);
if (ring_fd < 0) {
perror("io_uring_setup");
return 1;
}
size = p.sq_off.array + p.sq_entries * sizeof(unsigned);
/* Map the submission queue ring MAP_PRIVATE */
map = mmap(0, size, PROT_READ | PROT_WRITE, MAP_PRIVATE,
ring_fd, IORING_OFF_SQ_RING);
if (map == MAP_FAILED) {
perror("mmap");
return 1;
}
/* We have at least one page. Let's COW it. */
*map = 0;
pause();
return 0;
}
<--- C reproducer --->
On a system with 16 GiB RAM and swap configured:
# ./iouring &
# memhog 16G
# killall iouring
[ 301.552930] ------------[ cut here ]------------
[ 301.553285] WARNING: CPU: 7 PID: 1402 at arch/x86/mm/pat/memtype.c:1060 untrack_pfn+0xf4/0x100
[ 301.553989] Modules linked in: binfmt_misc nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_g
[ 301.558232] CPU: 7 PID: 1402 Comm: iouring Not tainted 6.7.5-100.fc38.x86_64 #1
[ 301.558772] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebu4
[ 301.559569] RIP: 0010:untrack_pfn+0xf4/0x100
[ 301.559893] Code: 75 c4 eb cf 48 8b 43 10 8b a8 e8 00 00 00 3b 6b 28 74 b8 48 8b 7b 30 e8 ea 1a f7 000
[ 301.561189] RSP: 0018:ffffba2c0377fab8 EFLAGS: 00010282
[ 301.561590] RAX: 00000000ffffffea RBX: ffff9208c8ce9cc0 RCX: 000000010455e047
[ 301.562105] RDX: 07fffffff0eb1e0a RSI: 0000000000000000 RDI: ffff9208c391d200
[ 301.562628] RBP: 0000000000000000 R08: ffffba2c0377fab8 R09: 0000000000000000
[ 301.563145] R10: ffff9208d2292d50 R11: 0000000000000002 R12: 00007fea890e0000
[ 301.563669] R13: 0000000000000000 R14: ffffba2c0377fc08 R15: 0000000000000000
[ 301.564186] FS: 0000000000000000(0000) GS:ffff920c2fbc0000(0000) knlGS:0000000000000000
[ 301.564773] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 301.565197] CR2: 00007fea88ee8a20 CR3: 00000001033a8000 CR4: 0000000000750ef0
[ 301.565725] PKRU: 55555554
[ 301.565944] Call Trace:
[ 301.566148] <TASK>
[ 301.566325] ? untrack_pfn+0xf4/0x100
[ 301.566618] ? __warn+0x81/0x130
[ 301.566876] ? untrack_pfn+0xf4/0x100
[ 301.567163] ? report_bug+0x171/0x1a0
[ 301.567466] ? handle_bug+0x3c/0x80
[ 301.567743] ? exc_invalid_op+0x17/0x70
[ 301.568038] ? asm_exc_invalid_op+0x1a/0x20
[ 301.568363] ? untrack_pfn+0xf4/0x100
[ 301.568660] ? untrack_pfn+0x65/0x100
[ 301.568947] unmap_single_vma+0xa6/0xe0
[ 301.569247] unmap_vmas+0xb5/0x190
[ 301.569532] exit_mmap+0xec/0x340
[ 301.569801] __mmput+0x3e/0x130
[ 301.570051] do_exit+0x305/0xaf0
...
Link: https://lkml.kernel.org/r/20240403212131.929421-3-david@redhat.com
Signed-off-by: David Hildenbrand <david(a)redhat.com>
Reported-by: Wupeng Ma <mawupeng1(a)huawei.com>
Closes: https://lkml.kernel.org/r/20240227122814.3781907-1-mawupeng1@huawei.com
Fixes: b1a86e15dc03 ("x86, pat: remove the dependency on 'vm_pgoff' in track/untrack pfn vma routines")
Fixes: 5899329b1910 ("x86: PAT: implement track/untrack of pfnmap regions for x86 - v3")
Acked-by: Ingo Molnar <mingo(a)kernel.org>
Cc: Dave Hansen <dave.hansen(a)linux.intel.com>
Cc: Andy Lutomirski <luto(a)kernel.org>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: "H. Peter Anvin" <hpa(a)zytor.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
arch/x86/mm/pat/memtype.c | 49 +++++++++++++++++++++++++-----------
mm/memory.c | 4 ++
2 files changed, 39 insertions(+), 14 deletions(-)
--- a/arch/x86/mm/pat/memtype.c~x86-mm-pat-fix-vm_pat-handling-in-cow-mappings
+++ a/arch/x86/mm/pat/memtype.c
@@ -947,6 +947,38 @@ static void free_pfn_range(u64 paddr, un
memtype_free(paddr, paddr + size);
}
+static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
+ pgprot_t *pgprot)
+{
+ unsigned long prot;
+
+ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
+
+ /*
+ * We need the starting PFN and cachemode used for track_pfn_remap()
+ * that covered the whole VMA. For most mappings, we can obtain that
+ * information from the page tables. For COW mappings, we might now
+ * suddenly have anon folios mapped and follow_phys() will fail.
+ *
+ * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
+ * detect the PFN. If we need the cachemode as well, we're out of luck
+ * for now and have to fail fork().
+ */
+ if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+ if (pgprot)
+ *pgprot = __pgprot(prot);
+ return 0;
+ }
+ if (is_cow_mapping(vma->vm_flags)) {
+ if (pgprot)
+ return -EINVAL;
+ *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+ return 0;
+ }
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+
/*
* track_pfn_copy is called when vma that is covering the pfnmap gets
* copied through copy_page_range().
@@ -957,20 +989,13 @@ static void free_pfn_range(u64 paddr, un
int track_pfn_copy(struct vm_area_struct *vma)
{
resource_size_t paddr;
- unsigned long prot;
unsigned long vma_size = vma->vm_end - vma->vm_start;
pgprot_t pgprot;
if (vma->vm_flags & VM_PAT) {
- /*
- * reserve the whole chunk covered by vma. We need the
- * starting address and protection from pte.
- */
- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
- WARN_ON_ONCE(1);
+ if (get_pat_info(vma, &paddr, &pgprot))
return -EINVAL;
- }
- pgprot = __pgprot(prot);
+ /* reserve the whole chunk covered by vma. */
return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
}
@@ -1045,7 +1070,6 @@ void untrack_pfn(struct vm_area_struct *
unsigned long size, bool mm_wr_locked)
{
resource_size_t paddr;
- unsigned long prot;
if (vma && !(vma->vm_flags & VM_PAT))
return;
@@ -1053,11 +1077,8 @@ void untrack_pfn(struct vm_area_struct *
/* free the chunk starting from pfn or the whole chunk */
paddr = (resource_size_t)pfn << PAGE_SHIFT;
if (!paddr && !size) {
- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
- WARN_ON_ONCE(1);
+ if (get_pat_info(vma, &paddr, NULL))
return;
- }
-
size = vma->vm_end - vma->vm_start;
}
free_pfn_range(paddr, size);
--- a/mm/memory.c~x86-mm-pat-fix-vm_pat-handling-in-cow-mappings
+++ a/mm/memory.c
@@ -5973,6 +5973,10 @@ int follow_phys(struct vm_area_struct *v
goto out;
pte = ptep_get(ptep);
+ /* Never return PFNs of anon folios in COW mappings. */
+ if (vm_normal_folio(vma, address, pte))
+ goto unlock;
+
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
_
Patches currently in -mm which might be from david(a)redhat.com are
mm-madvise-make-madv_populate_readwrite-handle-vm_fault_retry-properly.patch
mm-madvise-dont-perform-madvise-vma-walk-for-madv_populate_readwrite.patch
mm-userfaultfd-dont-place-zeropages-when-zeropages-are-disallowed.patch
s390-mm-re-enable-the-shared-zeropage-for-pv-and-skeys-kvm-guests.patch
mm-convert-folio_estimated_sharers-to-folio_likely_mapped_shared.patch
mm-convert-folio_estimated_sharers-to-folio_likely_mapped_shared-fix.patch
selftests-memfd_secret-add-vmsplice-test.patch
mm-merge-folio_is_secretmem-and-folio_fast_pin_allowed-into-gup_fast_folio_allowed.patch
mm-optimize-config_per_vma_lock-member-placement-in-vm_area_struct.patch
mm-remove-prot-parameter-from-move_pte.patch
mm-gup-consistently-name-gup-fast-functions.patch
mm-treewide-rename-config_have_fast_gup-to-config_have_gup_fast.patch
mm-use-gup-fast-instead-fast-gup-in-remaining-comments.patch
The quilt patch titled
Subject: selftests/mm: include strings.h for ffsl
has been removed from the -mm tree. Its filename was
selftests-mm-include-stringsh-for-ffsl.patch
This patch was dropped because it was merged into the mm-hotfixes-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Edward Liaw <edliaw(a)google.com>
Subject: selftests/mm: include strings.h for ffsl
Date: Fri, 29 Mar 2024 18:58:10 +0000
Got a compilation error on Android for ffsl after 91b80cc5b39f
("selftests: mm: fix map_hugetlb failure on 64K page size systems")
included vm_util.h.
Link: https://lkml.kernel.org/r/20240329185814.16304-1-edliaw@google.com
Fixes: af605d26a8f2 ("selftests/mm: merge util.h into vm_util.h")
Signed-off-by: Edward Liaw <edliaw(a)google.com>
Reviewed-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com>
Cc: Axel Rasmussen <axelrasmussen(a)google.com>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: "Mike Rapoport (IBM)" <rppt(a)kernel.org>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
tools/testing/selftests/mm/vm_util.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/tools/testing/selftests/mm/vm_util.h~selftests-mm-include-stringsh-for-ffsl
+++ a/tools/testing/selftests/mm/vm_util.h
@@ -3,7 +3,7 @@
#include <stdbool.h>
#include <sys/mman.h>
#include <err.h>
-#include <string.h> /* ffsl() */
+#include <strings.h> /* ffsl() */
#include <unistd.h> /* _SC_PAGESIZE */
#define BIT_ULL(nr) (1ULL << (nr))
_
Patches currently in -mm which might be from edliaw(a)google.com are
The quilt patch titled
Subject: mm/secretmem: fix GUP-fast succeeding on secretmem folios
has been removed from the -mm tree. Its filename was
mm-secretmem-fix-gup-fast-succeeding-on-secretmem-folios.patch
This patch was dropped because it was merged into the mm-hotfixes-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: David Hildenbrand <david(a)redhat.com>
Subject: mm/secretmem: fix GUP-fast succeeding on secretmem folios
Date: Tue, 26 Mar 2024 15:32:08 +0100
folio_is_secretmem() currently relies on secretmem folios being LRU
folios, to save some cycles.
However, folios might reside in a folio batch without the LRU flag set, or
temporarily have their LRU flag cleared. Consequently, the LRU flag is
unreliable for this purpose.
In particular, this is the case when secretmem_fault() allocates a fresh
page and calls filemap_add_folio()->folio_add_lru(). The folio might be
added to the per-cpu folio batch and won't get the LRU flag set until the
batch was drained using e.g., lru_add_drain().
Consequently, folio_is_secretmem() might not detect secretmem folios and
GUP-fast can succeed in grabbing a secretmem folio, crashing the kernel
when we would later try reading/writing to the folio, because the folio
has been unmapped from the directmap.
Fix it by removing that unreliable check.
Link: https://lkml.kernel.org/r/20240326143210.291116-2-david@redhat.com
Fixes: 1507f51255c9 ("mm: introduce memfd_secret system call to create "secret" memory areas")
Signed-off-by: David Hildenbrand <david(a)redhat.com>
Reported-by: xingwei lee <xrivendell7(a)gmail.com>
Reported-by: yue sun <samsun1006219(a)gmail.com>
Closes: https://lore.kernel.org/lkml/CABOYnLyevJeravW=QrH0JUPYEcDN160aZFb7kwndm-J2r…
Debugged-by: Miklos Szeredi <miklos(a)szeredi.hu>
Tested-by: Miklos Szeredi <mszeredi(a)redhat.com>
Reviewed-by: Mike Rapoport (IBM) <rppt(a)kernel.org>
Cc: Lorenzo Stoakes <lstoakes(a)gmail.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/linux/secretmem.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/include/linux/secretmem.h~mm-secretmem-fix-gup-fast-succeeding-on-secretmem-folios
+++ a/include/linux/secretmem.h
@@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(st
/*
* Using folio_mapping() is quite slow because of the actual call
* instruction.
- * We know that secretmem pages are not compound and LRU so we can
+ * We know that secretmem pages are not compound, so we can
* save a couple of cycles here.
*/
- if (folio_test_large(folio) || !folio_test_lru(folio))
+ if (folio_test_large(folio))
return false;
mapping = (struct address_space *)
_
Patches currently in -mm which might be from david(a)redhat.com are
mm-madvise-make-madv_populate_readwrite-handle-vm_fault_retry-properly.patch
mm-madvise-dont-perform-madvise-vma-walk-for-madv_populate_readwrite.patch
mm-userfaultfd-dont-place-zeropages-when-zeropages-are-disallowed.patch
s390-mm-re-enable-the-shared-zeropage-for-pv-and-skeys-kvm-guests.patch
mm-convert-folio_estimated_sharers-to-folio_likely_mapped_shared.patch
mm-convert-folio_estimated_sharers-to-folio_likely_mapped_shared-fix.patch
selftests-memfd_secret-add-vmsplice-test.patch
mm-merge-folio_is_secretmem-and-folio_fast_pin_allowed-into-gup_fast_folio_allowed.patch
mm-optimize-config_per_vma_lock-member-placement-in-vm_area_struct.patch
mm-remove-prot-parameter-from-move_pte.patch
mm-gup-consistently-name-gup-fast-functions.patch
mm-treewide-rename-config_have_fast_gup-to-config_have_gup_fast.patch
mm-use-gup-fast-instead-fast-gup-in-remaining-comments.patch
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 7a1b3490f47e88ec4cbde65f1a77a0f4bc972282
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040524-stitch-resolute-ead5@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7a1b3490f47e88ec4cbde65f1a77a0f4bc972282 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti(a)redhat.com>
Date: Fri, 29 Mar 2024 13:08:52 +0100
Subject: [PATCH] mptcp: don't account accept() of non-MPC client as fallback
to TCP
Current MPTCP servers increment MPTcpExtMPCapableFallbackACK when they
accept non-MPC connections. As reported by Christoph, this is "surprising"
because the counter might become greater than MPTcpExtMPCapableSYNRX.
MPTcpExtMPCapableFallbackACK counter's name suggests it should only be
incremented when a connection was seen using MPTCP options, then a
fallback to TCP has been done. Let's do that by incrementing it when
the subflow context of an inbound MPC connection attempt is dropped.
Also, update mptcp_connect.sh kselftest, to ensure that the
above MIB does not increment in case a pure TCP client connects to a
MPTCP server.
Fixes: fc518953bc9c ("mptcp: add and use MIB counter infrastructure")
Cc: stable(a)vger.kernel.org
Reported-by: Christoph Paasch <cpaasch(a)apple.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/449
Signed-off-by: Davide Caratti <dcaratti(a)redhat.com>
Reviewed-by: Mat Martineau <martineau(a)kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Link: https://lore.kernel.org/r/20240329-upstream-net-20240329-fallback-mib-v1-1-…
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3a1967bc7bad..7e74b812e366 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3937,8 +3937,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
mptcp_set_state(newsk, TCP_CLOSE);
}
} else {
- MPTCP_INC_STATS(sock_net(ssk),
- MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
tcpfallback:
newsk->sk_kern_sock = kern;
lock_sock(newsk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1626dd20c68f..6042a47da61b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -905,6 +905,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
return child;
fallback:
+ if (fallback)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
mptcp_subflow_drop_ctx(child);
return child;
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 4c4248554826..4131f3263a48 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -383,12 +383,14 @@ do_transfer()
local stat_cookierx_last
local stat_csum_err_s
local stat_csum_err_c
+ local stat_tcpfb_last_l
stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+ stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
timeout ${timeout_test} \
ip netns exec ${listener_ns} \
@@ -457,11 +459,13 @@ do_transfer()
local stat_cookietx_now
local stat_cookierx_now
local stat_ooo_now
+ local stat_tcpfb_now_l
stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue")
+ stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
expect_synrx=$((stat_synrx_last_l))
expect_ackrx=$((stat_ackrx_last_l))
@@ -508,6 +512,11 @@ do_transfer()
fi
fi
+ if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then
+ mptcp_lib_pr_fail "unexpected fallback to TCP"
+ rets=1
+ fi
+
if [ $cookies -eq 2 ];then
if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then
extra+=" WARN: CookieSent: did not advance"
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 7a1b3490f47e88ec4cbde65f1a77a0f4bc972282
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040523-handling-conceded-2895@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7a1b3490f47e88ec4cbde65f1a77a0f4bc972282 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti(a)redhat.com>
Date: Fri, 29 Mar 2024 13:08:52 +0100
Subject: [PATCH] mptcp: don't account accept() of non-MPC client as fallback
to TCP
Current MPTCP servers increment MPTcpExtMPCapableFallbackACK when they
accept non-MPC connections. As reported by Christoph, this is "surprising"
because the counter might become greater than MPTcpExtMPCapableSYNRX.
MPTcpExtMPCapableFallbackACK counter's name suggests it should only be
incremented when a connection was seen using MPTCP options, then a
fallback to TCP has been done. Let's do that by incrementing it when
the subflow context of an inbound MPC connection attempt is dropped.
Also, update mptcp_connect.sh kselftest, to ensure that the
above MIB does not increment in case a pure TCP client connects to a
MPTCP server.
Fixes: fc518953bc9c ("mptcp: add and use MIB counter infrastructure")
Cc: stable(a)vger.kernel.org
Reported-by: Christoph Paasch <cpaasch(a)apple.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/449
Signed-off-by: Davide Caratti <dcaratti(a)redhat.com>
Reviewed-by: Mat Martineau <martineau(a)kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Link: https://lore.kernel.org/r/20240329-upstream-net-20240329-fallback-mib-v1-1-…
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3a1967bc7bad..7e74b812e366 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3937,8 +3937,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
mptcp_set_state(newsk, TCP_CLOSE);
}
} else {
- MPTCP_INC_STATS(sock_net(ssk),
- MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
tcpfallback:
newsk->sk_kern_sock = kern;
lock_sock(newsk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1626dd20c68f..6042a47da61b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -905,6 +905,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
return child;
fallback:
+ if (fallback)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
mptcp_subflow_drop_ctx(child);
return child;
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 4c4248554826..4131f3263a48 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -383,12 +383,14 @@ do_transfer()
local stat_cookierx_last
local stat_csum_err_s
local stat_csum_err_c
+ local stat_tcpfb_last_l
stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+ stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
timeout ${timeout_test} \
ip netns exec ${listener_ns} \
@@ -457,11 +459,13 @@ do_transfer()
local stat_cookietx_now
local stat_cookierx_now
local stat_ooo_now
+ local stat_tcpfb_now_l
stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue")
+ stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
expect_synrx=$((stat_synrx_last_l))
expect_ackrx=$((stat_ackrx_last_l))
@@ -508,6 +512,11 @@ do_transfer()
fi
fi
+ if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then
+ mptcp_lib_pr_fail "unexpected fallback to TCP"
+ rets=1
+ fi
+
if [ $cookies -eq 2 ];then
if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then
extra+=" WARN: CookieSent: did not advance"
Case values introduced in commit
5f78e1fb7a3e ("ASoC: qcom: Add driver support for audioreach solution")
cause out of bounds access in arrays of sc7280 driver data (e.g. in case
of RX_CODEC_DMA_RX_0 in sc7280_snd_hw_params()).
Redefine LPASS_MAX_PORTS to consider the maximum possible port id for
q6dsp as sc7280 driver utilizes some of those values.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: 77d0ffef793d ("ASoC: qcom: Add macro for lpass DAI id's max limit")
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Mikhail Kobuk <m.kobuk(a)ispras.ru>
---
sound/soc/qcom/lpass.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h
index 27a2bf9a6613..10a507c95312 100644
--- a/sound/soc/qcom/lpass.h
+++ b/sound/soc/qcom/lpass.h
@@ -13,10 +13,11 @@
#include <linux/platform_device.h>
#include <linux/regmap.h>
#include <dt-bindings/sound/qcom,lpass.h>
+#include <dt-bindings/sound/qcom,q6dsp-lpass-ports.h>
#include "lpass-hdmi.h"
#define LPASS_AHBIX_CLOCK_FREQUENCY 131072000
-#define LPASS_MAX_PORTS (LPASS_CDC_DMA_VA_TX8 + 1)
+#define LPASS_MAX_PORTS (QUINARY_MI2S_TX + 1)
#define LPASS_MAX_MI2S_PORTS (8)
#define LPASS_MAX_DMA_CHANNELS (8)
#define LPASS_MAX_HDMI_DMA_CHANNELS (4)
--
2.44.0
This patch introduces a new API, tegra_xusb_padctl_get_port_number,
to the Tegra XUSB Pad Controller driver. This API is used to identify
the USB port that is associated with a given PHY.
The function takes a PHY pointer for either a USB2 PHY or USB3 PHY as input
and returns the corresponding port number. If the PHY pointer is invalid,
it returns -ENODEV.
Cc: stable(a)vger.kernel.org
Signed-off-by: Wayne Chang <waynec(a)nvidia.com>
---
V1 -> V2:cc stable
drivers/phy/tegra/xusb.c | 13 +++++++++++++
include/linux/phy/tegra/xusb.h | 1 +
2 files changed, 14 insertions(+)
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 142ebe0247cc..983a6e6173bd 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -1531,6 +1531,19 @@ int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl,
}
EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_usb3_companion);
+int tegra_xusb_padctl_get_port_number(struct phy *phy)
+{
+ struct tegra_xusb_lane *lane;
+
+ if (!phy)
+ return -ENODEV;
+
+ lane = phy_get_drvdata(phy);
+
+ return lane->index;
+}
+EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_port_number);
+
MODULE_AUTHOR("Thierry Reding <treding(a)nvidia.com>");
MODULE_DESCRIPTION("Tegra XUSB Pad Controller driver");
MODULE_LICENSE("GPL v2");
diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h
index 70998e6dd6fd..6ca51e0080ec 100644
--- a/include/linux/phy/tegra/xusb.h
+++ b/include/linux/phy/tegra/xusb.h
@@ -26,6 +26,7 @@ void tegra_phy_xusb_utmi_pad_power_down(struct phy *phy);
int tegra_phy_xusb_utmi_port_reset(struct phy *phy);
int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl,
unsigned int port);
+int tegra_xusb_padctl_get_port_number(struct phy *phy);
int tegra_xusb_padctl_enable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy,
enum usb_device_speed speed);
int tegra_xusb_padctl_disable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy);
--
2.25.1
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 7a1b3490f47e88ec4cbde65f1a77a0f4bc972282
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040522-tremor-freehand-618e@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7a1b3490f47e88ec4cbde65f1a77a0f4bc972282 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti(a)redhat.com>
Date: Fri, 29 Mar 2024 13:08:52 +0100
Subject: [PATCH] mptcp: don't account accept() of non-MPC client as fallback
to TCP
Current MPTCP servers increment MPTcpExtMPCapableFallbackACK when they
accept non-MPC connections. As reported by Christoph, this is "surprising"
because the counter might become greater than MPTcpExtMPCapableSYNRX.
MPTcpExtMPCapableFallbackACK counter's name suggests it should only be
incremented when a connection was seen using MPTCP options, then a
fallback to TCP has been done. Let's do that by incrementing it when
the subflow context of an inbound MPC connection attempt is dropped.
Also, update mptcp_connect.sh kselftest, to ensure that the
above MIB does not increment in case a pure TCP client connects to a
MPTCP server.
Fixes: fc518953bc9c ("mptcp: add and use MIB counter infrastructure")
Cc: stable(a)vger.kernel.org
Reported-by: Christoph Paasch <cpaasch(a)apple.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/449
Signed-off-by: Davide Caratti <dcaratti(a)redhat.com>
Reviewed-by: Mat Martineau <martineau(a)kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Link: https://lore.kernel.org/r/20240329-upstream-net-20240329-fallback-mib-v1-1-…
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3a1967bc7bad..7e74b812e366 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3937,8 +3937,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
mptcp_set_state(newsk, TCP_CLOSE);
}
} else {
- MPTCP_INC_STATS(sock_net(ssk),
- MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
tcpfallback:
newsk->sk_kern_sock = kern;
lock_sock(newsk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1626dd20c68f..6042a47da61b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -905,6 +905,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
return child;
fallback:
+ if (fallback)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
mptcp_subflow_drop_ctx(child);
return child;
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 4c4248554826..4131f3263a48 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -383,12 +383,14 @@ do_transfer()
local stat_cookierx_last
local stat_csum_err_s
local stat_csum_err_c
+ local stat_tcpfb_last_l
stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+ stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
timeout ${timeout_test} \
ip netns exec ${listener_ns} \
@@ -457,11 +459,13 @@ do_transfer()
local stat_cookietx_now
local stat_cookierx_now
local stat_ooo_now
+ local stat_tcpfb_now_l
stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue")
+ stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
expect_synrx=$((stat_synrx_last_l))
expect_ackrx=$((stat_ackrx_last_l))
@@ -508,6 +512,11 @@ do_transfer()
fi
fi
+ if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then
+ mptcp_lib_pr_fail "unexpected fallback to TCP"
+ rets=1
+ fi
+
if [ $cookies -eq 2 ];then
if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then
extra+=" WARN: CookieSent: did not advance"
The patch below does not apply to the 6.8-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-6.8.y
git checkout FETCH_HEAD
git cherry-pick -x 1a80dbcb2dbaf6e4c216e62e30fa7d3daa8001ce
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040527-propeller-immovably-a6d8@gregkh' --subject-prefix 'PATCH 6.8.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 1a80dbcb2dbaf6e4c216e62e30fa7d3daa8001ce Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii(a)kernel.org>
Date: Wed, 27 Mar 2024 22:24:26 -0700
Subject: [PATCH] bpf: support deferring bpf_link dealloc to after RCU grace
period
BPF link for some program types is passed as a "context" which can be
used by those BPF programs to look up additional information. E.g., for
multi-kprobes and multi-uprobes, link is used to fetch BPF cookie values.
Because of this runtime dependency, when bpf_link refcnt drops to zero
there could still be active BPF programs running accessing link data.
This patch adds generic support to defer bpf_link dealloc callback to
after RCU GP, if requested. This is done by exposing two different
deallocation callbacks, one synchronous and one deferred. If deferred
one is provided, bpf_link_free() will schedule dealloc_deferred()
callback to happen after RCU GP.
BPF is using two flavors of RCU: "classic" non-sleepable one and RCU
tasks trace one. The latter is used when sleepable BPF programs are
used. bpf_link_free() accommodates that by checking underlying BPF
program's sleepable flag, and goes either through normal RCU GP only for
non-sleepable, or through RCU tasks trace GP *and* then normal RCU GP
(taking into account rcu_trace_implies_rcu_gp() optimization), if BPF
program is sleepable.
We use this for multi-kprobe and multi-uprobe links, which dereference
link during program run. We also preventively switch raw_tp link to use
deferred dealloc callback, as upcoming changes in bpf-next tree expose
raw_tp link data (specifically, cookie value) to BPF program at runtime
as well.
Fixes: 0dcac2725406 ("bpf: Add multi kprobe link")
Fixes: 89ae89f53d20 ("bpf: Add multi uprobe link")
Reported-by: syzbot+981935d9485a560bfbcb(a)syzkaller.appspotmail.com
Reported-by: syzbot+2cb5a6c573e98db598cc(a)syzkaller.appspotmail.com
Reported-by: syzbot+62d8b26793e8a2bd0516(a)syzkaller.appspotmail.com
Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org>
Acked-by: Jiri Olsa <jolsa(a)kernel.org>
Link: https://lore.kernel.org/r/20240328052426.3042617-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast(a)kernel.org>
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4f20f62f9d63..890e152d553e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1574,12 +1574,26 @@ struct bpf_link {
enum bpf_link_type type;
const struct bpf_link_ops *ops;
struct bpf_prog *prog;
- struct work_struct work;
+ /* rcu is used before freeing, work can be used to schedule that
+ * RCU-based freeing before that, so they never overlap
+ */
+ union {
+ struct rcu_head rcu;
+ struct work_struct work;
+ };
};
struct bpf_link_ops {
void (*release)(struct bpf_link *link);
+ /* deallocate link resources callback, called without RCU grace period
+ * waiting
+ */
void (*dealloc)(struct bpf_link *link);
+ /* deallocate link resources callback, called after RCU grace period;
+ * if underlying BPF program is sleepable we go through tasks trace
+ * RCU GP and then "classic" RCU GP
+ */
+ void (*dealloc_deferred)(struct bpf_link *link);
int (*detach)(struct bpf_link *link);
int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
struct bpf_prog *old_prog);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ae2ff73bde7e..c287925471f6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3024,17 +3024,46 @@ void bpf_link_inc(struct bpf_link *link)
atomic64_inc(&link->refcnt);
}
+static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
+{
+ struct bpf_link *link = container_of(rcu, struct bpf_link, rcu);
+
+ /* free bpf_link and its containing memory */
+ link->ops->dealloc_deferred(link);
+}
+
+static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
+{
+ if (rcu_trace_implies_rcu_gp())
+ bpf_link_defer_dealloc_rcu_gp(rcu);
+ else
+ call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp);
+}
+
/* bpf_link_free is guaranteed to be called from process context */
static void bpf_link_free(struct bpf_link *link)
{
+ bool sleepable = false;
+
bpf_link_free_id(link->id);
if (link->prog) {
+ sleepable = link->prog->sleepable;
/* detach BPF program, clean up used resources */
link->ops->release(link);
bpf_prog_put(link->prog);
}
- /* free bpf_link and its containing memory */
- link->ops->dealloc(link);
+ if (link->ops->dealloc_deferred) {
+ /* schedule BPF link deallocation; if underlying BPF program
+ * is sleepable, we need to first wait for RCU tasks trace
+ * sync, then go through "classic" RCU grace period
+ */
+ if (sleepable)
+ call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
+ else
+ call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
+ }
+ if (link->ops->dealloc)
+ link->ops->dealloc(link);
}
static void bpf_link_put_deferred(struct work_struct *work)
@@ -3544,7 +3573,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_raw_tp_link_lops = {
.release = bpf_raw_tp_link_release,
- .dealloc = bpf_raw_tp_link_dealloc,
+ .dealloc_deferred = bpf_raw_tp_link_dealloc,
.show_fdinfo = bpf_raw_tp_link_show_fdinfo,
.fill_link_info = bpf_raw_tp_link_fill_link_info,
};
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0b73fe5f7206..9dc605f08a23 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2728,7 +2728,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
.release = bpf_kprobe_multi_link_release,
- .dealloc = bpf_kprobe_multi_link_dealloc,
+ .dealloc_deferred = bpf_kprobe_multi_link_dealloc,
.fill_link_info = bpf_kprobe_multi_link_fill_link_info,
};
@@ -3242,7 +3242,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
.release = bpf_uprobe_multi_link_release,
- .dealloc = bpf_uprobe_multi_link_dealloc,
+ .dealloc_deferred = bpf_uprobe_multi_link_dealloc,
.fill_link_info = bpf_uprobe_multi_link_fill_link_info,
};
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 40061817d95bce6dd5634a61a65cd5922e6ccc92
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040506-skinny-unsuited-f487@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 40061817d95bce6dd5634a61a65cd5922e6ccc92 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang(a)kylinos.cn>
Date: Fri, 29 Mar 2024 13:08:53 +0100
Subject: [PATCH] selftests: mptcp: join: fix dev in check_endpoint
There's a bug in pm_nl_check_endpoint(), 'dev' didn't be parsed correctly.
If calling it in the 2nd test of endpoint_tests() too, it fails with an
error like this:
creation [FAIL] expected '10.0.2.2 id 2 subflow dev dev' \
found '10.0.2.2 id 2 subflow dev ns2eth2'
The reason is '$2' should be set to 'dev', not '$1'. This patch fixes it.
Fixes: 69c6ce7b6eca ("selftests: mptcp: add implicit endpoint test case")
Cc: stable(a)vger.kernel.org
Signed-off-by: Geliang Tang <tanggeliang(a)kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Link: https://lore.kernel.org/r/20240329-upstream-net-20240329-fallback-mib-v1-2-…
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 5e9211e89825..e4403236f655 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -729,7 +729,7 @@ pm_nl_check_endpoint()
[ -n "$_flags" ]; flags="flags $_flags"
shift
elif [ $1 = "dev" ]; then
- [ -n "$2" ]; dev="dev $1"
+ [ -n "$2" ]; dev="dev $2"
shift
elif [ $1 = "id" ]; then
_id=$2
@@ -3610,6 +3610,8 @@ endpoint_tests()
local tests_pid=$!
wait_mpj $ns2
+ pm_nl_check_endpoint "creation" \
+ $ns2 10.0.2.2 id 2 flags subflow dev ns2eth2
chk_subflow_nr "before delete" 2
chk_mptcp_info subflows 1 subflows 1
ivpu_device->context_xa is locked both in kernel thread and IRQ context.
It requires XA_FLAGS_LOCK_IRQ flag to be passed during initialization
otherwise the lock could be acquired from a thread and interrupted by
an IRQ that locks it for the second time causing the deadlock.
This deadlock was reported by lockdep and observed in internal tests.
Fixes: 35b137630f08 ("accel/ivpu: Introduce a new DRM driver for Intel VPU")
Cc: <stable(a)vger.kernel.org> # v6.3+
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com>
---
drivers/accel/ivpu/ivpu_drv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 77283daaedd1..51d3f1a55d02 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -517,7 +517,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID;
vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID;
atomic64_set(&vdev->unique_id_counter, 0);
- xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC);
+ xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1);
lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
--
2.43.2
Put NPU in D3hot after ivpu_resume() fails to power up the device.
This will assure that D3->D0 power cycle will be performed before
the next resume and also will minimize power usage in this corner case.
Fixes: 28083ff18d3f ("accel/ivpu: Fix DevTLB errors on suspend/resume and recovery")
Cc: <stable(a)vger.kernel.org> # v6.8+
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com>
---
drivers/accel/ivpu/ivpu_pm.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 325b82f8d971..ba51781b5896 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -97,6 +97,7 @@ static int ivpu_resume(struct ivpu_device *vdev)
ivpu_mmu_disable(vdev);
err_power_down:
ivpu_hw_power_down(vdev);
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
if (!ivpu_fw_is_cold_boot(vdev)) {
ivpu_pm_prepare_cold_boot(vdev);
--
2.43.2
From: "Wachowski, Karol" <karol.wachowski(a)intel.com>
In case of failed power up we end up left in PCI D3hot
state making it impossible to access NPU registers on retry.
Enter D0 state on retry before proceeding with power up sequence.
Fixes: 28083ff18d3f ("accel/ivpu: Fix DevTLB errors on suspend/resume and recovery")
Cc: <stable(a)vger.kernel.org> # v6.8+
Signed-off-by: Wachowski, Karol <karol.wachowski(a)intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com>
---
drivers/accel/ivpu/ivpu_pm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 9cbd7af6576b..325b82f8d971 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -71,10 +71,10 @@ static int ivpu_resume(struct ivpu_device *vdev)
{
int ret;
- pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+retry:
pci_restore_state(to_pci_dev(vdev->drm.dev));
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
-retry:
ret = ivpu_hw_power_up(vdev);
if (ret) {
ivpu_err(vdev, "Failed to power up HW: %d\n", ret);
--
2.43.2
These pointers are frequently the same and memcmp does not compare the
pointers before comparing their contents so this was wasting cycles
comparing 16 KiB of memory which will always be equal.
Fixes: bb6780aa5a1d ("drm/vmwgfx: Diff cursors when using cmds")
Signed-off-by: Ian Forbes <ian.forbes(a)broadcom.com>
Cc: <stable(a)vger.kernel.org> # v6.2+
---
v2: Fix code and commit message formatting.
--
drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index cd4925346ed4..ef0af10c4968 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -216,7 +216,7 @@ static bool vmw_du_cursor_plane_has_changed(struct vmw_plane_state *old_vps,
new_image = vmw_du_cursor_plane_acquire_image(new_vps);
changed = false;
- if (old_image && new_image)
+ if (old_image && new_image && old_image != new_image)
changed = memcmp(old_image, new_image, size) != 0;
return changed;
--
2.34.1
The patch below does not apply to the 6.8-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-6.8.y
git checkout FETCH_HEAD
git cherry-pick -x 7a1b3490f47e88ec4cbde65f1a77a0f4bc972282
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040519-palpable-barrel-9103@gregkh' --subject-prefix 'PATCH 6.8.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7a1b3490f47e88ec4cbde65f1a77a0f4bc972282 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti(a)redhat.com>
Date: Fri, 29 Mar 2024 13:08:52 +0100
Subject: [PATCH] mptcp: don't account accept() of non-MPC client as fallback
to TCP
Current MPTCP servers increment MPTcpExtMPCapableFallbackACK when they
accept non-MPC connections. As reported by Christoph, this is "surprising"
because the counter might become greater than MPTcpExtMPCapableSYNRX.
MPTcpExtMPCapableFallbackACK counter's name suggests it should only be
incremented when a connection was seen using MPTCP options, then a
fallback to TCP has been done. Let's do that by incrementing it when
the subflow context of an inbound MPC connection attempt is dropped.
Also, update mptcp_connect.sh kselftest, to ensure that the
above MIB does not increment in case a pure TCP client connects to a
MPTCP server.
Fixes: fc518953bc9c ("mptcp: add and use MIB counter infrastructure")
Cc: stable(a)vger.kernel.org
Reported-by: Christoph Paasch <cpaasch(a)apple.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/449
Signed-off-by: Davide Caratti <dcaratti(a)redhat.com>
Reviewed-by: Mat Martineau <martineau(a)kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org>
Link: https://lore.kernel.org/r/20240329-upstream-net-20240329-fallback-mib-v1-1-…
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3a1967bc7bad..7e74b812e366 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3937,8 +3937,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
mptcp_set_state(newsk, TCP_CLOSE);
}
} else {
- MPTCP_INC_STATS(sock_net(ssk),
- MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
tcpfallback:
newsk->sk_kern_sock = kern;
lock_sock(newsk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1626dd20c68f..6042a47da61b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -905,6 +905,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
return child;
fallback:
+ if (fallback)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
mptcp_subflow_drop_ctx(child);
return child;
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 4c4248554826..4131f3263a48 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -383,12 +383,14 @@ do_transfer()
local stat_cookierx_last
local stat_csum_err_s
local stat_csum_err_c
+ local stat_tcpfb_last_l
stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+ stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
timeout ${timeout_test} \
ip netns exec ${listener_ns} \
@@ -457,11 +459,13 @@ do_transfer()
local stat_cookietx_now
local stat_cookierx_now
local stat_ooo_now
+ local stat_tcpfb_now_l
stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue")
+ stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
expect_synrx=$((stat_synrx_last_l))
expect_ackrx=$((stat_ackrx_last_l))
@@ -508,6 +512,11 @@ do_transfer()
fi
fi
+ if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then
+ mptcp_lib_pr_fail "unexpected fallback to TCP"
+ rets=1
+ fi
+
if [ $cookies -eq 2 ];then
if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then
extra+=" WARN: CookieSent: did not advance"
From: Kan Liang <kan.liang(a)linux.intel.com>
A non-0 retire latency can be observed on a Raptorlake which doesn't
support the retire latency feature.
By design, the retire latency shares the PERF_SAMPLE_WEIGHT_STRUCT
sample type with other types of latency. That could avoid adding too
many different sample types to support all kinds of latency. For the
machine which doesn't support some kind of latency, 0 should be
returned.
Perf doesn’t clear/init all the fields of a sample data for the sake
of performance. It expects the later perf_{prepare,output}_sample() to
update the uninitialized field. However, the current implementation
doesn't touch the field of the retire latency if the feature is not
supported. The memory garbage is dumped into the perf data.
Clear the retire latency if the feature is not supported.
Fixes: c87a31093c70 ("perf/x86: Support Retire Latency")
Reported-by: "Bayduraev, Alexey V" <alexey.v.bayduraev(a)intel.com>
Tested-by: "Bayduraev, Alexey V" <alexey.v.bayduraev(a)intel.com>
Signed-off-by: Kan Liang <kan.liang(a)linux.intel.com>
Cc: stable(a)vger.kernel.org
---
arch/x86/events/intel/ds.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f95cca6b632a..838f3e23bce9 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1989,8 +1989,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
set_linear_ip(regs, basic->ip);
regs->flags = PERF_EFLAGS_EXACT;
- if ((sample_type & PERF_SAMPLE_WEIGHT_STRUCT) && (x86_pmu.flags & PMU_FL_RETIRE_LATENCY))
- data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+ if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
+ if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
+ data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+ else
+ data->weight.var3_w = 0;
+ }
/*
* The record for MEMINFO is in front of GP
--
2.35.1
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 4535e1a4174c4111d92c5a9a21e542d232e0fcaa
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024033032-confess-monument-a6db@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 4535e1a4174c4111d92c5a9a21e542d232e0fcaa Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp(a)alien8.de>
Date: Thu, 28 Mar 2024 13:59:05 +0100
Subject: [PATCH] x86/bugs: Fix the SRSO mitigation on Zen3/4
The original version of the mitigation would patch in the calls to the
untraining routines directly. That is, the alternative() in UNTRAIN_RET
will patch in the CALL to srso_alias_untrain_ret() directly.
However, even if commit e7c25c441e9e ("x86/cpu: Cleanup the untrain
mess") meant well in trying to clean up the situation, due to micro-
architectural reasons, the untraining routine srso_alias_untrain_ret()
must be the target of a CALL instruction and not of a JMP instruction as
it is done now.
Reshuffle the alternative macros to accomplish that.
Fixes: e7c25c441e9e ("x86/cpu: Cleanup the untrain mess")
Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de>
Reviewed-by: Ingo Molnar <mingo(a)kernel.org>
Cc: stable(a)kernel.org
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 076bf8dee702..25466c4d2134 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -14,6 +14,7 @@
#include <asm/asm.h>
#include <asm/fred.h>
#include <asm/gsseg.h>
+#include <asm/nospec-branch.h>
#ifndef CONFIG_X86_CMPXCHG64
extern void cmpxchg8b_emu(void);
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index fc3a8a3c7ffe..170c89ed22fc 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -262,11 +262,20 @@
.Lskip_rsb_\@:
.endm
+/*
+ * The CALL to srso_alias_untrain_ret() must be patched in directly at
+ * the spot where untraining must be done, ie., srso_alias_untrain_ret()
+ * must be the target of a CALL instruction instead of indirectly
+ * jumping to a wrapper which then calls it. Therefore, this macro is
+ * called outside of __UNTRAIN_RET below, for the time being, before the
+ * kernel can support nested alternatives with arbitrary nesting.
+ */
+.macro CALL_UNTRAIN_RET
#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
-#define CALL_UNTRAIN_RET "call entry_untrain_ret"
-#else
-#define CALL_UNTRAIN_RET ""
+ ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \
+ "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
#endif
+.endm
/*
* Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the
@@ -282,8 +291,8 @@
.macro __UNTRAIN_RET ibpb_feature, call_depth_insns
#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY)
VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
+ CALL_UNTRAIN_RET
+ ALTERNATIVE_2 "", \
"call entry_ibpb", \ibpb_feature, \
__stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
#endif
@@ -342,6 +351,8 @@ extern void retbleed_return_thunk(void);
static inline void retbleed_return_thunk(void) {}
#endif
+extern void srso_alias_untrain_ret(void);
+
#ifdef CONFIG_MITIGATION_SRSO
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 721b528da9ac..02cde194a99e 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -163,6 +163,7 @@ SYM_CODE_START_NOALIGN(srso_alias_untrain_ret)
lfence
jmp srso_alias_return_thunk
SYM_FUNC_END(srso_alias_untrain_ret)
+__EXPORT_THUNK(srso_alias_untrain_ret)
.popsection
.pushsection .text..__x86.rethunk_safe
@@ -224,10 +225,12 @@ SYM_CODE_START(srso_return_thunk)
SYM_CODE_END(srso_return_thunk)
#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret"
-#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret"
#else /* !CONFIG_MITIGATION_SRSO */
+/* Dummy for the alternative in CALL_UNTRAIN_RET. */
+SYM_CODE_START(srso_alias_untrain_ret)
+ RET
+SYM_FUNC_END(srso_alias_untrain_ret)
#define JMP_SRSO_UNTRAIN_RET "ud2"
-#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2"
#endif /* CONFIG_MITIGATION_SRSO */
#ifdef CONFIG_MITIGATION_UNRET_ENTRY
@@ -319,9 +322,7 @@ SYM_FUNC_END(retbleed_untrain_ret)
#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
SYM_FUNC_START(entry_untrain_ret)
- ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \
- JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO, \
- JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS
+ ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
SYM_FUNC_END(entry_untrain_ret)
__EXPORT_THUNK(entry_untrain_ret)
Some systems have ACPI tables that don't include everything that needs
to be mapped for a successful kexec. These systems rely on identity
maps that include the full gigabyte surrounding any smaller region
requested for kexec success. Without this, they fail to kexec and end
up doing a full firmware reboot.
So, reduce the use of GB pages only on systems where this is known to
be necessary (specifically, UV systems).
Signed-off-by: Steve Wahl <steve.wahl(a)hpe.com>
Fixes: d794734c9bbf ("x86/mm/ident_map: Use gbpages only where full GB page should be mapped.")
Reported-by: Pavin Joseph <me(a)pavinjoseph.com>
Closes: https://lore.kernel.org/all/3a1b9909-45ac-4f97-ad68-d16ef1ce99db@pavinjosep…
Tested-by: Pavin Joseph <me(a)pavinjoseph.com>
Tested-by: Eric Hagberg <ehagberg(a)gmail.com>
Tested-by: Sarah Brofeldt <srhb(a)dbc.dk>
---
arch/x86/include/asm/init.h | 1 +
arch/x86/kernel/machine_kexec_64.c | 3 +++
arch/x86/mm/ident_map.c | 13 +++++++------
3 files changed, 11 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index cc9ccf61b6bd..4ae843e8fefb 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -10,6 +10,7 @@ struct x86_mapping_info {
unsigned long page_flag; /* page flag for PMD or PUD entry */
unsigned long offset; /* ident mapping offset */
bool direct_gbpages; /* PUD level 1GB page support */
+ bool direct_gbpages_always; /* use 1GB pages exclusively */
unsigned long kernpg_flag; /* kernel pagetable flag override */
};
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index b180d8e497c3..1e1c6633bbec 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -28,6 +28,7 @@
#include <asm/setup.h>
#include <asm/set_memory.h>
#include <asm/cpu.h>
+#include <asm/uv/uv.h>
#ifdef CONFIG_ACPI
/*
@@ -212,6 +213,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
if (direct_gbpages)
info.direct_gbpages = true;
+ if (!is_uv_system())
+ info.direct_gbpages_always = true;
for (i = 0; i < nr_pfn_mapped; i++) {
mstart = pfn_mapped[i].start << PAGE_SHIFT;
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index a204a332c71f..8039498b9713 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -39,12 +39,13 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
/* Is using a gbpage allowed? */
use_gbpage = info->direct_gbpages;
- /* Don't use gbpage if it maps more than the requested region. */
- /* at the begining: */
- use_gbpage &= ((addr & ~PUD_MASK) == 0);
- /* ... or at the end: */
- use_gbpage &= ((next & ~PUD_MASK) == 0);
-
+ if (!info->direct_gbpages_always) {
+ /* Don't use gbpage if it maps more than the requested region. */
+ /* at the beginning: */
+ use_gbpage &= ((addr & ~PUD_MASK) == 0);
+ /* ... or at the end: */
+ use_gbpage &= ((next & ~PUD_MASK) == 0);
+ }
/* Never overwrite existing mappings */
use_gbpage &= !pud_present(*pud);
--
2.26.2
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 fd819ad3ecf6f3c232a06b27423ce9ed8c20da89
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040512-graves-stipend-babf@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From fd819ad3ecf6f3c232a06b27423ce9ed8c20da89 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming(a)zju.edu.cn>
Date: Fri, 29 Mar 2024 09:50:23 +0800
Subject: [PATCH] ax25: fix use-after-free bugs caused by ax25_ds_del_timer
When the ax25 device is detaching, the ax25_dev_device_down()
calls ax25_ds_del_timer() to cleanup the slave_timer. When
the timer handler is running, the ax25_ds_del_timer() that
calls del_timer() in it will return directly. As a result,
the use-after-free bugs could happen, one of the scenarios
is shown below:
(Thread 1) | (Thread 2)
| ax25_ds_timeout()
ax25_dev_device_down() |
ax25_ds_del_timer() |
del_timer() |
ax25_dev_put() //FREE |
| ax25_dev-> //USE
In order to mitigate bugs, when the device is detaching, use
timer_shutdown_sync() to stop the timer.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Duoming Zhou <duoming(a)zju.edu.cn>
Reviewed-by: Simon Horman <horms(a)kernel.org>
Link: https://lore.kernel.org/r/20240329015023.9223-1-duoming@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index c5462486dbca..282ec581c072 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -105,7 +105,7 @@ void ax25_dev_device_down(struct net_device *dev)
spin_lock_bh(&ax25_dev_lock);
#ifdef CONFIG_AX25_DAMA_SLAVE
- ax25_ds_del_timer(ax25_dev);
+ timer_shutdown_sync(&ax25_dev->dama.slave_timer);
#endif
/*
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 fd819ad3ecf6f3c232a06b27423ce9ed8c20da89
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040511-chamber-yelp-2ec9@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From fd819ad3ecf6f3c232a06b27423ce9ed8c20da89 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming(a)zju.edu.cn>
Date: Fri, 29 Mar 2024 09:50:23 +0800
Subject: [PATCH] ax25: fix use-after-free bugs caused by ax25_ds_del_timer
When the ax25 device is detaching, the ax25_dev_device_down()
calls ax25_ds_del_timer() to cleanup the slave_timer. When
the timer handler is running, the ax25_ds_del_timer() that
calls del_timer() in it will return directly. As a result,
the use-after-free bugs could happen, one of the scenarios
is shown below:
(Thread 1) | (Thread 2)
| ax25_ds_timeout()
ax25_dev_device_down() |
ax25_ds_del_timer() |
del_timer() |
ax25_dev_put() //FREE |
| ax25_dev-> //USE
In order to mitigate bugs, when the device is detaching, use
timer_shutdown_sync() to stop the timer.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Duoming Zhou <duoming(a)zju.edu.cn>
Reviewed-by: Simon Horman <horms(a)kernel.org>
Link: https://lore.kernel.org/r/20240329015023.9223-1-duoming@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index c5462486dbca..282ec581c072 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -105,7 +105,7 @@ void ax25_dev_device_down(struct net_device *dev)
spin_lock_bh(&ax25_dev_lock);
#ifdef CONFIG_AX25_DAMA_SLAVE
- ax25_ds_del_timer(ax25_dev);
+ timer_shutdown_sync(&ax25_dev->dama.slave_timer);
#endif
/*
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 fd819ad3ecf6f3c232a06b27423ce9ed8c20da89
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040509-monetize-joyride-107c@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From fd819ad3ecf6f3c232a06b27423ce9ed8c20da89 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming(a)zju.edu.cn>
Date: Fri, 29 Mar 2024 09:50:23 +0800
Subject: [PATCH] ax25: fix use-after-free bugs caused by ax25_ds_del_timer
When the ax25 device is detaching, the ax25_dev_device_down()
calls ax25_ds_del_timer() to cleanup the slave_timer. When
the timer handler is running, the ax25_ds_del_timer() that
calls del_timer() in it will return directly. As a result,
the use-after-free bugs could happen, one of the scenarios
is shown below:
(Thread 1) | (Thread 2)
| ax25_ds_timeout()
ax25_dev_device_down() |
ax25_ds_del_timer() |
del_timer() |
ax25_dev_put() //FREE |
| ax25_dev-> //USE
In order to mitigate bugs, when the device is detaching, use
timer_shutdown_sync() to stop the timer.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Duoming Zhou <duoming(a)zju.edu.cn>
Reviewed-by: Simon Horman <horms(a)kernel.org>
Link: https://lore.kernel.org/r/20240329015023.9223-1-duoming@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index c5462486dbca..282ec581c072 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -105,7 +105,7 @@ void ax25_dev_device_down(struct net_device *dev)
spin_lock_bh(&ax25_dev_lock);
#ifdef CONFIG_AX25_DAMA_SLAVE
- ax25_ds_del_timer(ax25_dev);
+ timer_shutdown_sync(&ax25_dev->dama.slave_timer);
#endif
/*
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 fd819ad3ecf6f3c232a06b27423ce9ed8c20da89
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040506-earmark-skydiver-ab1c@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From fd819ad3ecf6f3c232a06b27423ce9ed8c20da89 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming(a)zju.edu.cn>
Date: Fri, 29 Mar 2024 09:50:23 +0800
Subject: [PATCH] ax25: fix use-after-free bugs caused by ax25_ds_del_timer
When the ax25 device is detaching, the ax25_dev_device_down()
calls ax25_ds_del_timer() to cleanup the slave_timer. When
the timer handler is running, the ax25_ds_del_timer() that
calls del_timer() in it will return directly. As a result,
the use-after-free bugs could happen, one of the scenarios
is shown below:
(Thread 1) | (Thread 2)
| ax25_ds_timeout()
ax25_dev_device_down() |
ax25_ds_del_timer() |
del_timer() |
ax25_dev_put() //FREE |
| ax25_dev-> //USE
In order to mitigate bugs, when the device is detaching, use
timer_shutdown_sync() to stop the timer.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Duoming Zhou <duoming(a)zju.edu.cn>
Reviewed-by: Simon Horman <horms(a)kernel.org>
Link: https://lore.kernel.org/r/20240329015023.9223-1-duoming@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index c5462486dbca..282ec581c072 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -105,7 +105,7 @@ void ax25_dev_device_down(struct net_device *dev)
spin_lock_bh(&ax25_dev_lock);
#ifdef CONFIG_AX25_DAMA_SLAVE
- ax25_ds_del_timer(ax25_dev);
+ timer_shutdown_sync(&ax25_dev->dama.slave_timer);
#endif
/*
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 fd819ad3ecf6f3c232a06b27423ce9ed8c20da89
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040503-tropical-fascism-219c@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From fd819ad3ecf6f3c232a06b27423ce9ed8c20da89 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming(a)zju.edu.cn>
Date: Fri, 29 Mar 2024 09:50:23 +0800
Subject: [PATCH] ax25: fix use-after-free bugs caused by ax25_ds_del_timer
When the ax25 device is detaching, the ax25_dev_device_down()
calls ax25_ds_del_timer() to cleanup the slave_timer. When
the timer handler is running, the ax25_ds_del_timer() that
calls del_timer() in it will return directly. As a result,
the use-after-free bugs could happen, one of the scenarios
is shown below:
(Thread 1) | (Thread 2)
| ax25_ds_timeout()
ax25_dev_device_down() |
ax25_ds_del_timer() |
del_timer() |
ax25_dev_put() //FREE |
| ax25_dev-> //USE
In order to mitigate bugs, when the device is detaching, use
timer_shutdown_sync() to stop the timer.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Duoming Zhou <duoming(a)zju.edu.cn>
Reviewed-by: Simon Horman <horms(a)kernel.org>
Link: https://lore.kernel.org/r/20240329015023.9223-1-duoming@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index c5462486dbca..282ec581c072 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -105,7 +105,7 @@ void ax25_dev_device_down(struct net_device *dev)
spin_lock_bh(&ax25_dev_lock);
#ifdef CONFIG_AX25_DAMA_SLAVE
- ax25_ds_del_timer(ax25_dev);
+ timer_shutdown_sync(&ax25_dev->dama.slave_timer);
#endif
/*
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 ea558de7238bb12c3435c47f0631e9d17bf4a09f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040510-impose-yonder-1ce4@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ea558de7238bb12c3435c47f0631e9d17bf4a09f Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera(a)redhat.com>
Date: Sat, 16 Mar 2024 12:38:29 +0100
Subject: [PATCH] i40e: Enforce software interrupt during busy-poll exit
As for ice bug fixed by commit b7306b42beaf ("ice: manage interrupts
during poll exit") followed by commit 23be7075b318 ("ice: fix software
generating extra interrupts") I'm seeing the similar issue also with
i40e driver.
In certain situation when busy-loop is enabled together with adaptive
coalescing, the driver occasionally misses that there are outstanding
descriptors to clean when exiting busy poll.
Try to catch the remaining work by triggering a software interrupt
when exiting busy poll. No extra interrupts will be generated when
busy polling is not used.
The issue was found when running sockperf ping-pong tcp test with
adaptive coalescing and busy poll enabled (50 as value busy_pool
and busy_read sysctl knobs) and results in huge latency spikes
with more than 100000us.
The fix is inspired from the ice driver and do the following:
1) During napi poll exit in case of busy-poll (napo_complete_done()
returns false) this is recorded to q_vector that we were in busy
loop.
2) Extends i40e_buildreg_itr() to be able to add an enforced software
interrupt into built value
2) In i40e_update_enable_itr() enforces a software interrupt trigger
if we are exiting busy poll to catch any pending clean-ups
3) Reuses unused 3rd ITR (interrupt throttle) index and set it to
20K interrupts per second to limit the number of these sw interrupts.
Test results
============
Prior:
[root@dell-per640-07 net]# sockperf ping-pong -i 10.9.9.1 --tcp -m 1000 --mps=max -t 120
sockperf: == version #3.10-no.git ==
sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
[ 0] IP = 10.9.9.1 PORT = 11111 # TCP
sockperf: Warmup stage (sending a few dummy messages)...
sockperf: Starting test...
sockperf: Test end (interrupted by timer)
sockperf: Test ended
sockperf: [Total Run] RunTime=119.999 sec; Warm up time=400 msec; SentMessages=2438563; ReceivedMessages=2438562
sockperf: ========= Printing statistics for Server No: 0
sockperf: [Valid Duration] RunTime=119.549 sec; SentMessages=2429473; ReceivedMessages=2429473
sockperf: ====> avg-latency=24.571 (std-dev=93.297, mean-ad=4.904, median-ad=1.510, siqr=1.063, cv=3.797, std-error=0.060, 99.0% ci=[24.417, 24.725])
sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
sockperf: Summary: Latency is 24.571 usec
sockperf: Total 2429473 observations; each percentile contains 24294.73 observations
sockperf: ---> <MAX> observation = 103294.331
sockperf: ---> percentile 99.999 = 45.633
sockperf: ---> percentile 99.990 = 37.013
sockperf: ---> percentile 99.900 = 35.910
sockperf: ---> percentile 99.000 = 33.390
sockperf: ---> percentile 90.000 = 28.626
sockperf: ---> percentile 75.000 = 27.741
sockperf: ---> percentile 50.000 = 26.743
sockperf: ---> percentile 25.000 = 25.614
sockperf: ---> <MIN> observation = 12.220
After:
[root@dell-per640-07 net]# sockperf ping-pong -i 10.9.9.1 --tcp -m 1000 --mps=max -t 120
sockperf: == version #3.10-no.git ==
sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
[ 0] IP = 10.9.9.1 PORT = 11111 # TCP
sockperf: Warmup stage (sending a few dummy messages)...
sockperf: Starting test...
sockperf: Test end (interrupted by timer)
sockperf: Test ended
sockperf: [Total Run] RunTime=119.999 sec; Warm up time=400 msec; SentMessages=2400055; ReceivedMessages=2400054
sockperf: ========= Printing statistics for Server No: 0
sockperf: [Valid Duration] RunTime=119.549 sec; SentMessages=2391186; ReceivedMessages=2391186
sockperf: ====> avg-latency=24.965 (std-dev=5.934, mean-ad=4.642, median-ad=1.485, siqr=1.067, cv=0.238, std-error=0.004, 99.0% ci=[24.955, 24.975])
sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
sockperf: Summary: Latency is 24.965 usec
sockperf: Total 2391186 observations; each percentile contains 23911.86 observations
sockperf: ---> <MAX> observation = 195.841
sockperf: ---> percentile 99.999 = 45.026
sockperf: ---> percentile 99.990 = 39.009
sockperf: ---> percentile 99.900 = 35.922
sockperf: ---> percentile 99.000 = 33.482
sockperf: ---> percentile 90.000 = 28.902
sockperf: ---> percentile 75.000 = 27.821
sockperf: ---> percentile 50.000 = 26.860
sockperf: ---> percentile 25.000 = 25.685
sockperf: ---> <MIN> observation = 12.277
Fixes: 0bcd952feec7 ("ethernet/intel: consolidate NAPI and NAPI exit")
Reported-by: Hugo Ferreira <hferreir(a)redhat.com>
Reviewed-by: Michal Schmidt <mschmidt(a)redhat.com>
Signed-off-by: Ivan Vecera <ivecera(a)redhat.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg(a)intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha(a)intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com>
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index ba24f3fa92c3..2fbabcdb5bb5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -955,6 +955,7 @@ struct i40e_q_vector {
struct rcu_head rcu; /* to avoid race with update stats on free */
char name[I40E_INT_NAME_STR_LEN];
bool arm_wb_state;
+ bool in_busy_poll;
int irq_num; /* IRQ assigned to this q_vector */
} ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f86578857e8a..6576a0081093 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3911,6 +3911,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
q_vector->tx.target_itr >> 1);
q_vector->tx.current_itr = q_vector->tx.target_itr;
+ /* Set ITR for software interrupts triggered after exiting
+ * busy-loop polling.
+ */
+ wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1),
+ I40E_ITR_20K);
+
wr32(hw, I40E_PFINT_RATEN(vector - 1),
i40e_intrl_usec_to_reg(vsi->int_rate_limit));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 14ab642cafdb..432afbb64201 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -333,8 +333,11 @@
#define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3
#define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT)
#define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5
+#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT)
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
#define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */
#define I40E_PFINT_ICR0_INTEVENT_SHIFT 0
#define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 0d7177083708..1a12b732818e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2630,7 +2630,22 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
return failure ? budget : (int)total_rx_packets;
}
-static inline u32 i40e_buildreg_itr(const int type, u16 itr)
+/**
+ * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register
+ * @itr_idx: interrupt throttling index
+ * @interval: interrupt throttling interval value in usecs
+ * @force_swint: force software interrupt
+ *
+ * The function builds a value for I40E_PFINT_DYN_CTLN register that
+ * is used to update interrupt throttling interval for specified ITR index
+ * and optionally enforces a software interrupt. If the @itr_idx is equal
+ * to I40E_ITR_NONE then no interval change is applied and only @force_swint
+ * parameter is taken into account. If the interval change and enforced
+ * software interrupt are not requested then the built value just enables
+ * appropriate vector interrupt.
+ **/
+static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval,
+ bool force_swint)
{
u32 val;
@@ -2644,23 +2659,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
* an event in the PBA anyway so we need to rely on the automask
* to hold pending events for us until the interrupt is re-enabled
*
- * The itr value is reported in microseconds, and the register
- * value is recorded in 2 microsecond units. For this reason we
- * only need to shift by the interval shift - 1 instead of the
- * full value.
+ * We have to shift the given value as it is reported in microseconds
+ * and the register value is recorded in 2 microsecond units.
*/
- itr &= I40E_ITR_MASK;
+ interval >>= 1;
+ /* 1. Enable vector interrupt
+ * 2. Update the interval for the specified ITR index
+ * (I40E_ITR_NONE in the register is used to indicate that
+ * no interval update is requested)
+ */
val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
- (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
- (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1));
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval);
+
+ /* 3. Enforce software interrupt trigger if requested
+ * (These software interrupts rate is limited by ITR2 that is
+ * set to 20K interrupts per second)
+ */
+ if (force_swint)
+ val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+ I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK,
+ I40E_SW_ITR);
return val;
}
-/* a small macro to shorten up some long lines */
-#define INTREG I40E_PFINT_DYN_CTLN
-
/* The act of updating the ITR will cause it to immediately trigger. In order
* to prevent this from throwing off adaptive update statistics we defer the
* update so that it can only happen so often. So after either Tx or Rx are
@@ -2679,8 +2704,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
struct i40e_q_vector *q_vector)
{
+ enum i40e_dyn_idx itr_idx = I40E_ITR_NONE;
struct i40e_hw *hw = &vsi->back->hw;
- u32 intval;
+ u16 interval = 0;
+ u32 itr_val;
/* If we don't have MSIX, then we only need to re-enable icr0 */
if (!test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) {
@@ -2702,8 +2729,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
*/
if (q_vector->rx.target_itr < q_vector->rx.current_itr) {
/* Rx ITR needs to be reduced, this is highest priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) ||
@@ -2712,25 +2739,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
/* Tx ITR needs to be reduced, this is second priority
* Tx ITR needs to be increased more than Rx, fourth priority
*/
- intval = i40e_buildreg_itr(I40E_TX_ITR,
- q_vector->tx.target_itr);
+ itr_idx = I40E_TX_ITR;
+ interval = q_vector->tx.target_itr;
q_vector->tx.current_itr = q_vector->tx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if (q_vector->rx.current_itr != q_vector->rx.target_itr) {
/* Rx ITR needs to be increased, third priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else {
/* No ITR update, lowest priority */
- intval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
if (q_vector->itr_countdown)
q_vector->itr_countdown--;
}
- if (!test_bit(__I40E_VSI_DOWN, vsi->state))
- wr32(hw, INTREG(q_vector->reg_idx), intval);
+ /* Do not update interrupt control register if VSI is down */
+ if (test_bit(__I40E_VSI_DOWN, vsi->state))
+ return;
+
+ /* Update ITR interval if necessary and enforce software interrupt
+ * if we are exiting busy poll.
+ */
+ if (q_vector->in_busy_poll) {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, true);
+ q_vector->in_busy_poll = false;
+ } else {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, false);
+ }
+ wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val);
}
/**
@@ -2845,6 +2883,8 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
*/
if (likely(napi_complete_done(napi, work_done)))
i40e_update_enable_itr(vsi, q_vector);
+ else
+ q_vector->in_busy_poll = true;
return min(work_done, budget - 1);
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index abf15067eb5d..2cdc7de6301c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -68,6 +68,7 @@ enum i40e_dyn_idx {
/* these are indexes into ITRN registers */
#define I40E_RX_ITR I40E_IDX_ITR0
#define I40E_TX_ITR I40E_IDX_ITR1
+#define I40E_SW_ITR I40E_IDX_ITR2
/* Supported RSS offloads */
#define I40E_DEFAULT_RSS_HENA ( \
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 ea558de7238bb12c3435c47f0631e9d17bf4a09f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040507-email-pried-bb87@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ea558de7238bb12c3435c47f0631e9d17bf4a09f Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera(a)redhat.com>
Date: Sat, 16 Mar 2024 12:38:29 +0100
Subject: [PATCH] i40e: Enforce software interrupt during busy-poll exit
As for ice bug fixed by commit b7306b42beaf ("ice: manage interrupts
during poll exit") followed by commit 23be7075b318 ("ice: fix software
generating extra interrupts") I'm seeing the similar issue also with
i40e driver.
In certain situation when busy-loop is enabled together with adaptive
coalescing, the driver occasionally misses that there are outstanding
descriptors to clean when exiting busy poll.
Try to catch the remaining work by triggering a software interrupt
when exiting busy poll. No extra interrupts will be generated when
busy polling is not used.
The issue was found when running sockperf ping-pong tcp test with
adaptive coalescing and busy poll enabled (50 as value busy_pool
and busy_read sysctl knobs) and results in huge latency spikes
with more than 100000us.
The fix is inspired from the ice driver and do the following:
1) During napi poll exit in case of busy-poll (napo_complete_done()
returns false) this is recorded to q_vector that we were in busy
loop.
2) Extends i40e_buildreg_itr() to be able to add an enforced software
interrupt into built value
2) In i40e_update_enable_itr() enforces a software interrupt trigger
if we are exiting busy poll to catch any pending clean-ups
3) Reuses unused 3rd ITR (interrupt throttle) index and set it to
20K interrupts per second to limit the number of these sw interrupts.
Test results
============
Prior:
[root@dell-per640-07 net]# sockperf ping-pong -i 10.9.9.1 --tcp -m 1000 --mps=max -t 120
sockperf: == version #3.10-no.git ==
sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
[ 0] IP = 10.9.9.1 PORT = 11111 # TCP
sockperf: Warmup stage (sending a few dummy messages)...
sockperf: Starting test...
sockperf: Test end (interrupted by timer)
sockperf: Test ended
sockperf: [Total Run] RunTime=119.999 sec; Warm up time=400 msec; SentMessages=2438563; ReceivedMessages=2438562
sockperf: ========= Printing statistics for Server No: 0
sockperf: [Valid Duration] RunTime=119.549 sec; SentMessages=2429473; ReceivedMessages=2429473
sockperf: ====> avg-latency=24.571 (std-dev=93.297, mean-ad=4.904, median-ad=1.510, siqr=1.063, cv=3.797, std-error=0.060, 99.0% ci=[24.417, 24.725])
sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
sockperf: Summary: Latency is 24.571 usec
sockperf: Total 2429473 observations; each percentile contains 24294.73 observations
sockperf: ---> <MAX> observation = 103294.331
sockperf: ---> percentile 99.999 = 45.633
sockperf: ---> percentile 99.990 = 37.013
sockperf: ---> percentile 99.900 = 35.910
sockperf: ---> percentile 99.000 = 33.390
sockperf: ---> percentile 90.000 = 28.626
sockperf: ---> percentile 75.000 = 27.741
sockperf: ---> percentile 50.000 = 26.743
sockperf: ---> percentile 25.000 = 25.614
sockperf: ---> <MIN> observation = 12.220
After:
[root@dell-per640-07 net]# sockperf ping-pong -i 10.9.9.1 --tcp -m 1000 --mps=max -t 120
sockperf: == version #3.10-no.git ==
sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
[ 0] IP = 10.9.9.1 PORT = 11111 # TCP
sockperf: Warmup stage (sending a few dummy messages)...
sockperf: Starting test...
sockperf: Test end (interrupted by timer)
sockperf: Test ended
sockperf: [Total Run] RunTime=119.999 sec; Warm up time=400 msec; SentMessages=2400055; ReceivedMessages=2400054
sockperf: ========= Printing statistics for Server No: 0
sockperf: [Valid Duration] RunTime=119.549 sec; SentMessages=2391186; ReceivedMessages=2391186
sockperf: ====> avg-latency=24.965 (std-dev=5.934, mean-ad=4.642, median-ad=1.485, siqr=1.067, cv=0.238, std-error=0.004, 99.0% ci=[24.955, 24.975])
sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
sockperf: Summary: Latency is 24.965 usec
sockperf: Total 2391186 observations; each percentile contains 23911.86 observations
sockperf: ---> <MAX> observation = 195.841
sockperf: ---> percentile 99.999 = 45.026
sockperf: ---> percentile 99.990 = 39.009
sockperf: ---> percentile 99.900 = 35.922
sockperf: ---> percentile 99.000 = 33.482
sockperf: ---> percentile 90.000 = 28.902
sockperf: ---> percentile 75.000 = 27.821
sockperf: ---> percentile 50.000 = 26.860
sockperf: ---> percentile 25.000 = 25.685
sockperf: ---> <MIN> observation = 12.277
Fixes: 0bcd952feec7 ("ethernet/intel: consolidate NAPI and NAPI exit")
Reported-by: Hugo Ferreira <hferreir(a)redhat.com>
Reviewed-by: Michal Schmidt <mschmidt(a)redhat.com>
Signed-off-by: Ivan Vecera <ivecera(a)redhat.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg(a)intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha(a)intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com>
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index ba24f3fa92c3..2fbabcdb5bb5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -955,6 +955,7 @@ struct i40e_q_vector {
struct rcu_head rcu; /* to avoid race with update stats on free */
char name[I40E_INT_NAME_STR_LEN];
bool arm_wb_state;
+ bool in_busy_poll;
int irq_num; /* IRQ assigned to this q_vector */
} ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f86578857e8a..6576a0081093 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3911,6 +3911,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
q_vector->tx.target_itr >> 1);
q_vector->tx.current_itr = q_vector->tx.target_itr;
+ /* Set ITR for software interrupts triggered after exiting
+ * busy-loop polling.
+ */
+ wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1),
+ I40E_ITR_20K);
+
wr32(hw, I40E_PFINT_RATEN(vector - 1),
i40e_intrl_usec_to_reg(vsi->int_rate_limit));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 14ab642cafdb..432afbb64201 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -333,8 +333,11 @@
#define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3
#define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT)
#define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5
+#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT)
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
#define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */
#define I40E_PFINT_ICR0_INTEVENT_SHIFT 0
#define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 0d7177083708..1a12b732818e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2630,7 +2630,22 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
return failure ? budget : (int)total_rx_packets;
}
-static inline u32 i40e_buildreg_itr(const int type, u16 itr)
+/**
+ * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register
+ * @itr_idx: interrupt throttling index
+ * @interval: interrupt throttling interval value in usecs
+ * @force_swint: force software interrupt
+ *
+ * The function builds a value for I40E_PFINT_DYN_CTLN register that
+ * is used to update interrupt throttling interval for specified ITR index
+ * and optionally enforces a software interrupt. If the @itr_idx is equal
+ * to I40E_ITR_NONE then no interval change is applied and only @force_swint
+ * parameter is taken into account. If the interval change and enforced
+ * software interrupt are not requested then the built value just enables
+ * appropriate vector interrupt.
+ **/
+static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval,
+ bool force_swint)
{
u32 val;
@@ -2644,23 +2659,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
* an event in the PBA anyway so we need to rely on the automask
* to hold pending events for us until the interrupt is re-enabled
*
- * The itr value is reported in microseconds, and the register
- * value is recorded in 2 microsecond units. For this reason we
- * only need to shift by the interval shift - 1 instead of the
- * full value.
+ * We have to shift the given value as it is reported in microseconds
+ * and the register value is recorded in 2 microsecond units.
*/
- itr &= I40E_ITR_MASK;
+ interval >>= 1;
+ /* 1. Enable vector interrupt
+ * 2. Update the interval for the specified ITR index
+ * (I40E_ITR_NONE in the register is used to indicate that
+ * no interval update is requested)
+ */
val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
- (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
- (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1));
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval);
+
+ /* 3. Enforce software interrupt trigger if requested
+ * (These software interrupts rate is limited by ITR2 that is
+ * set to 20K interrupts per second)
+ */
+ if (force_swint)
+ val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+ I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK,
+ I40E_SW_ITR);
return val;
}
-/* a small macro to shorten up some long lines */
-#define INTREG I40E_PFINT_DYN_CTLN
-
/* The act of updating the ITR will cause it to immediately trigger. In order
* to prevent this from throwing off adaptive update statistics we defer the
* update so that it can only happen so often. So after either Tx or Rx are
@@ -2679,8 +2704,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
struct i40e_q_vector *q_vector)
{
+ enum i40e_dyn_idx itr_idx = I40E_ITR_NONE;
struct i40e_hw *hw = &vsi->back->hw;
- u32 intval;
+ u16 interval = 0;
+ u32 itr_val;
/* If we don't have MSIX, then we only need to re-enable icr0 */
if (!test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) {
@@ -2702,8 +2729,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
*/
if (q_vector->rx.target_itr < q_vector->rx.current_itr) {
/* Rx ITR needs to be reduced, this is highest priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) ||
@@ -2712,25 +2739,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
/* Tx ITR needs to be reduced, this is second priority
* Tx ITR needs to be increased more than Rx, fourth priority
*/
- intval = i40e_buildreg_itr(I40E_TX_ITR,
- q_vector->tx.target_itr);
+ itr_idx = I40E_TX_ITR;
+ interval = q_vector->tx.target_itr;
q_vector->tx.current_itr = q_vector->tx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if (q_vector->rx.current_itr != q_vector->rx.target_itr) {
/* Rx ITR needs to be increased, third priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else {
/* No ITR update, lowest priority */
- intval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
if (q_vector->itr_countdown)
q_vector->itr_countdown--;
}
- if (!test_bit(__I40E_VSI_DOWN, vsi->state))
- wr32(hw, INTREG(q_vector->reg_idx), intval);
+ /* Do not update interrupt control register if VSI is down */
+ if (test_bit(__I40E_VSI_DOWN, vsi->state))
+ return;
+
+ /* Update ITR interval if necessary and enforce software interrupt
+ * if we are exiting busy poll.
+ */
+ if (q_vector->in_busy_poll) {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, true);
+ q_vector->in_busy_poll = false;
+ } else {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, false);
+ }
+ wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val);
}
/**
@@ -2845,6 +2883,8 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
*/
if (likely(napi_complete_done(napi, work_done)))
i40e_update_enable_itr(vsi, q_vector);
+ else
+ q_vector->in_busy_poll = true;
return min(work_done, budget - 1);
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index abf15067eb5d..2cdc7de6301c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -68,6 +68,7 @@ enum i40e_dyn_idx {
/* these are indexes into ITRN registers */
#define I40E_RX_ITR I40E_IDX_ITR0
#define I40E_TX_ITR I40E_IDX_ITR1
+#define I40E_SW_ITR I40E_IDX_ITR2
/* Supported RSS offloads */
#define I40E_DEFAULT_RSS_HENA ( \
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 ea558de7238bb12c3435c47f0631e9d17bf4a09f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040504-iron-respect-9ff0@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ea558de7238bb12c3435c47f0631e9d17bf4a09f Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera(a)redhat.com>
Date: Sat, 16 Mar 2024 12:38:29 +0100
Subject: [PATCH] i40e: Enforce software interrupt during busy-poll exit
As for ice bug fixed by commit b7306b42beaf ("ice: manage interrupts
during poll exit") followed by commit 23be7075b318 ("ice: fix software
generating extra interrupts") I'm seeing the similar issue also with
i40e driver.
In certain situation when busy-loop is enabled together with adaptive
coalescing, the driver occasionally misses that there are outstanding
descriptors to clean when exiting busy poll.
Try to catch the remaining work by triggering a software interrupt
when exiting busy poll. No extra interrupts will be generated when
busy polling is not used.
The issue was found when running sockperf ping-pong tcp test with
adaptive coalescing and busy poll enabled (50 as value busy_pool
and busy_read sysctl knobs) and results in huge latency spikes
with more than 100000us.
The fix is inspired from the ice driver and do the following:
1) During napi poll exit in case of busy-poll (napo_complete_done()
returns false) this is recorded to q_vector that we were in busy
loop.
2) Extends i40e_buildreg_itr() to be able to add an enforced software
interrupt into built value
2) In i40e_update_enable_itr() enforces a software interrupt trigger
if we are exiting busy poll to catch any pending clean-ups
3) Reuses unused 3rd ITR (interrupt throttle) index and set it to
20K interrupts per second to limit the number of these sw interrupts.
Test results
============
Prior:
[root@dell-per640-07 net]# sockperf ping-pong -i 10.9.9.1 --tcp -m 1000 --mps=max -t 120
sockperf: == version #3.10-no.git ==
sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
[ 0] IP = 10.9.9.1 PORT = 11111 # TCP
sockperf: Warmup stage (sending a few dummy messages)...
sockperf: Starting test...
sockperf: Test end (interrupted by timer)
sockperf: Test ended
sockperf: [Total Run] RunTime=119.999 sec; Warm up time=400 msec; SentMessages=2438563; ReceivedMessages=2438562
sockperf: ========= Printing statistics for Server No: 0
sockperf: [Valid Duration] RunTime=119.549 sec; SentMessages=2429473; ReceivedMessages=2429473
sockperf: ====> avg-latency=24.571 (std-dev=93.297, mean-ad=4.904, median-ad=1.510, siqr=1.063, cv=3.797, std-error=0.060, 99.0% ci=[24.417, 24.725])
sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
sockperf: Summary: Latency is 24.571 usec
sockperf: Total 2429473 observations; each percentile contains 24294.73 observations
sockperf: ---> <MAX> observation = 103294.331
sockperf: ---> percentile 99.999 = 45.633
sockperf: ---> percentile 99.990 = 37.013
sockperf: ---> percentile 99.900 = 35.910
sockperf: ---> percentile 99.000 = 33.390
sockperf: ---> percentile 90.000 = 28.626
sockperf: ---> percentile 75.000 = 27.741
sockperf: ---> percentile 50.000 = 26.743
sockperf: ---> percentile 25.000 = 25.614
sockperf: ---> <MIN> observation = 12.220
After:
[root@dell-per640-07 net]# sockperf ping-pong -i 10.9.9.1 --tcp -m 1000 --mps=max -t 120
sockperf: == version #3.10-no.git ==
sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
[ 0] IP = 10.9.9.1 PORT = 11111 # TCP
sockperf: Warmup stage (sending a few dummy messages)...
sockperf: Starting test...
sockperf: Test end (interrupted by timer)
sockperf: Test ended
sockperf: [Total Run] RunTime=119.999 sec; Warm up time=400 msec; SentMessages=2400055; ReceivedMessages=2400054
sockperf: ========= Printing statistics for Server No: 0
sockperf: [Valid Duration] RunTime=119.549 sec; SentMessages=2391186; ReceivedMessages=2391186
sockperf: ====> avg-latency=24.965 (std-dev=5.934, mean-ad=4.642, median-ad=1.485, siqr=1.067, cv=0.238, std-error=0.004, 99.0% ci=[24.955, 24.975])
sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
sockperf: Summary: Latency is 24.965 usec
sockperf: Total 2391186 observations; each percentile contains 23911.86 observations
sockperf: ---> <MAX> observation = 195.841
sockperf: ---> percentile 99.999 = 45.026
sockperf: ---> percentile 99.990 = 39.009
sockperf: ---> percentile 99.900 = 35.922
sockperf: ---> percentile 99.000 = 33.482
sockperf: ---> percentile 90.000 = 28.902
sockperf: ---> percentile 75.000 = 27.821
sockperf: ---> percentile 50.000 = 26.860
sockperf: ---> percentile 25.000 = 25.685
sockperf: ---> <MIN> observation = 12.277
Fixes: 0bcd952feec7 ("ethernet/intel: consolidate NAPI and NAPI exit")
Reported-by: Hugo Ferreira <hferreir(a)redhat.com>
Reviewed-by: Michal Schmidt <mschmidt(a)redhat.com>
Signed-off-by: Ivan Vecera <ivecera(a)redhat.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg(a)intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha(a)intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com>
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index ba24f3fa92c3..2fbabcdb5bb5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -955,6 +955,7 @@ struct i40e_q_vector {
struct rcu_head rcu; /* to avoid race with update stats on free */
char name[I40E_INT_NAME_STR_LEN];
bool arm_wb_state;
+ bool in_busy_poll;
int irq_num; /* IRQ assigned to this q_vector */
} ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f86578857e8a..6576a0081093 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3911,6 +3911,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
q_vector->tx.target_itr >> 1);
q_vector->tx.current_itr = q_vector->tx.target_itr;
+ /* Set ITR for software interrupts triggered after exiting
+ * busy-loop polling.
+ */
+ wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1),
+ I40E_ITR_20K);
+
wr32(hw, I40E_PFINT_RATEN(vector - 1),
i40e_intrl_usec_to_reg(vsi->int_rate_limit));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 14ab642cafdb..432afbb64201 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -333,8 +333,11 @@
#define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3
#define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT)
#define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5
+#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT)
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
#define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */
#define I40E_PFINT_ICR0_INTEVENT_SHIFT 0
#define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 0d7177083708..1a12b732818e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2630,7 +2630,22 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
return failure ? budget : (int)total_rx_packets;
}
-static inline u32 i40e_buildreg_itr(const int type, u16 itr)
+/**
+ * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register
+ * @itr_idx: interrupt throttling index
+ * @interval: interrupt throttling interval value in usecs
+ * @force_swint: force software interrupt
+ *
+ * The function builds a value for I40E_PFINT_DYN_CTLN register that
+ * is used to update interrupt throttling interval for specified ITR index
+ * and optionally enforces a software interrupt. If the @itr_idx is equal
+ * to I40E_ITR_NONE then no interval change is applied and only @force_swint
+ * parameter is taken into account. If the interval change and enforced
+ * software interrupt are not requested then the built value just enables
+ * appropriate vector interrupt.
+ **/
+static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval,
+ bool force_swint)
{
u32 val;
@@ -2644,23 +2659,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
* an event in the PBA anyway so we need to rely on the automask
* to hold pending events for us until the interrupt is re-enabled
*
- * The itr value is reported in microseconds, and the register
- * value is recorded in 2 microsecond units. For this reason we
- * only need to shift by the interval shift - 1 instead of the
- * full value.
+ * We have to shift the given value as it is reported in microseconds
+ * and the register value is recorded in 2 microsecond units.
*/
- itr &= I40E_ITR_MASK;
+ interval >>= 1;
+ /* 1. Enable vector interrupt
+ * 2. Update the interval for the specified ITR index
+ * (I40E_ITR_NONE in the register is used to indicate that
+ * no interval update is requested)
+ */
val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
- (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
- (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1));
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval);
+
+ /* 3. Enforce software interrupt trigger if requested
+ * (These software interrupts rate is limited by ITR2 that is
+ * set to 20K interrupts per second)
+ */
+ if (force_swint)
+ val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+ I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK,
+ I40E_SW_ITR);
return val;
}
-/* a small macro to shorten up some long lines */
-#define INTREG I40E_PFINT_DYN_CTLN
-
/* The act of updating the ITR will cause it to immediately trigger. In order
* to prevent this from throwing off adaptive update statistics we defer the
* update so that it can only happen so often. So after either Tx or Rx are
@@ -2679,8 +2704,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
struct i40e_q_vector *q_vector)
{
+ enum i40e_dyn_idx itr_idx = I40E_ITR_NONE;
struct i40e_hw *hw = &vsi->back->hw;
- u32 intval;
+ u16 interval = 0;
+ u32 itr_val;
/* If we don't have MSIX, then we only need to re-enable icr0 */
if (!test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) {
@@ -2702,8 +2729,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
*/
if (q_vector->rx.target_itr < q_vector->rx.current_itr) {
/* Rx ITR needs to be reduced, this is highest priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) ||
@@ -2712,25 +2739,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
/* Tx ITR needs to be reduced, this is second priority
* Tx ITR needs to be increased more than Rx, fourth priority
*/
- intval = i40e_buildreg_itr(I40E_TX_ITR,
- q_vector->tx.target_itr);
+ itr_idx = I40E_TX_ITR;
+ interval = q_vector->tx.target_itr;
q_vector->tx.current_itr = q_vector->tx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if (q_vector->rx.current_itr != q_vector->rx.target_itr) {
/* Rx ITR needs to be increased, third priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else {
/* No ITR update, lowest priority */
- intval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
if (q_vector->itr_countdown)
q_vector->itr_countdown--;
}
- if (!test_bit(__I40E_VSI_DOWN, vsi->state))
- wr32(hw, INTREG(q_vector->reg_idx), intval);
+ /* Do not update interrupt control register if VSI is down */
+ if (test_bit(__I40E_VSI_DOWN, vsi->state))
+ return;
+
+ /* Update ITR interval if necessary and enforce software interrupt
+ * if we are exiting busy poll.
+ */
+ if (q_vector->in_busy_poll) {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, true);
+ q_vector->in_busy_poll = false;
+ } else {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, false);
+ }
+ wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val);
}
/**
@@ -2845,6 +2883,8 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
*/
if (likely(napi_complete_done(napi, work_done)))
i40e_update_enable_itr(vsi, q_vector);
+ else
+ q_vector->in_busy_poll = true;
return min(work_done, budget - 1);
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index abf15067eb5d..2cdc7de6301c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -68,6 +68,7 @@ enum i40e_dyn_idx {
/* these are indexes into ITRN registers */
#define I40E_RX_ITR I40E_IDX_ITR0
#define I40E_TX_ITR I40E_IDX_ITR1
+#define I40E_SW_ITR I40E_IDX_ITR2
/* Supported RSS offloads */
#define I40E_DEFAULT_RSS_HENA ( \
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 ea558de7238bb12c3435c47f0631e9d17bf4a09f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040500-scalping-relatable-1383@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ea558de7238bb12c3435c47f0631e9d17bf4a09f Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera(a)redhat.com>
Date: Sat, 16 Mar 2024 12:38:29 +0100
Subject: [PATCH] i40e: Enforce software interrupt during busy-poll exit
As for ice bug fixed by commit b7306b42beaf ("ice: manage interrupts
during poll exit") followed by commit 23be7075b318 ("ice: fix software
generating extra interrupts") I'm seeing the similar issue also with
i40e driver.
In certain situation when busy-loop is enabled together with adaptive
coalescing, the driver occasionally misses that there are outstanding
descriptors to clean when exiting busy poll.
Try to catch the remaining work by triggering a software interrupt
when exiting busy poll. No extra interrupts will be generated when
busy polling is not used.
The issue was found when running sockperf ping-pong tcp test with
adaptive coalescing and busy poll enabled (50 as value busy_pool
and busy_read sysctl knobs) and results in huge latency spikes
with more than 100000us.
The fix is inspired from the ice driver and do the following:
1) During napi poll exit in case of busy-poll (napo_complete_done()
returns false) this is recorded to q_vector that we were in busy
loop.
2) Extends i40e_buildreg_itr() to be able to add an enforced software
interrupt into built value
2) In i40e_update_enable_itr() enforces a software interrupt trigger
if we are exiting busy poll to catch any pending clean-ups
3) Reuses unused 3rd ITR (interrupt throttle) index and set it to
20K interrupts per second to limit the number of these sw interrupts.
Test results
============
Prior:
[root@dell-per640-07 net]# sockperf ping-pong -i 10.9.9.1 --tcp -m 1000 --mps=max -t 120
sockperf: == version #3.10-no.git ==
sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
[ 0] IP = 10.9.9.1 PORT = 11111 # TCP
sockperf: Warmup stage (sending a few dummy messages)...
sockperf: Starting test...
sockperf: Test end (interrupted by timer)
sockperf: Test ended
sockperf: [Total Run] RunTime=119.999 sec; Warm up time=400 msec; SentMessages=2438563; ReceivedMessages=2438562
sockperf: ========= Printing statistics for Server No: 0
sockperf: [Valid Duration] RunTime=119.549 sec; SentMessages=2429473; ReceivedMessages=2429473
sockperf: ====> avg-latency=24.571 (std-dev=93.297, mean-ad=4.904, median-ad=1.510, siqr=1.063, cv=3.797, std-error=0.060, 99.0% ci=[24.417, 24.725])
sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
sockperf: Summary: Latency is 24.571 usec
sockperf: Total 2429473 observations; each percentile contains 24294.73 observations
sockperf: ---> <MAX> observation = 103294.331
sockperf: ---> percentile 99.999 = 45.633
sockperf: ---> percentile 99.990 = 37.013
sockperf: ---> percentile 99.900 = 35.910
sockperf: ---> percentile 99.000 = 33.390
sockperf: ---> percentile 90.000 = 28.626
sockperf: ---> percentile 75.000 = 27.741
sockperf: ---> percentile 50.000 = 26.743
sockperf: ---> percentile 25.000 = 25.614
sockperf: ---> <MIN> observation = 12.220
After:
[root@dell-per640-07 net]# sockperf ping-pong -i 10.9.9.1 --tcp -m 1000 --mps=max -t 120
sockperf: == version #3.10-no.git ==
sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
[ 0] IP = 10.9.9.1 PORT = 11111 # TCP
sockperf: Warmup stage (sending a few dummy messages)...
sockperf: Starting test...
sockperf: Test end (interrupted by timer)
sockperf: Test ended
sockperf: [Total Run] RunTime=119.999 sec; Warm up time=400 msec; SentMessages=2400055; ReceivedMessages=2400054
sockperf: ========= Printing statistics for Server No: 0
sockperf: [Valid Duration] RunTime=119.549 sec; SentMessages=2391186; ReceivedMessages=2391186
sockperf: ====> avg-latency=24.965 (std-dev=5.934, mean-ad=4.642, median-ad=1.485, siqr=1.067, cv=0.238, std-error=0.004, 99.0% ci=[24.955, 24.975])
sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
sockperf: Summary: Latency is 24.965 usec
sockperf: Total 2391186 observations; each percentile contains 23911.86 observations
sockperf: ---> <MAX> observation = 195.841
sockperf: ---> percentile 99.999 = 45.026
sockperf: ---> percentile 99.990 = 39.009
sockperf: ---> percentile 99.900 = 35.922
sockperf: ---> percentile 99.000 = 33.482
sockperf: ---> percentile 90.000 = 28.902
sockperf: ---> percentile 75.000 = 27.821
sockperf: ---> percentile 50.000 = 26.860
sockperf: ---> percentile 25.000 = 25.685
sockperf: ---> <MIN> observation = 12.277
Fixes: 0bcd952feec7 ("ethernet/intel: consolidate NAPI and NAPI exit")
Reported-by: Hugo Ferreira <hferreir(a)redhat.com>
Reviewed-by: Michal Schmidt <mschmidt(a)redhat.com>
Signed-off-by: Ivan Vecera <ivecera(a)redhat.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg(a)intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha(a)intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com>
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index ba24f3fa92c3..2fbabcdb5bb5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -955,6 +955,7 @@ struct i40e_q_vector {
struct rcu_head rcu; /* to avoid race with update stats on free */
char name[I40E_INT_NAME_STR_LEN];
bool arm_wb_state;
+ bool in_busy_poll;
int irq_num; /* IRQ assigned to this q_vector */
} ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f86578857e8a..6576a0081093 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3911,6 +3911,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
q_vector->tx.target_itr >> 1);
q_vector->tx.current_itr = q_vector->tx.target_itr;
+ /* Set ITR for software interrupts triggered after exiting
+ * busy-loop polling.
+ */
+ wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1),
+ I40E_ITR_20K);
+
wr32(hw, I40E_PFINT_RATEN(vector - 1),
i40e_intrl_usec_to_reg(vsi->int_rate_limit));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 14ab642cafdb..432afbb64201 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -333,8 +333,11 @@
#define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3
#define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT)
#define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5
+#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT)
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
#define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */
#define I40E_PFINT_ICR0_INTEVENT_SHIFT 0
#define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 0d7177083708..1a12b732818e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2630,7 +2630,22 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
return failure ? budget : (int)total_rx_packets;
}
-static inline u32 i40e_buildreg_itr(const int type, u16 itr)
+/**
+ * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register
+ * @itr_idx: interrupt throttling index
+ * @interval: interrupt throttling interval value in usecs
+ * @force_swint: force software interrupt
+ *
+ * The function builds a value for I40E_PFINT_DYN_CTLN register that
+ * is used to update interrupt throttling interval for specified ITR index
+ * and optionally enforces a software interrupt. If the @itr_idx is equal
+ * to I40E_ITR_NONE then no interval change is applied and only @force_swint
+ * parameter is taken into account. If the interval change and enforced
+ * software interrupt are not requested then the built value just enables
+ * appropriate vector interrupt.
+ **/
+static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval,
+ bool force_swint)
{
u32 val;
@@ -2644,23 +2659,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
* an event in the PBA anyway so we need to rely on the automask
* to hold pending events for us until the interrupt is re-enabled
*
- * The itr value is reported in microseconds, and the register
- * value is recorded in 2 microsecond units. For this reason we
- * only need to shift by the interval shift - 1 instead of the
- * full value.
+ * We have to shift the given value as it is reported in microseconds
+ * and the register value is recorded in 2 microsecond units.
*/
- itr &= I40E_ITR_MASK;
+ interval >>= 1;
+ /* 1. Enable vector interrupt
+ * 2. Update the interval for the specified ITR index
+ * (I40E_ITR_NONE in the register is used to indicate that
+ * no interval update is requested)
+ */
val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
- (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
- (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1));
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval);
+
+ /* 3. Enforce software interrupt trigger if requested
+ * (These software interrupts rate is limited by ITR2 that is
+ * set to 20K interrupts per second)
+ */
+ if (force_swint)
+ val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+ I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK,
+ I40E_SW_ITR);
return val;
}
-/* a small macro to shorten up some long lines */
-#define INTREG I40E_PFINT_DYN_CTLN
-
/* The act of updating the ITR will cause it to immediately trigger. In order
* to prevent this from throwing off adaptive update statistics we defer the
* update so that it can only happen so often. So after either Tx or Rx are
@@ -2679,8 +2704,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
struct i40e_q_vector *q_vector)
{
+ enum i40e_dyn_idx itr_idx = I40E_ITR_NONE;
struct i40e_hw *hw = &vsi->back->hw;
- u32 intval;
+ u16 interval = 0;
+ u32 itr_val;
/* If we don't have MSIX, then we only need to re-enable icr0 */
if (!test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) {
@@ -2702,8 +2729,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
*/
if (q_vector->rx.target_itr < q_vector->rx.current_itr) {
/* Rx ITR needs to be reduced, this is highest priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) ||
@@ -2712,25 +2739,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
/* Tx ITR needs to be reduced, this is second priority
* Tx ITR needs to be increased more than Rx, fourth priority
*/
- intval = i40e_buildreg_itr(I40E_TX_ITR,
- q_vector->tx.target_itr);
+ itr_idx = I40E_TX_ITR;
+ interval = q_vector->tx.target_itr;
q_vector->tx.current_itr = q_vector->tx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if (q_vector->rx.current_itr != q_vector->rx.target_itr) {
/* Rx ITR needs to be increased, third priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else {
/* No ITR update, lowest priority */
- intval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
if (q_vector->itr_countdown)
q_vector->itr_countdown--;
}
- if (!test_bit(__I40E_VSI_DOWN, vsi->state))
- wr32(hw, INTREG(q_vector->reg_idx), intval);
+ /* Do not update interrupt control register if VSI is down */
+ if (test_bit(__I40E_VSI_DOWN, vsi->state))
+ return;
+
+ /* Update ITR interval if necessary and enforce software interrupt
+ * if we are exiting busy poll.
+ */
+ if (q_vector->in_busy_poll) {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, true);
+ q_vector->in_busy_poll = false;
+ } else {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, false);
+ }
+ wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val);
}
/**
@@ -2845,6 +2883,8 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
*/
if (likely(napi_complete_done(napi, work_done)))
i40e_update_enable_itr(vsi, q_vector);
+ else
+ q_vector->in_busy_poll = true;
return min(work_done, budget - 1);
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index abf15067eb5d..2cdc7de6301c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -68,6 +68,7 @@ enum i40e_dyn_idx {
/* these are indexes into ITRN registers */
#define I40E_RX_ITR I40E_IDX_ITR0
#define I40E_TX_ITR I40E_IDX_ITR1
+#define I40E_SW_ITR I40E_IDX_ITR2
/* Supported RSS offloads */
#define I40E_DEFAULT_RSS_HENA ( \
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 ef15ddeeb6bee87c044bf7754fac524545bf71e8
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040558-trustee-garage-e392@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ef15ddeeb6bee87c044bf7754fac524545bf71e8 Mon Sep 17 00:00:00 2001
From: Aleksandr Mishin <amishin(a)t-argos.ru>
Date: Thu, 28 Mar 2024 19:55:05 +0300
Subject: [PATCH] octeontx2-af: Add array index check
In rvu_map_cgx_lmac_pf() the 'iter', which is used as an array index, can reach
value (up to 14) that exceed the size (MAX_LMAC_COUNT = 8) of the array.
Fix this bug by adding 'iter' value check.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: 91c6945ea1f9 ("octeontx2-af: cn10k: Add RPM MAC support")
Signed-off-by: Aleksandr Mishin <amishin(a)t-argos.ru>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 72e060cf6b61..e9bf9231b018 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -160,6 +160,8 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
continue;
lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu));
for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) {
+ if (iter >= MAX_LMAC_COUNT)
+ continue;
lmac = cgx_get_lmacid(rvu_cgx_pdata(cgx, rvu),
iter);
rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac);
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 861e8086029e003305750b4126ecd6617465f5c7
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040539-fiber-dormitory-6321@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 861e8086029e003305750b4126ecd6617465f5c7 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits(a)intel.com>
Date: Sun, 3 Mar 2024 12:51:32 +0200
Subject: [PATCH] e1000e: move force SMBUS from enable ulp function to avoid
PHY loss issue
Forcing SMBUS inside the ULP enabling flow leads to sporadic PHY loss on
some systems. It is suspected to be caused by initiating PHY transactions
before the interface settles.
Separating this configuration from the ULP enabling flow and moving it to
the shutdown function allows enough time for the interface to settle and
avoids adding a delay.
Fixes: 6607c99e7034 ("e1000e: i219 - fix to enable both ULP and EEE in Sx state")
Co-developed-by: Dima Ruinskiy <dima.ruinskiy(a)intel.com>
Signed-off-by: Dima Ruinskiy <dima.ruinskiy(a)intel.com>
Signed-off-by: Vitaly Lifshits <vitaly.lifshits(a)intel.com>
Tested-by: Naama Meir <naamax.meir(a)linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com>
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index d8e97669f31b..f9e94be36e97 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1165,25 +1165,6 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx)
if (ret_val)
goto out;
- /* Switching PHY interface always returns MDI error
- * so disable retry mechanism to avoid wasting time
- */
- e1000e_disable_phy_retry(hw);
-
- /* Force SMBus mode in PHY */
- ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
- if (ret_val)
- goto release;
- phy_reg |= CV_SMB_CTRL_FORCE_SMBUS;
- e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
-
- e1000e_enable_phy_retry(hw);
-
- /* Force SMBus mode in MAC */
- mac_reg = er32(CTRL_EXT);
- mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
- ew32(CTRL_EXT, mac_reg);
-
/* Si workaround for ULP entry flow on i127/rev6 h/w. Enable
* LPLU and disable Gig speed when entering ULP
*/
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index cc8c531ec3df..3692fce20195 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6623,6 +6623,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
struct e1000_hw *hw = &adapter->hw;
u32 ctrl, ctrl_ext, rctl, status, wufc;
int retval = 0;
+ u16 smb_ctrl;
/* Runtime suspend should only enable wakeup for link changes */
if (runtime)
@@ -6696,6 +6697,23 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
if (retval)
return retval;
}
+
+ /* Force SMBUS to allow WOL */
+ /* Switching PHY interface always returns MDI error
+ * so disable retry mechanism to avoid wasting time
+ */
+ e1000e_disable_phy_retry(hw);
+
+ e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl);
+ smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS;
+ e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl);
+
+ e1000e_enable_phy_retry(hw);
+
+ /* Force SMBus mode in MAC */
+ ctrl_ext = er32(CTRL_EXT);
+ ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS;
+ ew32(CTRL_EXT, ctrl_ext);
}
/* Ensure that the appropriate bits are set in LPI_CTRL
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 861e8086029e003305750b4126ecd6617465f5c7
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024040536-paying-life-0a32@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 861e8086029e003305750b4126ecd6617465f5c7 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits(a)intel.com>
Date: Sun, 3 Mar 2024 12:51:32 +0200
Subject: [PATCH] e1000e: move force SMBUS from enable ulp function to avoid
PHY loss issue
Forcing SMBUS inside the ULP enabling flow leads to sporadic PHY loss on
some systems. It is suspected to be caused by initiating PHY transactions
before the interface settles.
Separating this configuration from the ULP enabling flow and moving it to
the shutdown function allows enough time for the interface to settle and
avoids adding a delay.
Fixes: 6607c99e7034 ("e1000e: i219 - fix to enable both ULP and EEE in Sx state")
Co-developed-by: Dima Ruinskiy <dima.ruinskiy(a)intel.com>
Signed-off-by: Dima Ruinskiy <dima.ruinskiy(a)intel.com>
Signed-off-by: Vitaly Lifshits <vitaly.lifshits(a)intel.com>
Tested-by: Naama Meir <naamax.meir(a)linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com>
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index d8e97669f31b..f9e94be36e97 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1165,25 +1165,6 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx)
if (ret_val)
goto out;
- /* Switching PHY interface always returns MDI error
- * so disable retry mechanism to avoid wasting time
- */
- e1000e_disable_phy_retry(hw);
-
- /* Force SMBus mode in PHY */
- ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
- if (ret_val)
- goto release;
- phy_reg |= CV_SMB_CTRL_FORCE_SMBUS;
- e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
-
- e1000e_enable_phy_retry(hw);
-
- /* Force SMBus mode in MAC */
- mac_reg = er32(CTRL_EXT);
- mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
- ew32(CTRL_EXT, mac_reg);
-
/* Si workaround for ULP entry flow on i127/rev6 h/w. Enable
* LPLU and disable Gig speed when entering ULP
*/
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index cc8c531ec3df..3692fce20195 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6623,6 +6623,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
struct e1000_hw *hw = &adapter->hw;
u32 ctrl, ctrl_ext, rctl, status, wufc;
int retval = 0;
+ u16 smb_ctrl;
/* Runtime suspend should only enable wakeup for link changes */
if (runtime)
@@ -6696,6 +6697,23 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
if (retval)
return retval;
}
+
+ /* Force SMBUS to allow WOL */
+ /* Switching PHY interface always returns MDI error
+ * so disable retry mechanism to avoid wasting time
+ */
+ e1000e_disable_phy_retry(hw);
+
+ e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl);
+ smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS;
+ e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl);
+
+ e1000e_enable_phy_retry(hw);
+
+ /* Force SMBus mode in MAC */
+ ctrl_ext = er32(CTRL_EXT);
+ ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS;
+ ew32(CTRL_EXT, ctrl_ext);
}
/* Ensure that the appropriate bits are set in LPI_CTRL