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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 55e8c8eb2c7b6bf30e99423ccfe7ca032f498f59 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm(a)xmission.com>
Date: Fri, 28 Feb 2020 11:11:06 -0600
Subject: [PATCH] posix-cpu-timers: Store a reference to a pid not a task
posix cpu timers do not handle the death of a process well.
This is most clearly seen when a multi-threaded process calls exec from a
thread that is not the leader of the thread group. The posix cpu timer code
continues to pin the old thread group leader and is unable to find the
siglock from there.
This results in posix_cpu_timer_del being unable to delete a timer,
posix_cpu_timer_set being unable to set a timer. Further to compensate for
the problems in posix_cpu_timer_del on a multi-threaded exec all timers
that point at the multi-threaded task are stopped.
The code for the timers fundamentally needs to check if the target
process/thread is alive. This needs an extra level of indirection. This
level of indirection is already available in struct pid.
So replace cpu.task with cpu.pid to get the needed extra layer of
indirection.
In addition to handling things more cleanly this reduces the amount of
memory a timer can pin when a process exits and then is reaped from
a task_struct to the vastly smaller struct pid.
Fixes: e0a70217107e ("posix-cpu-timers: workaround to suppress the problems with mt exec")
Signed-off-by: "Eric W. Biederman" <ebiederm(a)xmission.com>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Link: https://lkml.kernel.org/r/87wo86tz6d.fsf@x220.int.ebiederm.org
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 3d10c84a97a9..e3f0f8585da4 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -69,7 +69,7 @@ static inline int clockid_to_fd(const clockid_t clk)
struct cpu_timer {
struct timerqueue_node node;
struct timerqueue_head *head;
- struct task_struct *task;
+ struct pid *pid;
struct list_head elist;
int firing;
};
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index ef936c5a910b..6df468a622fe 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -118,6 +118,16 @@ static inline int validate_clock_permissions(const clockid_t clock)
return __get_task_for_clock(clock, false, false) ? 0 : -EINVAL;
}
+static inline enum pid_type cpu_timer_pid_type(struct k_itimer *timer)
+{
+ return CPUCLOCK_PERTHREAD(timer->it_clock) ? PIDTYPE_PID : PIDTYPE_TGID;
+}
+
+static inline struct task_struct *cpu_timer_task_rcu(struct k_itimer *timer)
+{
+ return pid_task(timer->it.cpu.pid, cpu_timer_pid_type(timer));
+}
+
/*
* Update expiry time from increment, and increase overrun count,
* given the current clock sample.
@@ -391,7 +401,12 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
new_timer->kclock = &clock_posix_cpu;
timerqueue_init(&new_timer->it.cpu.node);
- new_timer->it.cpu.task = p;
+ new_timer->it.cpu.pid = get_task_pid(p, cpu_timer_pid_type(new_timer));
+ /*
+ * get_task_for_clock() took a reference on @p. Drop it as the timer
+ * holds a reference on the pid of @p.
+ */
+ put_task_struct(p);
return 0;
}
@@ -404,13 +419,15 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
static int posix_cpu_timer_del(struct k_itimer *timer)
{
struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
struct sighand_struct *sighand;
+ struct task_struct *p;
unsigned long flags;
int ret = 0;
- if (WARN_ON_ONCE(!p))
- return -EINVAL;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Protect against sighand release/switch in exit/exec and process/
@@ -432,8 +449,10 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
unlock_task_sighand(p, &flags);
}
+out:
+ rcu_read_unlock();
if (!ret)
- put_task_struct(p);
+ put_pid(ctmr->pid);
return ret;
}
@@ -561,13 +580,21 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
u64 old_expires, new_expires, old_incr, val;
struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
struct sighand_struct *sighand;
+ struct task_struct *p;
unsigned long flags;
int ret = 0;
- if (WARN_ON_ONCE(!p))
- return -EINVAL;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p) {
+ /*
+ * If p has just been reaped, we can no
+ * longer get any information about it at all.
+ */
+ rcu_read_unlock();
+ return -ESRCH;
+ }
/*
* Use the to_ktime conversion because that clamps the maximum
@@ -584,8 +611,10 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
* If p has just been reaped, we can no
* longer get any information about it at all.
*/
- if (unlikely(sighand == NULL))
+ if (unlikely(sighand == NULL)) {
+ rcu_read_unlock();
return -ESRCH;
+ }
/*
* Disarm any old timer after extracting its expiry time.
@@ -690,6 +719,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
ret = 0;
out:
+ rcu_read_unlock();
if (old)
old->it_interval = ns_to_timespec64(old_incr);
@@ -701,10 +731,12 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
struct cpu_timer *ctmr = &timer->it.cpu;
u64 now, expires = cpu_timer_getexpires(ctmr);
- struct task_struct *p = ctmr->task;
+ struct task_struct *p;
- if (WARN_ON_ONCE(!p))
- return;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Easy part: convert the reload time.
@@ -712,7 +744,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
itp->it_interval = ktime_to_timespec64(timer->it_interval);
if (!expires)
- return;
+ goto out;
/*
* Sample the clock to take the difference with the expiry time.
@@ -732,6 +764,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
itp->it_value.tv_nsec = 1;
itp->it_value.tv_sec = 0;
}
+out:
+ rcu_read_unlock();
}
#define MAX_COLLECTED 20
@@ -952,14 +986,15 @@ static void check_process_timers(struct task_struct *tsk,
static void posix_cpu_timer_rearm(struct k_itimer *timer)
{
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
- struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
+ struct task_struct *p;
struct sighand_struct *sighand;
unsigned long flags;
u64 now;
- if (WARN_ON_ONCE(!p))
- return;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Fetch the current sample and update the timer's expiry time.
@@ -974,13 +1009,15 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
/* Protect timer list r/w in arm_timer() */
sighand = lock_task_sighand(p, &flags);
if (unlikely(sighand == NULL))
- return;
+ goto out;
/*
* Now re-arm for the new expiry time.
*/
arm_timer(timer, p);
unlock_task_sighand(p, &flags);
+out:
+ rcu_read_unlock();
}
/**
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 55e8c8eb2c7b6bf30e99423ccfe7ca032f498f59 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm(a)xmission.com>
Date: Fri, 28 Feb 2020 11:11:06 -0600
Subject: [PATCH] posix-cpu-timers: Store a reference to a pid not a task
posix cpu timers do not handle the death of a process well.
This is most clearly seen when a multi-threaded process calls exec from a
thread that is not the leader of the thread group. The posix cpu timer code
continues to pin the old thread group leader and is unable to find the
siglock from there.
This results in posix_cpu_timer_del being unable to delete a timer,
posix_cpu_timer_set being unable to set a timer. Further to compensate for
the problems in posix_cpu_timer_del on a multi-threaded exec all timers
that point at the multi-threaded task are stopped.
The code for the timers fundamentally needs to check if the target
process/thread is alive. This needs an extra level of indirection. This
level of indirection is already available in struct pid.
So replace cpu.task with cpu.pid to get the needed extra layer of
indirection.
In addition to handling things more cleanly this reduces the amount of
memory a timer can pin when a process exits and then is reaped from
a task_struct to the vastly smaller struct pid.
Fixes: e0a70217107e ("posix-cpu-timers: workaround to suppress the problems with mt exec")
Signed-off-by: "Eric W. Biederman" <ebiederm(a)xmission.com>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Link: https://lkml.kernel.org/r/87wo86tz6d.fsf@x220.int.ebiederm.org
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 3d10c84a97a9..e3f0f8585da4 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -69,7 +69,7 @@ static inline int clockid_to_fd(const clockid_t clk)
struct cpu_timer {
struct timerqueue_node node;
struct timerqueue_head *head;
- struct task_struct *task;
+ struct pid *pid;
struct list_head elist;
int firing;
};
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index ef936c5a910b..6df468a622fe 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -118,6 +118,16 @@ static inline int validate_clock_permissions(const clockid_t clock)
return __get_task_for_clock(clock, false, false) ? 0 : -EINVAL;
}
+static inline enum pid_type cpu_timer_pid_type(struct k_itimer *timer)
+{
+ return CPUCLOCK_PERTHREAD(timer->it_clock) ? PIDTYPE_PID : PIDTYPE_TGID;
+}
+
+static inline struct task_struct *cpu_timer_task_rcu(struct k_itimer *timer)
+{
+ return pid_task(timer->it.cpu.pid, cpu_timer_pid_type(timer));
+}
+
/*
* Update expiry time from increment, and increase overrun count,
* given the current clock sample.
@@ -391,7 +401,12 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
new_timer->kclock = &clock_posix_cpu;
timerqueue_init(&new_timer->it.cpu.node);
- new_timer->it.cpu.task = p;
+ new_timer->it.cpu.pid = get_task_pid(p, cpu_timer_pid_type(new_timer));
+ /*
+ * get_task_for_clock() took a reference on @p. Drop it as the timer
+ * holds a reference on the pid of @p.
+ */
+ put_task_struct(p);
return 0;
}
@@ -404,13 +419,15 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
static int posix_cpu_timer_del(struct k_itimer *timer)
{
struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
struct sighand_struct *sighand;
+ struct task_struct *p;
unsigned long flags;
int ret = 0;
- if (WARN_ON_ONCE(!p))
- return -EINVAL;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Protect against sighand release/switch in exit/exec and process/
@@ -432,8 +449,10 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
unlock_task_sighand(p, &flags);
}
+out:
+ rcu_read_unlock();
if (!ret)
- put_task_struct(p);
+ put_pid(ctmr->pid);
return ret;
}
@@ -561,13 +580,21 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
u64 old_expires, new_expires, old_incr, val;
struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
struct sighand_struct *sighand;
+ struct task_struct *p;
unsigned long flags;
int ret = 0;
- if (WARN_ON_ONCE(!p))
- return -EINVAL;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p) {
+ /*
+ * If p has just been reaped, we can no
+ * longer get any information about it at all.
+ */
+ rcu_read_unlock();
+ return -ESRCH;
+ }
/*
* Use the to_ktime conversion because that clamps the maximum
@@ -584,8 +611,10 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
* If p has just been reaped, we can no
* longer get any information about it at all.
*/
- if (unlikely(sighand == NULL))
+ if (unlikely(sighand == NULL)) {
+ rcu_read_unlock();
return -ESRCH;
+ }
/*
* Disarm any old timer after extracting its expiry time.
@@ -690,6 +719,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
ret = 0;
out:
+ rcu_read_unlock();
if (old)
old->it_interval = ns_to_timespec64(old_incr);
@@ -701,10 +731,12 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
struct cpu_timer *ctmr = &timer->it.cpu;
u64 now, expires = cpu_timer_getexpires(ctmr);
- struct task_struct *p = ctmr->task;
+ struct task_struct *p;
- if (WARN_ON_ONCE(!p))
- return;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Easy part: convert the reload time.
@@ -712,7 +744,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
itp->it_interval = ktime_to_timespec64(timer->it_interval);
if (!expires)
- return;
+ goto out;
/*
* Sample the clock to take the difference with the expiry time.
@@ -732,6 +764,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
itp->it_value.tv_nsec = 1;
itp->it_value.tv_sec = 0;
}
+out:
+ rcu_read_unlock();
}
#define MAX_COLLECTED 20
@@ -952,14 +986,15 @@ static void check_process_timers(struct task_struct *tsk,
static void posix_cpu_timer_rearm(struct k_itimer *timer)
{
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
- struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
+ struct task_struct *p;
struct sighand_struct *sighand;
unsigned long flags;
u64 now;
- if (WARN_ON_ONCE(!p))
- return;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Fetch the current sample and update the timer's expiry time.
@@ -974,13 +1009,15 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
/* Protect timer list r/w in arm_timer() */
sighand = lock_task_sighand(p, &flags);
if (unlikely(sighand == NULL))
- return;
+ goto out;
/*
* Now re-arm for the new expiry time.
*/
arm_timer(timer, p);
unlock_task_sighand(p, &flags);
+out:
+ rcu_read_unlock();
}
/**
The patch below does not apply to the 4.9-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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From fe867cac9e1967c553e4ac2aece5fc8675258010 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi(a)mellanox.com>
Date: Mon, 4 Nov 2019 12:02:14 +0200
Subject: [PATCH] net/mlx5e: Use preactivate hook to set the indirection table
mlx5e_ethtool_set_channels updates the indirection table before
switching to the new channels. If the switch fails, the indirection
table is new, but the channels are old, which is wrong. Fix it by using
the preactivate hook of mlx5e_safe_switch_channels to update the
indirection table at the stage when nothing can fail anymore.
As the code that updates the indirection table is now encapsulated into
a new function, use that function in the attach flow when the driver has
to reduce the number of channels, and prepare the code for the next
commit.
Fixes: 85082dba0a ("net/mlx5e: Correctly handle RSS indirection table when changing number of channels")
Signed-off-by: Maxim Mikityanskiy <maximmi(a)mellanox.com>
Reviewed-by: Tariq Toukan <tariqt(a)mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm(a)mellanox.com>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index bc2c96b34de1..4ddccab02a4b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1043,6 +1043,7 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
struct mlx5e_channels *new_chs,
mlx5e_fp_preactivate preactivate);
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv);
void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 68b520df07e4..ff7f5a931520 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -432,9 +432,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
*cur_params = new_channels.params;
- if (!netif_is_rxfh_configured(priv->netdev))
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
+ mlx5e_num_channels_changed(priv);
goto out;
}
@@ -442,12 +440,8 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
if (arfs_enabled)
mlx5e_arfs_disable(priv);
- if (!netif_is_rxfh_configured(priv->netdev))
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
-
/* Switch to new channels, set new parameters and close old ones */
- err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+ err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_num_channels_changed);
if (arfs_enabled) {
int err2 = mlx5e_arfs_enable(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 152aa5d7df79..bbe8c32fb423 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2880,6 +2880,17 @@ static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
netif_set_real_num_rx_queues(netdev, num_rxqs);
}
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
+{
+ u16 count = priv->channels.params.num_channels;
+
+ if (!netif_is_rxfh_configured(priv->netdev))
+ mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+ MLX5E_INDIR_RQT_SIZE, count);
+
+ return 0;
+}
+
static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
{
int i, ch;
@@ -5288,9 +5299,10 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
max_nch = mlx5e_get_max_num_channels(priv->mdev);
if (priv->channels.params.num_channels > max_nch) {
mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
+ /* Reducing the number of channels - RXFH has to be reset. */
+ priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED;
priv->channels.params.num_channels = max_nch;
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, max_nch);
+ mlx5e_num_channels_changed(priv);
}
err = profile->init_tx(priv);
The patch below does not apply to the 4.4-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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From fe867cac9e1967c553e4ac2aece5fc8675258010 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi(a)mellanox.com>
Date: Mon, 4 Nov 2019 12:02:14 +0200
Subject: [PATCH] net/mlx5e: Use preactivate hook to set the indirection table
mlx5e_ethtool_set_channels updates the indirection table before
switching to the new channels. If the switch fails, the indirection
table is new, but the channels are old, which is wrong. Fix it by using
the preactivate hook of mlx5e_safe_switch_channels to update the
indirection table at the stage when nothing can fail anymore.
As the code that updates the indirection table is now encapsulated into
a new function, use that function in the attach flow when the driver has
to reduce the number of channels, and prepare the code for the next
commit.
Fixes: 85082dba0a ("net/mlx5e: Correctly handle RSS indirection table when changing number of channels")
Signed-off-by: Maxim Mikityanskiy <maximmi(a)mellanox.com>
Reviewed-by: Tariq Toukan <tariqt(a)mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm(a)mellanox.com>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index bc2c96b34de1..4ddccab02a4b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1043,6 +1043,7 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
struct mlx5e_channels *new_chs,
mlx5e_fp_preactivate preactivate);
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv);
void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 68b520df07e4..ff7f5a931520 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -432,9 +432,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
*cur_params = new_channels.params;
- if (!netif_is_rxfh_configured(priv->netdev))
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
+ mlx5e_num_channels_changed(priv);
goto out;
}
@@ -442,12 +440,8 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
if (arfs_enabled)
mlx5e_arfs_disable(priv);
- if (!netif_is_rxfh_configured(priv->netdev))
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
-
/* Switch to new channels, set new parameters and close old ones */
- err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+ err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_num_channels_changed);
if (arfs_enabled) {
int err2 = mlx5e_arfs_enable(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 152aa5d7df79..bbe8c32fb423 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2880,6 +2880,17 @@ static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
netif_set_real_num_rx_queues(netdev, num_rxqs);
}
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
+{
+ u16 count = priv->channels.params.num_channels;
+
+ if (!netif_is_rxfh_configured(priv->netdev))
+ mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+ MLX5E_INDIR_RQT_SIZE, count);
+
+ return 0;
+}
+
static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
{
int i, ch;
@@ -5288,9 +5299,10 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
max_nch = mlx5e_get_max_num_channels(priv->mdev);
if (priv->channels.params.num_channels > max_nch) {
mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
+ /* Reducing the number of channels - RXFH has to be reset. */
+ priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED;
priv->channels.params.num_channels = max_nch;
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, max_nch);
+ mlx5e_num_channels_changed(priv);
}
err = profile->init_tx(priv);
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From fe867cac9e1967c553e4ac2aece5fc8675258010 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi(a)mellanox.com>
Date: Mon, 4 Nov 2019 12:02:14 +0200
Subject: [PATCH] net/mlx5e: Use preactivate hook to set the indirection table
mlx5e_ethtool_set_channels updates the indirection table before
switching to the new channels. If the switch fails, the indirection
table is new, but the channels are old, which is wrong. Fix it by using
the preactivate hook of mlx5e_safe_switch_channels to update the
indirection table at the stage when nothing can fail anymore.
As the code that updates the indirection table is now encapsulated into
a new function, use that function in the attach flow when the driver has
to reduce the number of channels, and prepare the code for the next
commit.
Fixes: 85082dba0a ("net/mlx5e: Correctly handle RSS indirection table when changing number of channels")
Signed-off-by: Maxim Mikityanskiy <maximmi(a)mellanox.com>
Reviewed-by: Tariq Toukan <tariqt(a)mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm(a)mellanox.com>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index bc2c96b34de1..4ddccab02a4b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1043,6 +1043,7 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
struct mlx5e_channels *new_chs,
mlx5e_fp_preactivate preactivate);
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv);
void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 68b520df07e4..ff7f5a931520 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -432,9 +432,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
*cur_params = new_channels.params;
- if (!netif_is_rxfh_configured(priv->netdev))
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
+ mlx5e_num_channels_changed(priv);
goto out;
}
@@ -442,12 +440,8 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
if (arfs_enabled)
mlx5e_arfs_disable(priv);
- if (!netif_is_rxfh_configured(priv->netdev))
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
-
/* Switch to new channels, set new parameters and close old ones */
- err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+ err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_num_channels_changed);
if (arfs_enabled) {
int err2 = mlx5e_arfs_enable(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 152aa5d7df79..bbe8c32fb423 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2880,6 +2880,17 @@ static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
netif_set_real_num_rx_queues(netdev, num_rxqs);
}
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
+{
+ u16 count = priv->channels.params.num_channels;
+
+ if (!netif_is_rxfh_configured(priv->netdev))
+ mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+ MLX5E_INDIR_RQT_SIZE, count);
+
+ return 0;
+}
+
static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
{
int i, ch;
@@ -5288,9 +5299,10 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
max_nch = mlx5e_get_max_num_channels(priv->mdev);
if (priv->channels.params.num_channels > max_nch) {
mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
+ /* Reducing the number of channels - RXFH has to be reset. */
+ priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED;
priv->channels.params.num_channels = max_nch;
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, max_nch);
+ mlx5e_num_channels_changed(priv);
}
err = profile->init_tx(priv);
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From fe867cac9e1967c553e4ac2aece5fc8675258010 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi(a)mellanox.com>
Date: Mon, 4 Nov 2019 12:02:14 +0200
Subject: [PATCH] net/mlx5e: Use preactivate hook to set the indirection table
mlx5e_ethtool_set_channels updates the indirection table before
switching to the new channels. If the switch fails, the indirection
table is new, but the channels are old, which is wrong. Fix it by using
the preactivate hook of mlx5e_safe_switch_channels to update the
indirection table at the stage when nothing can fail anymore.
As the code that updates the indirection table is now encapsulated into
a new function, use that function in the attach flow when the driver has
to reduce the number of channels, and prepare the code for the next
commit.
Fixes: 85082dba0a ("net/mlx5e: Correctly handle RSS indirection table when changing number of channels")
Signed-off-by: Maxim Mikityanskiy <maximmi(a)mellanox.com>
Reviewed-by: Tariq Toukan <tariqt(a)mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm(a)mellanox.com>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index bc2c96b34de1..4ddccab02a4b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1043,6 +1043,7 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
struct mlx5e_channels *new_chs,
mlx5e_fp_preactivate preactivate);
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv);
void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 68b520df07e4..ff7f5a931520 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -432,9 +432,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
*cur_params = new_channels.params;
- if (!netif_is_rxfh_configured(priv->netdev))
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
+ mlx5e_num_channels_changed(priv);
goto out;
}
@@ -442,12 +440,8 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
if (arfs_enabled)
mlx5e_arfs_disable(priv);
- if (!netif_is_rxfh_configured(priv->netdev))
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
-
/* Switch to new channels, set new parameters and close old ones */
- err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+ err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_num_channels_changed);
if (arfs_enabled) {
int err2 = mlx5e_arfs_enable(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 152aa5d7df79..bbe8c32fb423 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2880,6 +2880,17 @@ static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
netif_set_real_num_rx_queues(netdev, num_rxqs);
}
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
+{
+ u16 count = priv->channels.params.num_channels;
+
+ if (!netif_is_rxfh_configured(priv->netdev))
+ mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+ MLX5E_INDIR_RQT_SIZE, count);
+
+ return 0;
+}
+
static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
{
int i, ch;
@@ -5288,9 +5299,10 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
max_nch = mlx5e_get_max_num_channels(priv->mdev);
if (priv->channels.params.num_channels > max_nch) {
mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
+ /* Reducing the number of channels - RXFH has to be reset. */
+ priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED;
priv->channels.params.num_channels = max_nch;
- mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, max_nch);
+ mlx5e_num_channels_changed(priv);
}
err = profile->init_tx(priv);
On Fri, Apr 17, 2020 at 9:41 PM Toralf Förster <toralf.foerster(a)gmx.de> wrote:
>
> On 4/17/20 8:52 PM, Rafael J. Wysocki wrote:
> > On Fri, Apr 17, 2020 at 6:36 PM Toralf Förster <toralf.foerster(a)gmx.de> wrote:
> >>
> >> On 4/17/20 5:53 PM, Rafael J. Wysocki wrote:
> >>> Does the patch below (untested) make any difference?
> >>>
> >>> ---
> >>> drivers/acpi/ec.c | 5 ++++-
> >>> 1 file changed, 4 insertions(+), 1 deletion(-)
> >>>
> >>> Index: linux-pm/drivers/acpi/ec.c
> >>> ===================================================================
> >>> --- linux-pm.orig/drivers/acpi/ec.c
> >>> +++ linux-pm/drivers/acpi/ec.c
> >>> @@ -2067,7 +2067,10 @@ static struct acpi_driver acpi_ec_driver
> >>> .add = acpi_ec_add,
> >>> .remove = acpi_ec_remove,
> >>> },
> >>> - .drv.pm = &acpi_ec_pm,
> >>> + .drv = {
> >>> + .probe_type = PROBE_FORCE_SYNCHRONOUS,
> >>> + .pm = &acpi_ec_pm,
> >>> + },
> >>> };
> >>>
> >>> static void acpi_ec_destroy_workqueues(void)
> >> I'd say no, but for completeness:
> >
> > OK, it looks like mainline commit
> >
> > 65a691f5f8f0 ("ACPI: EC: Do not clear boot_ec_is_ecdt in acpi_ec_add()")
> >
> > was backported into 5.6.5 by mistake.
> >
> > Can you please revert that patch and retest?
> >
> Yes, reverting that commit solved the issue.
OK, thanks!
Greg, I'm not sure why commit 65a691f5f8f0 from the mainline ended up in 5.6.5.
It has not been marked for -stable or otherwise requested to be
included AFAICS. Also it depends on other mainline commits that have
not been included into 5.6.5.
Can you please drop it?
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From ef4a632ccc1c7d3fb71a5baae85b79af08b7f94b Mon Sep 17 00:00:00 2001
From: Murphy Zhou <jencce.kernel(a)gmail.com>
Date: Wed, 18 Mar 2020 20:43:38 +0800
Subject: [PATCH] CIFS: check new file size when extending file by fallocate
xfstests generic/228 checks if fallocate respect RLIMIT_FSIZE.
After fallocate mode 0 extending enabled, we can hit this failure.
Fix this by check the new file size with vfs helper, return
error if file size is larger then RLIMIT_FSIZE(ulimit -f).
This patch has been tested by LTP/xfstests aginst samba and
Windows server.
Acked-by: Ronnie Sahlberg <lsahlber(a)redhat.com>
Signed-off-by: Murphy Zhou <jencce.kernel(a)gmail.com>
Signed-off-by: Steve French <stfrench(a)microsoft.com>
CC: Stable <stable(a)vger.kernel.org>
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index b0759c8aa6f5..9c9258fc8756 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -3255,6 +3255,10 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
* Extending the file
*/
if ((keep_size == false) && i_size_read(inode) < off + len) {
+ rc = inode_newsize_ok(inode, off + len);
+ if (rc)
+ goto out;
+
if ((cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) == 0)
smb2_set_sparse(xid, tcon, cfile, inode, false);
A recent commit 9852ae3fe529 ("mm, memcg: consider subtrees in
memory.events") changes the behavior of memcg events, which will
consider subtrees in memory.events. But oom_kill event is a special one
as it is used in both cgroup1 and cgroup2. In cgroup1, it is displayed
in memory.oom_control. The file memory.oom_control is in both root memcg
and non root memcg, that is different with memory.event as it only in
non-root memcg. That commit is okay for cgroup2, but it is not okay for
cgroup1 as it will cause inconsistent behavior between root memcg and
non-root memcg.
Let's recover the original behavior for cgroup1.
Fixes: 9852ae3fe529 ("mm, memcg: consider subtrees in memory.events")
Cc: Chris Down <chris(a)chrisdown.name>
Cc: Johannes Weiner <hannes(a)cmpxchg.org>
Cc: Shakeel Butt <shakeelb(a)google.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Yafang Shao <laoar.shao(a)gmail.com>
---
include/linux/memcontrol.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8c340e6b347f..a0ae080a67d1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -798,7 +798,8 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg,
atomic_long_inc(&memcg->memory_events[event]);
cgroup_file_notify(&memcg->events_file);
- if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
+ if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS ||
+ !cgroup_subsys_on_dfl(memory_cgrp_subsys))
break;
} while ((memcg = parent_mem_cgroup(memcg)) &&
!mem_cgroup_is_root(memcg));
--
2.18.2