| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20220207145718.GA523931@lothringen>
Date: Mon, 7 Feb 2022 15:57:18 +0100
From: Frederic Weisbecker <frederic@...nel.org>
To: Marcelo Tosatti <mtosatti@...hat.com>
Cc: linux-kernel@...r.kernel.org, Nitesh Lal <nilal@...hat.com>,
Nicolas Saenz Julienne <nsaenzju@...hat.com>,
Christoph Lameter <cl@...ux.com>,
Juri Lelli <juri.lelli@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Alex Belits <abelits@...its.com>, Peter Xu <peterx@...hat.com>,
Thomas Gleixner <tglx@...utronix.de>,
Daniel Bristot de Oliveira <bristot@...hat.com>,
Oscar Shiang <oscar0225@...email.tw>
Subject: Re: [patch v11 05/13] task isolation: sync vmstats on return to
userspace
On Fri, Feb 04, 2022 at 02:35:42PM -0300, Marcelo Tosatti wrote:
> The logic to disable vmstat worker thread, when entering
> nohz full, does not cover all scenarios. For example, it is possible
> for the following to happen:
>
> 1) enter nohz_full, which calls refresh_cpu_vm_stats, syncing the stats.
> 2) app runs mlock, which increases counters for mlock'ed pages.
> 3) start -RT loop
>
> Since refresh_cpu_vm_stats from nohz_full logic can happen _before_
> the mlock, vmstat shepherd can restart vmstat worker thread on
> the CPU in question.
>
> To fix this, use the task isolation prctl interface to quiesce
> deferred actions when returning to userspace.
>
> This patch adds hooks to fork and exit code paths.
>
> Signed-off-by: Marcelo Tosatti <mtosatti@...hat.com>
>
> ---
> v11: fold patch to add task_isol_exit hooks (Frederic)
> Use _TIF_TASK_ISOL bit on thread flags (Frederic)
>
> v6: modify exit_to_user_mode_loop to cover exceptions and interrupts
> v5: no changes
> v4: add oneshot mode support
>
> include/linux/task_isolation.h | 16 ++++++++++++++++
> include/linux/vmstat.h | 8 ++++++++
> kernel/entry/common.c | 15 +++++++++++----
> kernel/task_isolation.c | 21 +++++++++++++++++++++
> mm/vmstat.c | 21 +++++++++++++++++++++
> 5 files changed, 77 insertions(+), 4 deletions(-)
>
> Index: linux-2.6/include/linux/task_isolation.h
> ===================================================================
> --- linux-2.6.orig/include/linux/task_isolation.h
> +++ linux-2.6/include/linux/task_isolation.h
> @@ -27,6 +27,13 @@ static inline void task_isol_free(struct
> __task_isol_free(tsk);
> }
>
> +void __task_isol_exit(struct task_struct *tsk);
> +static inline void task_isol_exit(struct task_struct *tsk)
> +{
> + if (tsk->task_isol_info)
> + __task_isol_exit(tsk);
> +}
> +
> int prctl_task_isol_feat_get(unsigned long arg2, unsigned long arg3,
> unsigned long arg4, unsigned long arg5);
> int prctl_task_isol_cfg_get(unsigned long arg2, unsigned long arg3,
> @@ -40,12 +47,22 @@ int prctl_task_isol_activate_set(unsigne
>
> int __copy_task_isol(struct task_struct *tsk);
>
> +void task_isol_exit_to_user_mode(void);
> +
> #else
>
> +static inline void task_isol_exit_to_user_mode(void)
> +{
> +}
> +
> static inline void task_isol_free(struct task_struct *tsk)
> {
> }
>
> +static inline void task_isol_exit(struct task_struct *tsk)
> +{
> +}
> +
> static inline int prctl_task_isol_feat_get(unsigned long arg2,
> unsigned long arg3,
> unsigned long arg4,
> Index: linux-2.6/include/linux/vmstat.h
> ===================================================================
> --- linux-2.6.orig/include/linux/vmstat.h
> +++ linux-2.6/include/linux/vmstat.h
> @@ -21,6 +21,14 @@ int sysctl_vm_numa_stat_handler(struct c
> void *buffer, size_t *length, loff_t *ppos);
> #endif
>
> +#if defined(CONFIG_SMP) && defined(CONFIG_TASK_ISOLATION)
> +void sync_vmstat(void);
> +#else
> +static inline void sync_vmstat(void)
> +{
> +}
> +#endif
> +
> struct reclaim_stat {
> unsigned nr_dirty;
> unsigned nr_unqueued_dirty;
> Index: linux-2.6/kernel/entry/common.c
> ===================================================================
> --- linux-2.6.orig/kernel/entry/common.c
> +++ linux-2.6/kernel/entry/common.c
> @@ -6,6 +6,7 @@
> #include <linux/livepatch.h>
> #include <linux/audit.h>
> #include <linux/tick.h>
> +#include <linux/task_isolation.h>
>
> #include "common.h"
>
> @@ -174,6 +175,9 @@ static unsigned long exit_to_user_mode_l
> if (ti_work & _TIF_NOTIFY_RESUME)
> tracehook_notify_resume(regs);
>
> + if (ti_work & _TIF_TASK_ISOL)
> + task_isol_exit_to_user_mode();
> +
> /* Architecture specific TIF work */
> arch_exit_to_user_mode_work(regs, ti_work);
>
> Index: linux-2.6/kernel/task_isolation.c
> ===================================================================
> --- linux-2.6.orig/kernel/task_isolation.c
> +++ linux-2.6/kernel/task_isolation.c
> @@ -18,6 +18,12 @@
> #include <linux/sysfs.h>
> #include <linux/init.h>
> #include <linux/sched/task.h>
> +#include <linux/mm.h>
> +#include <linux/vmstat.h>
> +
> +void __task_isol_exit(struct task_struct *tsk)
> +{
> +}
>
> void __task_isol_free(struct task_struct *tsk)
> {
> @@ -251,6 +257,9 @@ static int cfg_feat_quiesce_set(unsigned
> task_isol_info->quiesce_mask = i_qctrl->quiesce_mask;
> task_isol_info->oneshot_mask = i_qctrl->quiesce_oneshot_mask;
> task_isol_info->conf_mask |= ISOL_F_QUIESCE;
> + if (task_isol_info->quiesce_mask & ISOL_F_QUIESCE_VMSTATS)
> + set_thread_flag(TIF_TASK_ISOL);
Should you check if (i->active_mask == ISOL_F_QUIESCE) before setting the
flag?
> +
> ret = 0;
>
> out_free:
> @@ -303,6 +312,7 @@ int __copy_task_isol(struct task_struct
> new_info->active_mask = info->active_mask;
>
> tsk->task_isol_info = new_info;
> + set_ti_thread_flag(task_thread_info(tsk), TIF_TASK_ISOL);
Same here?
>
> return 0;
Thanks.
Powered by blists - more mailing lists