| 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: <200703231542.45459.rjw@sisk.pl>
Date: Fri, 23 Mar 2007 15:42:44 +0100
From: "Rafael J. Wysocki" <rjw@...k.pl>
To: Maxim <maximlevitsky@...il.com>
Cc: linux-kernel@...r.kernel.org, Pavel Machek <pavel@....cz>,
Tigran Aivazian <tigran@...azian.fsnet.co.uk>
Subject: Re: [BUG] Code reordering in swsusp breaks suspend on SMP systems
On Friday, 23 March 2007 00:30, Rafael J. Wysocki wrote:
> On Thursday, 22 March 2007 00:53, Rafael J. Wysocki wrote:
> > On Thursday, 22 March 2007 00:39, Maxim wrote:
> > > On Thursday 22 March 2007 01:24:25 Rafael J. Wysocki wrote:
> > > > On Thursday, 22 March 2007 00:09, Maxim wrote:
> > > > > On Thursday 22 March 2007 00:39:02 you wrote:
> > > > > > On Wednesday, 21 March 2007 23:21, Pavel Machek wrote:
> > > > > > > Hi!
> > > > > > >
> > > > > > > > Starting with 2.6.21-rc1 suspend to ram and disk doesn't work anymore on my system.
> > > > > > > >
> > > > > > > > I did a git-bisect and found that those commits break it:
> > > > > > > >
> > > > > > > > e3c7db621bed4afb8e231cb005057f2feb5db557 - [PATCH] [PATCH] PM: Change code ordering in main.c
> > > > > > > > ed746e3b18f4df18afa3763155972c5835f284c5 - [PATCH] [PATCH] swsusp: Change code ordering in disk.c
> > > > > > > > 259130526c267550bc365d3015917d90667732f1 - [PATCH] [PATCH] swsusp: Change code ordering in user.c
> > > > > > > >
> > > > > > >
> > > > > > > (Yep, it was in my "to analyze" queue).
> > > > > > >
> > > > > > > > I already reported about it, but now i know the reason why suspend breaks.
> > > > > > > >
> > > > > > > > The problem is that both cpu_up/cpu_down were allowed to sleep until now,
> > > > > > > > and it did work because those functions could be called only in process context
> > > > > > > > (the one that writes to /sys/devices/system/cpu/cpu*/online) or idle thread that does smp_init()).
> > > > > > > >
> > > > > > > > But now they are called _after_ all tasks were suspended, so if cpu_down tries for example to take a lock
> > > > > > > > that is taken by different process, it can't since the different proccess is frozen and can't release the lock.
> > > > > > > >
> > > > > > >
> > > > > > > Thanks for detailed explanation.
> > > > > > >
> > > > > > > ...but, on my machine suspend works ok in -rc4. I'm not seeing this.
> > > > > > >
> > > > > > > ...by design, "frozen" tasks must not hold any locks. If frozen task
> > > > > > > holds a lock, that's a bug.
> > > > > > >
> > > > > > > > Or, it is also possible to revert this change.
> > > > > > >
> > > > > > > Are you using xfs?
> > > > > >
> > > > > > Well, this is the only case that can trigger it. There are no other freezable
> > > > > > workqueues.
> > > > > >
> > > > > > Greetings,
> > > > > > Rafael
> > > > > >
> > > > >
> > > > > Hello,
> > > > >
> > > > > Yes, you are right and it is XFS
> > > > >
> > > > > System suspends and resumes with xfs and your patch correctly,
> > > >
> > > > Could you please sent this information to the list? I'd like it to reach all
> > > > of the CCed parites. ;-)
> > >
> > > I did now ( sorry I just keep using this Answer command, instead of Answer to everybody)
> > > I didn't intend to send private email.
> > > >
> > > > > Of course I need to mention that I had to unload microcode update driver because it prevented resume,
> > > > > because it calls firmware loader helper, and again sleeps on lock
> > > >
> > > > This is interesting. Did it happen before or is it a regression?
> > >
> > > It is from the same group of bugs , I mean hang because cpu_up/down is called with frozen tasks
> > > Of course it didn't happen before those reordering commits were introduced
> >
> > Well, we want cpu_up/down to be called after processes have been frozen, for
> > various reasons (one of them being that applications shouldn't see us playing
> > with the CPUs).
> >
> > Thanks for reporting this, I'll have a look at the microcode update driver.
>
> Well, I have invented the appended workaround, but I'm not sure how much
> sense it makes with respect to the microcode driver. At least, it doesn't
> break my AMD64 SMP setup. ;-)
Modified version of the patch is appended. Unfortunately I have no hardware
supporting the microcode updates.
Greetings,
Rafael
---
arch/i386/kernel/microcode.c | 28 +++++++++++++++++++++++++---
include/linux/cpu.h | 2 ++
kernel/cpu.c | 32 ++++++++++++++++----------------
3 files changed, 43 insertions(+), 19 deletions(-)
Index: linux-2.6.21-rc4/arch/i386/kernel/microcode.c
===================================================================
--- linux-2.6.21-rc4.orig/arch/i386/kernel/microcode.c
+++ linux-2.6.21-rc4/arch/i386/kernel/microcode.c
@@ -567,6 +567,16 @@ static int cpu_request_microcode(int cpu
return error;
}
+static void apply_microcode_on_cpu(int cpu)
+{
+ cpumask_t old;
+
+ old = current->cpus_allowed;
+ set_cpus_allowed(current, cpumask_of_cpu(cpu));
+ apply_microcode(cpu);
+ set_cpus_allowed(current, old);
+}
+
static void microcode_init_cpu(int cpu)
{
cpumask_t old;
@@ -663,13 +673,21 @@ static int mc_sysdev_add(struct sys_devi
return 0;
pr_debug("Microcode:CPU %d added\n", cpu);
- memset(uci, 0, sizeof(*uci));
+ /* If suspend_cpu_hotplug is set, the system is resuming and we should
+ * use the data from before the suspend.
+ */
+ if (!suspend_cpu_hotplug)
+ memset(uci, 0, sizeof(*uci));
err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
if (err)
return err;
- microcode_init_cpu(cpu);
+ if (suspend_cpu_hotplug && uci->valid)
+ apply_microcode_on_cpu(cpu);
+ else
+ microcode_init_cpu(cpu);
+
return 0;
}
@@ -680,7 +698,11 @@ static int mc_sysdev_remove(struct sys_d
if (!cpu_online(cpu))
return 0;
pr_debug("Microcode:CPU %d removed\n", cpu);
- microcode_fini_cpu(cpu);
+ /* If suspend_cpu_hotplug is set, the system is suspending and we should
+ * keep the microcode in memory for the resume.
+ */
+ if (!suspend_cpu_hotplug)
+ microcode_fini_cpu(cpu);
sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
return 0;
}
Index: linux-2.6.21-rc4/include/linux/cpu.h
===================================================================
--- linux-2.6.21-rc4.orig/include/linux/cpu.h
+++ linux-2.6.21-rc4/include/linux/cpu.h
@@ -127,6 +127,8 @@ static inline int cpu_is_offline(int cpu
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_SUSPEND_SMP
+extern int suspend_cpu_hotplug;
+
extern int disable_nonboot_cpus(void);
extern void enable_nonboot_cpus(void);
#else
Index: linux-2.6.21-rc4/kernel/cpu.c
===================================================================
--- linux-2.6.21-rc4.orig/kernel/cpu.c
+++ linux-2.6.21-rc4/kernel/cpu.c
@@ -254,6 +254,12 @@ int __cpuinit cpu_up(unsigned int cpu)
}
#ifdef CONFIG_SUSPEND_SMP
+/* Needed to prevent the microcode driver from requesting firmware in its CPU
+ * hotplug notifier during the suspend/resume.
+ */
+int suspend_cpu_hotplug;
+EXPORT_SYMBOL(suspend_cpu_hotplug);
+
static cpumask_t frozen_cpus;
int disable_nonboot_cpus(void)
@@ -261,16 +267,8 @@ int disable_nonboot_cpus(void)
int cpu, first_cpu, error = 0;
mutex_lock(&cpu_add_remove_lock);
- first_cpu = first_cpu(cpu_present_map);
- if (!cpu_online(first_cpu)) {
- error = _cpu_up(first_cpu);
- if (error) {
- printk(KERN_ERR "Could not bring CPU%d up.\n",
- first_cpu);
- goto out;
- }
- }
-
+ suspend_cpu_hotplug = 1;
+ first_cpu = first_cpu(cpu_online_map);
/* We take down all of the non-boot CPUs in one shot to avoid races
* with the userspace trying to use the CPU hotplug at the same time
*/
@@ -296,7 +294,7 @@ int disable_nonboot_cpus(void)
} else {
printk(KERN_ERR "Non-boot CPUs are not disabled\n");
}
-out:
+ suspend_cpu_hotplug = 0;
mutex_unlock(&cpu_add_remove_lock);
return error;
}
@@ -308,20 +306,22 @@ void enable_nonboot_cpus(void)
/* Allow everyone to use the CPU hotplug again */
mutex_lock(&cpu_add_remove_lock);
cpu_hotplug_disabled = 0;
- mutex_unlock(&cpu_add_remove_lock);
if (cpus_empty(frozen_cpus))
- return;
+ goto out;
+ suspend_cpu_hotplug = 1;
printk("Enabling non-boot CPUs ...\n");
for_each_cpu_mask(cpu, frozen_cpus) {
- error = cpu_up(cpu);
+ error = _cpu_up(cpu);
if (!error) {
printk("CPU%d is up\n", cpu);
continue;
}
- printk(KERN_WARNING "Error taking CPU%d up: %d\n",
- cpu, error);
+ printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
}
cpus_clear(frozen_cpus);
+ suspend_cpu_hotplug = 0;
+out:
+ mutex_unlock(&cpu_add_remove_lock);
}
#endif
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists