void *dev_id)
writel(stat & MXS_MMC_IRQ_BITS,
host->base + HW_SSP_CTRL1(host) + STMP_OFFSET_REG_CLR);
+ spin_unlock(&host->lock);
+
if ((stat & BM_SSP_CTRL1_SDIO_IRQ) && (stat & BM_SSP_CTRL1_SDIO_IRQ_EN))
mmc_signal_sdio_irq(host->mmc);
- spin_unlock(&host->lock);
-
if (stat & BM_SSP_CTRL1_RESP_TIMEOUT_IRQ)
cmd->error = -ETIMEDOUT;
else if (stat & BM_SSP_CTRL1_RESP_ERR_IRQ)
Is there any reason to keep mmc_signal_sdio_irq inside the spinlock?
mmc_signal_sdio_irq calls mxs_mmc_enable_sdio_irq and it tries to
acquire lock while it is already acquired.
Best regards,
Lauri Hintsala
if (stat & BM_SSP_CTRL1_RESP_TIMEOUT_IRQ)
cmd->error = -ETIMEDOUT;
else if (stat & BM_SSP_CTRL1_RESP_ERR_IRQ)
Is there any reason to keep mmc_signal_sdio_irq inside the spinlock?
mmc_signal_sdio_irq calls mxs_mmc_enable_sdio_irq and it tries to
acquire lock while it is already acquired.
Best regards,
Lauri Hintsala
On Tue, Jul 10, 2012 at 05:04:42PM +0300, Lauri Hintsala wrote:
Hi,
I was able to get deadlock with CONFIG_DEBUG_SPINLOCK enabled. I
added also CONFIG_PROVE_LOCKING to get more verbose output. I got
following error message after SDIO device has been powered.
I'm able to replicate issue with Linux next-20120710. Platform is imx28.
The bug is there probably because the driver hasn't been widely tested
on SDIO card.
irq, void *dev_id)
writel(stat & MXS_MMC_IRQ_BITS,
host->base + HW_SSP_CTRL1(host) + STMP_OFFSET_REG_CLR);
+ spin_unlock(&host->lock);
+
if ((stat & BM_SSP_CTRL1_SDIO_IRQ) && (stat & BM_SSP_CTRL1_SDIO_IRQ_EN))
mmc_signal_sdio_irq(host->mmc);
- spin_unlock(&host->lock);
-
if (stat & BM_SSP_CTRL1_RESP_TIMEOUT_IRQ)
cmd->error = -ETIMEDOUT;
else if (stat & BM_SSP_CTRL1_RESP_ERR_IRQ)
Is there any reason to keep mmc_signal_sdio_irq inside the spinlock?
mmc_signal_sdio_irq calls mxs_mmc_enable_sdio_irq and it tries to
acquire lock while it is already acquired.
The fix looks right to me. You can have my ack when you send a patch
for it.
Acked-by: Shawn Guo <redacted>
--
Regards,
Shawn
irq, void *dev_id)
writel(stat & MXS_MMC_IRQ_BITS,
host->base + HW_SSP_CTRL1(host) + STMP_OFFSET_REG_CLR);
+ spin_unlock(&host->lock);
+
if ((stat & BM_SSP_CTRL1_SDIO_IRQ) && (stat & BM_SSP_CTRL1_SDIO_IRQ_EN))
mmc_signal_sdio_irq(host->mmc);
- spin_unlock(&host->lock);
-
if (stat & BM_SSP_CTRL1_RESP_TIMEOUT_IRQ)
cmd->error = -ETIMEDOUT;
else if (stat & BM_SSP_CTRL1_RESP_ERR_IRQ)
Is there any reason to keep mmc_signal_sdio_irq inside the spinlock?
mmc_signal_sdio_irq calls mxs_mmc_enable_sdio_irq and it tries to
acquire lock while it is already acquired.
The fix looks right to me. You can have my ack when you send a patch
for it.
Acked-by: Shawn Guo <redacted>
For you information, the following is what I learnt from Arnd when I
was a beginner.
Regards,
Shawn
--- Quote Begins ---
A short form of the strict rules (there are better documentations
out there) is:
* If all users are outside of interrupt or tasklet context,
use a bare spin_lock().
* If one user is in a tasklet context, use spin_lock() inside
the tasklet, but spin_lock_bh() outside, to prevent the
tasklet from interrupting the critical section. Code that
can be called in either tasklet or regular context needs
to use spin_lock_bh() as well.
* If one user is in interrupt context, use spin_lock() inside
of the interrupt handler, but spin_lock_irq() in tasklet
and normal context (not spin_lock_irqsave()), to prevent
the interrupt from happening during the critical section.
* Use spin_lock_irqsave() only for functions that can be called
in either interrupt or non-interrupt context. Most drivers
don't need this at all.
The simplified rule would be to always use spin_lock_irqsave(),
because that does not require you to understand what you are doing.
My position is that it is better to use the stricter rules, because
that documents that you actually do understand what you are doing ;-)
It's also slightly more efficient, because it avoids having to
save the interrupt status in a variable.
irq, void *dev_id)
writel(stat & MXS_MMC_IRQ_BITS,
host->base + HW_SSP_CTRL1(host) + STMP_OFFSET_REG_CLR);
+ spin_unlock(&host->lock);
+
if ((stat & BM_SSP_CTRL1_SDIO_IRQ) && (stat & BM_SSP_CTRL1_SDIO_IRQ_EN))
mmc_signal_sdio_irq(host->mmc);
- spin_unlock(&host->lock);
-
if (stat & BM_SSP_CTRL1_RESP_TIMEOUT_IRQ)
cmd->error = -ETIMEDOUT;
else if (stat & BM_SSP_CTRL1_RESP_ERR_IRQ)
Is there any reason to keep mmc_signal_sdio_irq inside the spinlock?
mmc_signal_sdio_irq calls mxs_mmc_enable_sdio_irq and it tries to
acquire lock while it is already acquired.
The fix looks right to me. You can have my ack when you send a patch
for it.
Acked-by: Shawn Guo <redacted>
I ran into the same problem today, but the proposed fix doesn't seem
to work for me:
---schnipp---
# modprobe libertas_sdio
[ 59.200000] lib80211: common routines for IEEE802.11 drivers
[ 59.240000] cfg80211: Calling CRDA to update world regulatory domain
[ 59.320000] libertas_sdio: Libertas SDIO driver
[ 59.330000] libertas_sdio: Copyright Pierre Ossman
# modprobe mxs-mmc
[ 64.210000] mxs-mmc 80010000.ssp: initialized
[ 64.260000] mxs-mmc 80034000.ssp: initialized
[ 64.270000] mmc0: new SDIO card at address 0001
# [ 65.440000] libertas_sdio mmc0:0001:1: (unregistered net_device): 00:13:04:80:00:3f, fw 9.70.3p24, cap 0x00000303
[ 65.470000]
[ 65.470000] =============================================
[ 65.470000] [ INFO: possible recursive locking detected ]
[ 65.470000] 3.5.0-rc5 #2 Not tainted
[ 65.470000] ---------------------------------------------
[ 65.470000] ksdioirqd/mmc0/73 is trying to acquire lock:
[ 65.470000] (&(&host->lock)->rlock#2){-.-...}, at: [<bf054120>] mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]
[ 65.470000]
[ 65.470000] but task is already holding lock:
[ 65.470000] (&(&host->lock)->rlock#2){-.-...}, at: [<bf054120>] mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]
[ 65.470000]
[ 65.470000] other info that might help us debug this:
[ 65.470000] Possible unsafe locking scenario:
[ 65.470000]
[ 65.470000] CPU0
[ 65.470000] ----
[ 65.470000] lock(&(&host->lock)->rlock#2);
[ 65.470000] lock(&(&host->lock)->rlock#2);
[ 65.470000]
[ 65.470000] *** DEADLOCK ***
[ 65.470000]
[ 65.470000] May be due to missing lock nesting notation
[ 65.470000]
[ 65.470000] 1 lock held by ksdioirqd/mmc0/73:
[ 65.470000] #0: (&(&host->lock)->rlock#2){-.-...}, at: [<bf054120>] mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]
[ 65.470000]
[ 65.470000] stack backtrace:
[ 65.470000] [<c0014990>] (unwind_backtrace+0x0/0xf4) from [<c005ccb8>] (__lock_acquire+0x14f8/0x1b98)
[ 65.470000] [<c005ccb8>] (__lock_acquire+0x14f8/0x1b98) from [<c005d3f8>] (lock_acquire+0xa0/0x108)
[ 65.470000] [<c005d3f8>] (lock_acquire+0xa0/0x108) from [<c02f671c>] (_raw_spin_lock_irqsave+0x48/0x5c)
[ 65.470000] [<c02f671c>] (_raw_spin_lock_irqsave+0x48/0x5c) from [<bf054120>] (mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc])
[ 65.470000] [<bf054120>] (mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]) from [<bf0541d0>] (mxs_mmc_enable_sdio_irq+0xc8/0xdc [mxs_mmc])
[ 65.470000] [<bf0541d0>] (mxs_mmc_enable_sdio_irq+0xc8/0xdc [mxs_mmc]) from [<c0219b38>] (sdio_irq_thread+0x1bc/0x274)
[ 65.470000] [<c0219b38>] (sdio_irq_thread+0x1bc/0x274) from [<c003c324>] (kthread+0x8c/0x98)
[ 65.470000] [<c003c324>] (kthread+0x8c/0x98) from [<c00101ac>] (kernel_thread_exit+0x0/0x8)
[ 65.470000] BUG: spinlock lockup suspected on CPU#0, ksdioirqd/mmc0/73
[ 65.470000] lock: 0xc3358724, .magic: dead4ead, .owner: ksdioirqd/mmc0/73, .owner_cpu: 0
[ 65.470000] [<c0014990>] (unwind_backtrace+0x0/0xf4) from [<c01b46b0>] (do_raw_spin_lock+0x100/0x144)
[ 65.470000] [<c01b46b0>] (do_raw_spin_lock+0x100/0x144) from [<c02f6724>] (_raw_spin_lock_irqsave+0x50/0x5c)
[ 65.470000] [<c02f6724>] (_raw_spin_lock_irqsave+0x50/0x5c) from [<bf054120>] (mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc])
[ 65.470000] [<bf054120>] (mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]) from [<bf0541d0>] (mxs_mmc_enable_sdio_irq+0xc8/0xdc [mxs_mmc])
[ 65.470000] [<bf0541d0>] (mxs_mmc_enable_sdio_irq+0xc8/0xdc [mxs_mmc]) from [<c0219b38>] (sdio_irq_thread+0x1bc/0x274)
[ 65.470000] [<c0219b38>] (sdio_irq_thread+0x1bc/0x274) from [<c003c324>] (kthread+0x8c/0x98)
[ 65.470000] [<c003c324>] (kthread+0x8c/0x98) from [<c00101ac>] (kernel_thread_exit+0x0/0x8)
---schnapp---
Any hints how to work around or fix this, would be appreciated
Attila Kinali
--
It is upon moral qualities that a society is ultimately founded. All
the prosperity and technological sophistication in the world is of no
use without that foundation.
-- Miss Matheson, The Diamond Age, Neil Stephenson
irq, void *dev_id)
writel(stat & MXS_MMC_IRQ_BITS,
host->base + HW_SSP_CTRL1(host) + STMP_OFFSET_REG_CLR);
+ spin_unlock(&host->lock);
+
if ((stat & BM_SSP_CTRL1_SDIO_IRQ) && (stat & BM_SSP_CTRL1_SDIO_IRQ_EN))
mmc_signal_sdio_irq(host->mmc);
- spin_unlock(&host->lock);
-
if (stat & BM_SSP_CTRL1_RESP_TIMEOUT_IRQ)
cmd->error = -ETIMEDOUT;
else if (stat & BM_SSP_CTRL1_RESP_ERR_IRQ)
Is there any reason to keep mmc_signal_sdio_irq inside the spinlock?
mmc_signal_sdio_irq calls mxs_mmc_enable_sdio_irq and it tries to
acquire lock while it is already acquired.
The fix looks right to me. You can have my ack when you send a patch
for it.
Acked-by: Shawn Guo <redacted>
I ran into the same problem today, but the proposed fix doesn't seem
to work for me:
It's a different problem from what Lauri reported and fixed. I haven't
played SDIO card that much, so I'm not completely clear about the SDIO
calling sequence, but is it reasonable that mxs_mmc_enable_sdio_irq is
being called recursively?
Regards,
Shawn
---schnipp---
# modprobe libertas_sdio
[ 59.200000] lib80211: common routines for IEEE802.11 drivers
[ 59.240000] cfg80211: Calling CRDA to update world regulatory domain
[ 59.320000] libertas_sdio: Libertas SDIO driver
[ 59.330000] libertas_sdio: Copyright Pierre Ossman
# modprobe mxs-mmc
[ 64.210000] mxs-mmc 80010000.ssp: initialized
[ 64.260000] mxs-mmc 80034000.ssp: initialized
[ 64.270000] mmc0: new SDIO card at address 0001
# [ 65.440000] libertas_sdio mmc0:0001:1: (unregistered net_device): 00:13:04:80:00:3f, fw 9.70.3p24, cap 0x00000303
[ 65.470000]
[ 65.470000] =============================================
[ 65.470000] [ INFO: possible recursive locking detected ]
[ 65.470000] 3.5.0-rc5 #2 Not tainted
[ 65.470000] ---------------------------------------------
[ 65.470000] ksdioirqd/mmc0/73 is trying to acquire lock:
[ 65.470000] (&(&host->lock)->rlock#2){-.-...}, at: [<bf054120>] mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]
[ 65.470000]
[ 65.470000] but task is already holding lock:
[ 65.470000] (&(&host->lock)->rlock#2){-.-...}, at: [<bf054120>] mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]
[ 65.470000]
[ 65.470000] other info that might help us debug this:
[ 65.470000] Possible unsafe locking scenario:
[ 65.470000]
[ 65.470000] CPU0
[ 65.470000] ----
[ 65.470000] lock(&(&host->lock)->rlock#2);
[ 65.470000] lock(&(&host->lock)->rlock#2);
[ 65.470000]
[ 65.470000] *** DEADLOCK ***
[ 65.470000]
[ 65.470000] May be due to missing lock nesting notation
[ 65.470000]
[ 65.470000] 1 lock held by ksdioirqd/mmc0/73:
[ 65.470000] #0: (&(&host->lock)->rlock#2){-.-...}, at: [<bf054120>] mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]
[ 65.470000]
[ 65.470000] stack backtrace:
[ 65.470000] [<c0014990>] (unwind_backtrace+0x0/0xf4) from [<c005ccb8>] (__lock_acquire+0x14f8/0x1b98)
[ 65.470000] [<c005ccb8>] (__lock_acquire+0x14f8/0x1b98) from [<c005d3f8>] (lock_acquire+0xa0/0x108)
[ 65.470000] [<c005d3f8>] (lock_acquire+0xa0/0x108) from [<c02f671c>] (_raw_spin_lock_irqsave+0x48/0x5c)
[ 65.470000] [<c02f671c>] (_raw_spin_lock_irqsave+0x48/0x5c) from [<bf054120>] (mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc])
[ 65.470000] [<bf054120>] (mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]) from [<bf0541d0>] (mxs_mmc_enable_sdio_irq+0xc8/0xdc [mxs_mmc])
[ 65.470000] [<bf0541d0>] (mxs_mmc_enable_sdio_irq+0xc8/0xdc [mxs_mmc]) from [<c0219b38>] (sdio_irq_thread+0x1bc/0x274)
[ 65.470000] [<c0219b38>] (sdio_irq_thread+0x1bc/0x274) from [<c003c324>] (kthread+0x8c/0x98)
[ 65.470000] [<c003c324>] (kthread+0x8c/0x98) from [<c00101ac>] (kernel_thread_exit+0x0/0x8)
[ 65.470000] BUG: spinlock lockup suspected on CPU#0, ksdioirqd/mmc0/73
[ 65.470000] lock: 0xc3358724, .magic: dead4ead, .owner: ksdioirqd/mmc0/73, .owner_cpu: 0
[ 65.470000] [<c0014990>] (unwind_backtrace+0x0/0xf4) from [<c01b46b0>] (do_raw_spin_lock+0x100/0x144)
[ 65.470000] [<c01b46b0>] (do_raw_spin_lock+0x100/0x144) from [<c02f6724>] (_raw_spin_lock_irqsave+0x50/0x5c)
[ 65.470000] [<c02f6724>] (_raw_spin_lock_irqsave+0x50/0x5c) from [<bf054120>] (mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc])
[ 65.470000] [<bf054120>] (mxs_mmc_enable_sdio_irq+0x18/0xdc [mxs_mmc]) from [<bf0541d0>] (mxs_mmc_enable_sdio_irq+0xc8/0xdc [mxs_mmc])
[ 65.470000] [<bf0541d0>] (mxs_mmc_enable_sdio_irq+0xc8/0xdc [mxs_mmc]) from [<c0219b38>] (sdio_irq_thread+0x1bc/0x274)
[ 65.470000] [<c0219b38>] (sdio_irq_thread+0x1bc/0x274) from [<c003c324>] (kthread+0x8c/0x98)
[ 65.470000] [<c003c324>] (kthread+0x8c/0x98) from [<c00101ac>] (kernel_thread_exit+0x0/0x8)
---schnapp---
Any hints how to work around or fix this, would be appreciated
Attila Kinali
--
It is upon moral qualities that a society is ultimately founded. All
the prosperity and technological sophistication in the world is of no
use without that foundation.
-- Miss Matheson, The Diamond Age, Neil Stephenson
I ran into the same problem today, but the proposed fix doesn't seem
to work for me:
It's a different problem from what Lauri reported and fixed.
Ok...
I haven't
played SDIO card that much, so I'm not completely clear about the SDIO
calling sequence, but is it reasonable that mxs_mmc_enable_sdio_irq is
being called recursively?
I don't know. I dont know the code at all and not how the sdio system
works. But a quick check shows, that mxs_mmc_enable_sdio_irq does not
call any other function (besides readel, writel) and hence cannot call itself.
For me it rather looks like that there seem to be two consequtive
irqs that get passed to sdio_irq_thread which then calls
mxs_mmc_enable_sdio_irq.
But with my limited knowledge i cannot check this theory.
Can anyone give me some hints how i could verify this?
Attila Kinali
--
The trouble with you, Shev, is you don't say anything until you've saved
up a whole truckload of damned heavy brick arguments and then you dump
them all out and never look at the bleeding body mangled beneath the heap
-- Tirin, The Dispossessed, U. Le Guin
*mmc, int enable)
}
spin_unlock_irqrestore(&host->lock, flags);
+
+ if (enable && readl(host->base + HW_SSP_STATUS(host)) &
+ BM_SSP_STATUS_SDIO_IRQ)
+ mmc_signal_sdio_irq(host->mmc);
+
}
static const struct mmc_host_ops mxs_mmc_ops = {
<<<<<<<
mxs_mmc_enable_sdio_irq was called by mmc_signal_sdio_irq.
mmc_signal_sdio_irq was called inside spin lock. So the lock was tried
to acquire before it was released.
Best regards,
Lauri Hintsala
From: Attila Kinali <hidden> Date: 2012-07-16 12:07:20
Moin, Lauri,
On Mon, 16 Jul 2012 08:57:38 +0300
Lauri Hintsala [off-list ref] wrote:
Does this patch fix your issue?
A preliminary test shows that it at least fixes the oops at module loading.
I haven't had the chance yet to give it a full test, but i would say it
fixes it enough to be workable.
Thanks a lot!
Attila Kinali
--
The trouble with you, Shev, is you don't say anything until you've saved
up a whole truckload of damned heavy brick arguments and then you dump
them all out and never look at the bleeding body mangled beneath the heap
-- Tirin, The Dispossessed, U. Le Guin
*mmc, int enable)
}
spin_unlock_irqrestore(&host->lock, flags);
+
+ if (enable && readl(host->base + HW_SSP_STATUS(host)) &
+ BM_SSP_STATUS_SDIO_IRQ)
+ mmc_signal_sdio_irq(host->mmc);
+
}
static const struct mmc_host_ops mxs_mmc_ops = {
<<<<<<<
mxs_mmc_enable_sdio_irq was called by mmc_signal_sdio_irq.
mmc_signal_sdio_irq was called inside spin lock. So the lock was tried
to acquire before it was released.
Best regards,
Lauri Hintsala
--
To unsubscribe from this list: send the line "unsubscribe linux-mmc" in
the body of a message to majordomo at vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
*mmc, int enable)
}
spin_unlock_irqrestore(&host->lock, flags);
+
+ if (enable && readl(host->base + HW_SSP_STATUS(host)) &
+ BM_SSP_STATUS_SDIO_IRQ)
+ mmc_signal_sdio_irq(host->mmc);
+
}
static const struct mmc_host_ops mxs_mmc_ops = {
<<<<<<<
mxs_mmc_enable_sdio_irq was called by mmc_signal_sdio_irq.
mmc_signal_sdio_irq was called inside spin lock. So the lock was tried
to acquire before it was released.
Best regards,
Lauri Hintsala
--
To unsubscribe from this list: send the line "unsubscribe linux-mmc" in
the body of a message to majordomo at vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-mmc" in
the body of a message to majordomo at vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html