* [PATCH RESEND] mmc: sdhci-s3c: solve problem with sleeping in atomic context
@ 2015-02-04 9:16 Paul Osmialowski
2015-02-04 9:51 ` Jaehoon Chung
2015-02-04 12:41 ` Ulf Hansson
0 siblings, 2 replies; 3+ messages in thread
From: Paul Osmialowski @ 2015-02-04 9:16 UTC (permalink / raw)
To: Chris Ball, Ulf Hansson, linux-mmc, linux-kernel, Ben Dooks
Cc: Paul Osmialowski
This change addresses following problem:
[ 2.560726] ------------[ cut here ]------------
[ 2.565341] WARNING: CPU: 0 PID: 1 at kernel/locking/lockdep.c:2744 lockdep_trace_alloc+0xec/0x118()
[ 2.574439] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))
[ 2.579821] Modules linked in:
[ 2.583038] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 3.18.0-next-20141216-00002-g4ff197fc1902-dirty #1318
[ 2.593796] Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
[ 2.599892] [<c0014c44>] (unwind_backtrace) from [<c0011bbc>] (show_stack+0x10/0x14)
[ 2.607612] [<c0011bbc>] (show_stack) from [<c04953b8>] (dump_stack+0x70/0xbc)
[ 2.614822] [<c04953b8>] (dump_stack) from [<c0023444>] (warn_slowpath_common+0x74/0xb0)
[ 2.622885] [<c0023444>] (warn_slowpath_common) from [<c0023514>] (warn_slowpath_fmt+0x30/0x40)
[ 2.631569] [<c0023514>] (warn_slowpath_fmt) from [<c0063644>] (lockdep_trace_alloc+0xec/0x118)
[ 2.640246] [<c0063644>] (lockdep_trace_alloc) from [<c00df52c>] (__kmalloc+0x3c/0x1cc)
[ 2.648240] [<c00df52c>] (__kmalloc) from [<c0394970>] (clk_fetch_parent_index+0xb8/0xd4)
[ 2.656390] [<c0394970>] (clk_fetch_parent_index) from [<c0394a6c>] (clk_calc_new_rates+0xe0/0x1fc)
[ 2.665415] [<c0394a6c>] (clk_calc_new_rates) from [<c0394b40>] (clk_calc_new_rates+0x1b4/0x1fc)
[ 2.674181] [<c0394b40>] (clk_calc_new_rates) from [<c0395408>] (clk_set_rate+0x50/0xc8)
[ 2.682265] [<c0395408>] (clk_set_rate) from [<c0377708>] (sdhci_cmu_set_clock+0x68/0x16c)
[ 2.690503] [<c0377708>] (sdhci_cmu_set_clock) from [<c03735cc>] (sdhci_do_set_ios+0xf0/0x64c)
[ 2.699095] [<c03735cc>] (sdhci_do_set_ios) from [<c0373b48>] (sdhci_set_ios+0x20/0x2c)
[ 2.707080] [<c0373b48>] (sdhci_set_ios) from [<c035ddf0>] (mmc_power_up+0x118/0x1fc)
[ 2.714889] [<c035ddf0>] (mmc_power_up) from [<c035ecd0>] (mmc_start_host+0x44/0x6c)
[ 2.722615] [<c035ecd0>] (mmc_start_host) from [<c035fd60>] (mmc_add_host+0x58/0x7c)
[ 2.730341] [<c035fd60>] (mmc_add_host) from [<c037454c>] (sdhci_add_host+0x968/0xd94)
[ 2.738240] [<c037454c>] (sdhci_add_host) from [<c0377b60>] (sdhci_s3c_probe+0x354/0x52c)
[ 2.746406] [<c0377b60>] (sdhci_s3c_probe) from [<c0283b58>] (platform_drv_probe+0x48/0xa4)
[ 2.754733] [<c0283b58>] (platform_drv_probe) from [<c02824e8>] (driver_probe_device+0x13c/0x37c)
[ 2.763585] [<c02824e8>] (driver_probe_device) from [<c02827bc>] (__driver_attach+0x94/0x98)
[ 2.772003] [<c02827bc>] (__driver_attach) from [<c0280a60>] (bus_for_each_dev+0x54/0x88)
[ 2.780163] [<c0280a60>] (bus_for_each_dev) from [<c0281b48>] (bus_add_driver+0xe4/0x200)
[ 2.788322] [<c0281b48>] (bus_add_driver) from [<c0282dfc>] (driver_register+0x78/0xf4)
[ 2.796308] [<c0282dfc>] (driver_register) from [<c00089b0>] (do_one_initcall+0xac/0x1f0)
[ 2.804473] [<c00089b0>] (do_one_initcall) from [<c0673d94>] (kernel_init_freeable+0x10c/0x1d8)
[ 2.813153] [<c0673d94>] (kernel_init_freeable) from [<c0490058>] (kernel_init+0x28/0x108)
[ 2.821398] [<c0490058>] (kernel_init) from [<c000f268>] (ret_from_fork+0x14/0x2c)
[ 2.828939] ---[ end trace 03cc00e539849d1f ]---
clk_set_rate() tries to take clk's prepare_lock mutex while being in atomic
context entered in sdhci_do_set_ios().
The solution is inspired by similar situation in sdhci_set_power() also called
from sdhci_do_set_ios():
spin_unlock_irq(&host->lock);
mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
spin_lock_irq(&host->lock);
Note that since sdhci_s3c_set_clock() sets SDHCI_CLOCK_CARD_EN, proposed change
first resets this bit. It is reset anyway (by setting SDHCI_CLOCK_INT_EN bit
only) after call to clk_set_rate() in order to wait for the clock to stabilize
and is set again as soon as the clock becomes stable.
Signed-off-by: Paul Osmialowski <p.osmialowsk@samsung.com>
---
drivers/mmc/host/sdhci-s3c.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index c45b893..115f556 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -12,6 +12,7 @@
* published by the Free Software Foundation.
*/
+#include <linux/spinlock.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/platform_device.h>
@@ -312,7 +313,14 @@ static void sdhci_cmu_set_clock(struct sdhci_host *host, unsigned int clock)
sdhci_s3c_set_clock(host, clock);
+ /* Reset SD Clock Enable */
+ clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
+ clk &= ~SDHCI_CLOCK_CARD_EN;
+ sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
+
+ spin_unlock_irq(&host->lock);
ret = clk_set_rate(ourhost->clk_bus[ourhost->cur_clk], clock);
+ spin_lock_irq(&host->lock);
if (ret != 0) {
dev_err(dev, "%s: failed to set clock rate %uHz\n",
mmc_hostname(host->mmc), clock);
--
1.9.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH RESEND] mmc: sdhci-s3c: solve problem with sleeping in atomic context
2015-02-04 9:16 [PATCH RESEND] mmc: sdhci-s3c: solve problem with sleeping in atomic context Paul Osmialowski
@ 2015-02-04 9:51 ` Jaehoon Chung
2015-02-04 12:41 ` Ulf Hansson
1 sibling, 0 replies; 3+ messages in thread
From: Jaehoon Chung @ 2015-02-04 9:51 UTC (permalink / raw)
To: Paul Osmialowski, Chris Ball, Ulf Hansson, linux-mmc,
linux-kernel, Ben Dooks
Hi.
Tested-by: Jaehoon Chung <jh80.chung@samsung.com>
(with exynos4 board)
Acked-by: Jaehoon Chung <jh80.chung@samsung.com>
Best Regards,
Jaehoon Chung
On 02/04/2015 06:16 PM, Paul Osmialowski wrote:
> This change addresses following problem:
>
> [ 2.560726] ------------[ cut here ]------------
> [ 2.565341] WARNING: CPU: 0 PID: 1 at kernel/locking/lockdep.c:2744 lockdep_trace_alloc+0xec/0x118()
> [ 2.574439] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))
> [ 2.579821] Modules linked in:
> [ 2.583038] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 3.18.0-next-20141216-00002-g4ff197fc1902-dirty #1318
> [ 2.593796] Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
> [ 2.599892] [<c0014c44>] (unwind_backtrace) from [<c0011bbc>] (show_stack+0x10/0x14)
> [ 2.607612] [<c0011bbc>] (show_stack) from [<c04953b8>] (dump_stack+0x70/0xbc)
> [ 2.614822] [<c04953b8>] (dump_stack) from [<c0023444>] (warn_slowpath_common+0x74/0xb0)
> [ 2.622885] [<c0023444>] (warn_slowpath_common) from [<c0023514>] (warn_slowpath_fmt+0x30/0x40)
> [ 2.631569] [<c0023514>] (warn_slowpath_fmt) from [<c0063644>] (lockdep_trace_alloc+0xec/0x118)
> [ 2.640246] [<c0063644>] (lockdep_trace_alloc) from [<c00df52c>] (__kmalloc+0x3c/0x1cc)
> [ 2.648240] [<c00df52c>] (__kmalloc) from [<c0394970>] (clk_fetch_parent_index+0xb8/0xd4)
> [ 2.656390] [<c0394970>] (clk_fetch_parent_index) from [<c0394a6c>] (clk_calc_new_rates+0xe0/0x1fc)
> [ 2.665415] [<c0394a6c>] (clk_calc_new_rates) from [<c0394b40>] (clk_calc_new_rates+0x1b4/0x1fc)
> [ 2.674181] [<c0394b40>] (clk_calc_new_rates) from [<c0395408>] (clk_set_rate+0x50/0xc8)
> [ 2.682265] [<c0395408>] (clk_set_rate) from [<c0377708>] (sdhci_cmu_set_clock+0x68/0x16c)
> [ 2.690503] [<c0377708>] (sdhci_cmu_set_clock) from [<c03735cc>] (sdhci_do_set_ios+0xf0/0x64c)
> [ 2.699095] [<c03735cc>] (sdhci_do_set_ios) from [<c0373b48>] (sdhci_set_ios+0x20/0x2c)
> [ 2.707080] [<c0373b48>] (sdhci_set_ios) from [<c035ddf0>] (mmc_power_up+0x118/0x1fc)
> [ 2.714889] [<c035ddf0>] (mmc_power_up) from [<c035ecd0>] (mmc_start_host+0x44/0x6c)
> [ 2.722615] [<c035ecd0>] (mmc_start_host) from [<c035fd60>] (mmc_add_host+0x58/0x7c)
> [ 2.730341] [<c035fd60>] (mmc_add_host) from [<c037454c>] (sdhci_add_host+0x968/0xd94)
> [ 2.738240] [<c037454c>] (sdhci_add_host) from [<c0377b60>] (sdhci_s3c_probe+0x354/0x52c)
> [ 2.746406] [<c0377b60>] (sdhci_s3c_probe) from [<c0283b58>] (platform_drv_probe+0x48/0xa4)
> [ 2.754733] [<c0283b58>] (platform_drv_probe) from [<c02824e8>] (driver_probe_device+0x13c/0x37c)
> [ 2.763585] [<c02824e8>] (driver_probe_device) from [<c02827bc>] (__driver_attach+0x94/0x98)
> [ 2.772003] [<c02827bc>] (__driver_attach) from [<c0280a60>] (bus_for_each_dev+0x54/0x88)
> [ 2.780163] [<c0280a60>] (bus_for_each_dev) from [<c0281b48>] (bus_add_driver+0xe4/0x200)
> [ 2.788322] [<c0281b48>] (bus_add_driver) from [<c0282dfc>] (driver_register+0x78/0xf4)
> [ 2.796308] [<c0282dfc>] (driver_register) from [<c00089b0>] (do_one_initcall+0xac/0x1f0)
> [ 2.804473] [<c00089b0>] (do_one_initcall) from [<c0673d94>] (kernel_init_freeable+0x10c/0x1d8)
> [ 2.813153] [<c0673d94>] (kernel_init_freeable) from [<c0490058>] (kernel_init+0x28/0x108)
> [ 2.821398] [<c0490058>] (kernel_init) from [<c000f268>] (ret_from_fork+0x14/0x2c)
> [ 2.828939] ---[ end trace 03cc00e539849d1f ]---
>
> clk_set_rate() tries to take clk's prepare_lock mutex while being in atomic
> context entered in sdhci_do_set_ios().
>
> The solution is inspired by similar situation in sdhci_set_power() also called
> from sdhci_do_set_ios():
>
> spin_unlock_irq(&host->lock);
> mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
> spin_lock_irq(&host->lock);
>
> Note that since sdhci_s3c_set_clock() sets SDHCI_CLOCK_CARD_EN, proposed change
> first resets this bit. It is reset anyway (by setting SDHCI_CLOCK_INT_EN bit
> only) after call to clk_set_rate() in order to wait for the clock to stabilize
> and is set again as soon as the clock becomes stable.
>
> Signed-off-by: Paul Osmialowski <p.osmialowsk@samsung.com>
> ---
> drivers/mmc/host/sdhci-s3c.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
> index c45b893..115f556 100644
> --- a/drivers/mmc/host/sdhci-s3c.c
> +++ b/drivers/mmc/host/sdhci-s3c.c
> @@ -12,6 +12,7 @@
> * published by the Free Software Foundation.
> */
>
> +#include <linux/spinlock.h>
> #include <linux/delay.h>
> #include <linux/dma-mapping.h>
> #include <linux/platform_device.h>
> @@ -312,7 +313,14 @@ static void sdhci_cmu_set_clock(struct sdhci_host *host, unsigned int clock)
>
> sdhci_s3c_set_clock(host, clock);
>
> + /* Reset SD Clock Enable */
> + clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
> + clk &= ~SDHCI_CLOCK_CARD_EN;
> + sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
> +
> + spin_unlock_irq(&host->lock);
> ret = clk_set_rate(ourhost->clk_bus[ourhost->cur_clk], clock);
> + spin_lock_irq(&host->lock);
> if (ret != 0) {
> dev_err(dev, "%s: failed to set clock rate %uHz\n",
> mmc_hostname(host->mmc), clock);
>
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH RESEND] mmc: sdhci-s3c: solve problem with sleeping in atomic context
2015-02-04 9:16 [PATCH RESEND] mmc: sdhci-s3c: solve problem with sleeping in atomic context Paul Osmialowski
2015-02-04 9:51 ` Jaehoon Chung
@ 2015-02-04 12:41 ` Ulf Hansson
1 sibling, 0 replies; 3+ messages in thread
From: Ulf Hansson @ 2015-02-04 12:41 UTC (permalink / raw)
To: Paul Osmialowski; +Cc: Chris Ball, linux-mmc, linux-kernel, Ben Dooks
On 4 February 2015 at 10:16, Paul Osmialowski <p.osmialowsk@samsung.com> wrote:
> This change addresses following problem:
>
> [ 2.560726] ------------[ cut here ]------------
> [ 2.565341] WARNING: CPU: 0 PID: 1 at kernel/locking/lockdep.c:2744 lockdep_trace_alloc+0xec/0x118()
> [ 2.574439] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))
> [ 2.579821] Modules linked in:
> [ 2.583038] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 3.18.0-next-20141216-00002-g4ff197fc1902-dirty #1318
> [ 2.593796] Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
> [ 2.599892] [<c0014c44>] (unwind_backtrace) from [<c0011bbc>] (show_stack+0x10/0x14)
> [ 2.607612] [<c0011bbc>] (show_stack) from [<c04953b8>] (dump_stack+0x70/0xbc)
> [ 2.614822] [<c04953b8>] (dump_stack) from [<c0023444>] (warn_slowpath_common+0x74/0xb0)
> [ 2.622885] [<c0023444>] (warn_slowpath_common) from [<c0023514>] (warn_slowpath_fmt+0x30/0x40)
> [ 2.631569] [<c0023514>] (warn_slowpath_fmt) from [<c0063644>] (lockdep_trace_alloc+0xec/0x118)
> [ 2.640246] [<c0063644>] (lockdep_trace_alloc) from [<c00df52c>] (__kmalloc+0x3c/0x1cc)
> [ 2.648240] [<c00df52c>] (__kmalloc) from [<c0394970>] (clk_fetch_parent_index+0xb8/0xd4)
> [ 2.656390] [<c0394970>] (clk_fetch_parent_index) from [<c0394a6c>] (clk_calc_new_rates+0xe0/0x1fc)
> [ 2.665415] [<c0394a6c>] (clk_calc_new_rates) from [<c0394b40>] (clk_calc_new_rates+0x1b4/0x1fc)
> [ 2.674181] [<c0394b40>] (clk_calc_new_rates) from [<c0395408>] (clk_set_rate+0x50/0xc8)
> [ 2.682265] [<c0395408>] (clk_set_rate) from [<c0377708>] (sdhci_cmu_set_clock+0x68/0x16c)
> [ 2.690503] [<c0377708>] (sdhci_cmu_set_clock) from [<c03735cc>] (sdhci_do_set_ios+0xf0/0x64c)
> [ 2.699095] [<c03735cc>] (sdhci_do_set_ios) from [<c0373b48>] (sdhci_set_ios+0x20/0x2c)
> [ 2.707080] [<c0373b48>] (sdhci_set_ios) from [<c035ddf0>] (mmc_power_up+0x118/0x1fc)
> [ 2.714889] [<c035ddf0>] (mmc_power_up) from [<c035ecd0>] (mmc_start_host+0x44/0x6c)
> [ 2.722615] [<c035ecd0>] (mmc_start_host) from [<c035fd60>] (mmc_add_host+0x58/0x7c)
> [ 2.730341] [<c035fd60>] (mmc_add_host) from [<c037454c>] (sdhci_add_host+0x968/0xd94)
> [ 2.738240] [<c037454c>] (sdhci_add_host) from [<c0377b60>] (sdhci_s3c_probe+0x354/0x52c)
> [ 2.746406] [<c0377b60>] (sdhci_s3c_probe) from [<c0283b58>] (platform_drv_probe+0x48/0xa4)
> [ 2.754733] [<c0283b58>] (platform_drv_probe) from [<c02824e8>] (driver_probe_device+0x13c/0x37c)
> [ 2.763585] [<c02824e8>] (driver_probe_device) from [<c02827bc>] (__driver_attach+0x94/0x98)
> [ 2.772003] [<c02827bc>] (__driver_attach) from [<c0280a60>] (bus_for_each_dev+0x54/0x88)
> [ 2.780163] [<c0280a60>] (bus_for_each_dev) from [<c0281b48>] (bus_add_driver+0xe4/0x200)
> [ 2.788322] [<c0281b48>] (bus_add_driver) from [<c0282dfc>] (driver_register+0x78/0xf4)
> [ 2.796308] [<c0282dfc>] (driver_register) from [<c00089b0>] (do_one_initcall+0xac/0x1f0)
> [ 2.804473] [<c00089b0>] (do_one_initcall) from [<c0673d94>] (kernel_init_freeable+0x10c/0x1d8)
> [ 2.813153] [<c0673d94>] (kernel_init_freeable) from [<c0490058>] (kernel_init+0x28/0x108)
> [ 2.821398] [<c0490058>] (kernel_init) from [<c000f268>] (ret_from_fork+0x14/0x2c)
> [ 2.828939] ---[ end trace 03cc00e539849d1f ]---
>
> clk_set_rate() tries to take clk's prepare_lock mutex while being in atomic
> context entered in sdhci_do_set_ios().
>
> The solution is inspired by similar situation in sdhci_set_power() also called
> from sdhci_do_set_ios():
>
> spin_unlock_irq(&host->lock);
> mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
> spin_lock_irq(&host->lock);
>
> Note that since sdhci_s3c_set_clock() sets SDHCI_CLOCK_CARD_EN, proposed change
> first resets this bit. It is reset anyway (by setting SDHCI_CLOCK_INT_EN bit
> only) after call to clk_set_rate() in order to wait for the clock to stabilize
> and is set again as soon as the clock becomes stable.
>
> Signed-off-by: Paul Osmialowski <p.osmialowsk@samsung.com>
Thanks! Applied for next.
Kind regards
Uffe
> ---
> drivers/mmc/host/sdhci-s3c.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
> index c45b893..115f556 100644
> --- a/drivers/mmc/host/sdhci-s3c.c
> +++ b/drivers/mmc/host/sdhci-s3c.c
> @@ -12,6 +12,7 @@
> * published by the Free Software Foundation.
> */
>
> +#include <linux/spinlock.h>
> #include <linux/delay.h>
> #include <linux/dma-mapping.h>
> #include <linux/platform_device.h>
> @@ -312,7 +313,14 @@ static void sdhci_cmu_set_clock(struct sdhci_host *host, unsigned int clock)
>
> sdhci_s3c_set_clock(host, clock);
>
> + /* Reset SD Clock Enable */
> + clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
> + clk &= ~SDHCI_CLOCK_CARD_EN;
> + sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
> +
> + spin_unlock_irq(&host->lock);
> ret = clk_set_rate(ourhost->clk_bus[ourhost->cur_clk], clock);
> + spin_lock_irq(&host->lock);
> if (ret != 0) {
> dev_err(dev, "%s: failed to set clock rate %uHz\n",
> mmc_hostname(host->mmc), clock);
> --
> 1.9.1
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2015-02-04 12:41 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-02-04 9:16 [PATCH RESEND] mmc: sdhci-s3c: solve problem with sleeping in atomic context Paul Osmialowski
2015-02-04 9:51 ` Jaehoon Chung
2015-02-04 12:41 ` Ulf Hansson
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).