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>
Tested-by: Jaehoon Chung <jh80.chung@samsung.com>
Acked-by: Jaehoon Chung <jh80.chung@samsung.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>