From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755938AbbAPObG (ORCPT ); Fri, 16 Jan 2015 09:31:06 -0500 Received: from mailout1.w1.samsung.com ([210.118.77.11]:50454 "EHLO mailout1.w1.samsung.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752090AbbAPObC (ORCPT ); Fri, 16 Jan 2015 09:31:02 -0500 X-AuditID: cbfec7f4-b7f126d000001e9a-2b-54b920a36dff From: Paul Osmialowski To: Chris Ball , Ulf Hansson , linux-mmc@vger.kernel.org, linux-kernel@vger.kernel.org Cc: Paul Osmialowski Subject: [PATCH] mmc: sdhci-s3c: solve problem with sleeping in atomic context Date: Fri, 16 Jan 2015 15:30:05 +0100 Message-id: <1421418605-457-1-git-send-email-p.osmialowsk@samsung.com> X-Mailer: git-send-email 1.9.1 X-Brightmail-Tracker: H4sIAAAAAAAAA+NgFjrDJMWRmVeSWpSXmKPExsVy+t/xq7pLFHaGGOzhsZhweTujxeVdc9gs jvzvZ7SY8OYAs8XxteEOrB53ru1h87jxaiGTR9+WVYwenzfJBbBEcdmkpOZklqUW6dslcGXs XRlY8ECt4nTXReYGxm7FLkZODgkBE4n/txYwQthiEhfurWfrYuTiEBJYyijRdOkIO4TTyyRx /dZENpAqNgFDiZv/D4N1iAg0MUpM/+gLYjML6Es09T9lBrGFBfwkfnW9YwKxWQRUJZo2TgaL 8wq4SfQuvsoMsU1O4uSxyawTGLkXMDKsYhRNLU0uKE5KzzXUK07MLS7NS9dLzs/dxAgJgS87 GBcfszrEKMDBqMTDO2PLjhAh1sSy4srcQ4wSHMxKIrwZAjtDhHhTEiurUovy44tKc1KLDzEy cXBKNTCq/u+ax6aSzdHv2vVhq926v1+2nYx4n7JwT89/jwjGdL2dsdOkd+rc1fW7Me+m3to9 U8XOBbD1Sa7z++0zbckhzeP/si+1zTn7ecUu5aNP7iy/un4K+/+3x9+GsZbpv/H/sCjn48RD X7fzvj00YeG/3TpRFo8ergs93VS2nMP33ovqf4qMHut6LiuxFGckGmoxFxUnAgDRFn0x3wEA AA== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 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] [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [ 2.607612] [] (show_stack) from [] (dump_stack+0x70/0xbc) [ 2.614822] [] (dump_stack) from [] (warn_slowpath_common+0x74/0xb0) [ 2.622885] [] (warn_slowpath_common) from [] (warn_slowpath_fmt+0x30/0x40) [ 2.631569] [] (warn_slowpath_fmt) from [] (lockdep_trace_alloc+0xec/0x118) [ 2.640246] [] (lockdep_trace_alloc) from [] (__kmalloc+0x3c/0x1cc) [ 2.648240] [] (__kmalloc) from [] (clk_fetch_parent_index+0xb8/0xd4) [ 2.656390] [] (clk_fetch_parent_index) from [] (clk_calc_new_rates+0xe0/0x1fc) [ 2.665415] [] (clk_calc_new_rates) from [] (clk_calc_new_rates+0x1b4/0x1fc) [ 2.674181] [] (clk_calc_new_rates) from [] (clk_set_rate+0x50/0xc8) [ 2.682265] [] (clk_set_rate) from [] (sdhci_cmu_set_clock+0x68/0x16c) [ 2.690503] [] (sdhci_cmu_set_clock) from [] (sdhci_do_set_ios+0xf0/0x64c) [ 2.699095] [] (sdhci_do_set_ios) from [] (sdhci_set_ios+0x20/0x2c) [ 2.707080] [] (sdhci_set_ios) from [] (mmc_power_up+0x118/0x1fc) [ 2.714889] [] (mmc_power_up) from [] (mmc_start_host+0x44/0x6c) [ 2.722615] [] (mmc_start_host) from [] (mmc_add_host+0x58/0x7c) [ 2.730341] [] (mmc_add_host) from [] (sdhci_add_host+0x968/0xd94) [ 2.738240] [] (sdhci_add_host) from [] (sdhci_s3c_probe+0x354/0x52c) [ 2.746406] [] (sdhci_s3c_probe) from [] (platform_drv_probe+0x48/0xa4) [ 2.754733] [] (platform_drv_probe) from [] (driver_probe_device+0x13c/0x37c) [ 2.763585] [] (driver_probe_device) from [] (__driver_attach+0x94/0x98) [ 2.772003] [] (__driver_attach) from [] (bus_for_each_dev+0x54/0x88) [ 2.780163] [] (bus_for_each_dev) from [] (bus_add_driver+0xe4/0x200) [ 2.788322] [] (bus_add_driver) from [] (driver_register+0x78/0xf4) [ 2.796308] [] (driver_register) from [] (do_one_initcall+0xac/0x1f0) [ 2.804473] [] (do_one_initcall) from [] (kernel_init_freeable+0x10c/0x1d8) [ 2.813153] [] (kernel_init_freeable) from [] (kernel_init+0x28/0x108) [ 2.821398] [] (kernel_init) from [] (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 --- 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 #include #include #include @@ -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