Merge tag 'mmc-v5.4-2' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc

Pull more MMC updates from Ulf Hansson:
 "A couple more updates/fixes for MMC:

   - sdhci-pci: Add Genesys Logic GL975x support

   - sdhci-tegra: Recover loss in throughput for DMA

   - sdhci-of-esdhc: Fix DMA bug"

* tag 'mmc-v5.4-2' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc:
  mmc: host: sdhci-pci: Add Genesys Logic GL975x support
  mmc: tegra: Implement ->set_dma_mask()
  mmc: sdhci: Let drivers define their DMA mask
  mmc: sdhci-of-esdhc: set DMA snooping based on DMA coherence
  mmc: sdhci: improve ADMA error reporting

drivers/mmc/host/Kconfig

@@ -94,6 +94,7 @@ config MMC_SDHCI_PCI
 	depends on MMC_SDHCI && PCI
 	select MMC_CQHCI
 	select IOSF_MBI if X86
+	select MMC_SDHCI_IO_ACCESSORS
 	help
 	  This selects the PCI Secure Digital Host Controller Interface.
 	  Most controllers found today are PCI devices.

drivers/mmc/host/Makefile

@@ -13,7 +13,7 @@ obj-$(CONFIG_MMC_MXS)		+= mxs-mmc.o
 obj-$(CONFIG_MMC_SDHCI)		+= sdhci.o
 obj-$(CONFIG_MMC_SDHCI_PCI)	+= sdhci-pci.o
 sdhci-pci-y			+= sdhci-pci-core.o sdhci-pci-o2micro.o sdhci-pci-arasan.o \
-				   sdhci-pci-dwc-mshc.o
+				   sdhci-pci-dwc-mshc.o sdhci-pci-gli.o
 obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI))	+= sdhci-pci-data.o
 obj-$(CONFIG_MMC_SDHCI_ACPI)	+= sdhci-acpi.o
 obj-$(CONFIG_MMC_SDHCI_PXAV3)	+= sdhci-pxav3.o

drivers/mmc/host/sdhci-of-esdhc.c

@@ -495,7 +495,12 @@ static int esdhc_of_enable_dma(struct sdhci_host *host)
 		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
 
 	value = sdhci_readl(host, ESDHC_DMA_SYSCTL);
+
+	if (of_dma_is_coherent(dev->of_node))
 		value |= ESDHC_DMA_SNOOP;
+	else
+		value &= ~ESDHC_DMA_SNOOP;
+
 	sdhci_writel(host, value, ESDHC_DMA_SYSCTL);
 	return 0;
 }

drivers/mmc/host/sdhci-pci-core.c

@@ -1685,6 +1685,8 @@ static const struct pci_device_id pci_ids[] = {
 	SDHCI_PCI_DEVICE(O2, SEABIRD1, o2),
 	SDHCI_PCI_DEVICE(ARASAN, PHY_EMMC, arasan),
 	SDHCI_PCI_DEVICE(SYNOPSYS, DWC_MSHC, snps),
+	SDHCI_PCI_DEVICE(GLI, 9750, gl9750),
+	SDHCI_PCI_DEVICE(GLI, 9755, gl9755),
 	SDHCI_PCI_DEVICE_CLASS(AMD, SYSTEM_SDHCI, PCI_CLASS_MASK, amd),
 	/* Generic SD host controller */
 	{PCI_DEVICE_CLASS(SYSTEM_SDHCI, PCI_CLASS_MASK)},

drivers/mmc/host/sdhci-pci-gli.c

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 Genesys Logic, Inc.
+ *
+ * Authors: Ben Chuang <ben.chuang@genesyslogic.com.tw>
+ *
+ * Version: v0.9.0 (2019-08-08)
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/pci.h>
+#include <linux/mmc/mmc.h>
+#include <linux/delay.h>
+#include "sdhci.h"
+#include "sdhci-pci.h"
+
+/*  Genesys Logic extra registers */
+#define SDHCI_GLI_9750_WT         0x800
+#define   SDHCI_GLI_9750_WT_EN      BIT(0)
+#define   GLI_9750_WT_EN_ON	    0x1
+#define   GLI_9750_WT_EN_OFF	    0x0
+
+#define SDHCI_GLI_9750_DRIVING      0x860
+#define   SDHCI_GLI_9750_DRIVING_1    GENMASK(11, 0)
+#define   SDHCI_GLI_9750_DRIVING_2    GENMASK(27, 26)
+#define   GLI_9750_DRIVING_1_VALUE    0xFFF
+#define   GLI_9750_DRIVING_2_VALUE    0x3
+
+#define SDHCI_GLI_9750_PLL	      0x864
+#define   SDHCI_GLI_9750_PLL_TX2_INV    BIT(23)
+#define   SDHCI_GLI_9750_PLL_TX2_DLY    GENMASK(22, 20)
+#define   GLI_9750_PLL_TX2_INV_VALUE    0x1
+#define   GLI_9750_PLL_TX2_DLY_VALUE    0x0
+
+#define SDHCI_GLI_9750_SW_CTRL      0x874
+#define   SDHCI_GLI_9750_SW_CTRL_4    GENMASK(7, 6)
+#define   GLI_9750_SW_CTRL_4_VALUE    0x3
+
+#define SDHCI_GLI_9750_MISC            0x878
+#define   SDHCI_GLI_9750_MISC_TX1_INV    BIT(2)
+#define   SDHCI_GLI_9750_MISC_RX_INV     BIT(3)
+#define   SDHCI_GLI_9750_MISC_TX1_DLY    GENMASK(6, 4)
+#define   GLI_9750_MISC_TX1_INV_VALUE    0x0
+#define   GLI_9750_MISC_RX_INV_ON        0x1
+#define   GLI_9750_MISC_RX_INV_OFF       0x0
+#define   GLI_9750_MISC_RX_INV_VALUE     GLI_9750_MISC_RX_INV_OFF
+#define   GLI_9750_MISC_TX1_DLY_VALUE    0x5
+
+#define SDHCI_GLI_9750_TUNING_CONTROL	          0x540
+#define   SDHCI_GLI_9750_TUNING_CONTROL_EN          BIT(4)
+#define   GLI_9750_TUNING_CONTROL_EN_ON             0x1
+#define   GLI_9750_TUNING_CONTROL_EN_OFF            0x0
+#define   SDHCI_GLI_9750_TUNING_CONTROL_GLITCH_1    BIT(16)
+#define   SDHCI_GLI_9750_TUNING_CONTROL_GLITCH_2    GENMASK(20, 19)
+#define   GLI_9750_TUNING_CONTROL_GLITCH_1_VALUE    0x1
+#define   GLI_9750_TUNING_CONTROL_GLITCH_2_VALUE    0x2
+
+#define SDHCI_GLI_9750_TUNING_PARAMETERS           0x544
+#define   SDHCI_GLI_9750_TUNING_PARAMETERS_RX_DLY    GENMASK(2, 0)
+#define   GLI_9750_TUNING_PARAMETERS_RX_DLY_VALUE    0x1
+
+#define GLI_MAX_TUNING_LOOP 40
+
+/* Genesys Logic chipset */
+static inline void gl9750_wt_on(struct sdhci_host *host)
+{
+	u32 wt_value;
+	u32 wt_enable;
+
+	wt_value = sdhci_readl(host, SDHCI_GLI_9750_WT);
+	wt_enable = FIELD_GET(SDHCI_GLI_9750_WT_EN, wt_value);
+
+	if (wt_enable == GLI_9750_WT_EN_ON)
+		return;
+
+	wt_value &= ~SDHCI_GLI_9750_WT_EN;
+	wt_value |= FIELD_PREP(SDHCI_GLI_9750_WT_EN, GLI_9750_WT_EN_ON);
+
+	sdhci_writel(host, wt_value, SDHCI_GLI_9750_WT);
+}
+
+static inline void gl9750_wt_off(struct sdhci_host *host)
+{
+	u32 wt_value;
+	u32 wt_enable;
+
+	wt_value = sdhci_readl(host, SDHCI_GLI_9750_WT);
+	wt_enable = FIELD_GET(SDHCI_GLI_9750_WT_EN, wt_value);
+
+	if (wt_enable == GLI_9750_WT_EN_OFF)
+		return;
+
+	wt_value &= ~SDHCI_GLI_9750_WT_EN;
+	wt_value |= FIELD_PREP(SDHCI_GLI_9750_WT_EN, GLI_9750_WT_EN_OFF);
+
+	sdhci_writel(host, wt_value, SDHCI_GLI_9750_WT);
+}
+
+static void gli_set_9750(struct sdhci_host *host)
+{
+	u32 driving_value;
+	u32 pll_value;
+	u32 sw_ctrl_value;
+	u32 misc_value;
+	u32 parameter_value;
+	u32 control_value;
+	u16 ctrl2;
+
+	gl9750_wt_on(host);
+
+	driving_value = sdhci_readl(host, SDHCI_GLI_9750_DRIVING);
+	pll_value = sdhci_readl(host, SDHCI_GLI_9750_PLL);
+	sw_ctrl_value = sdhci_readl(host, SDHCI_GLI_9750_SW_CTRL);
+	misc_value = sdhci_readl(host, SDHCI_GLI_9750_MISC);
+	parameter_value = sdhci_readl(host, SDHCI_GLI_9750_TUNING_PARAMETERS);
+	control_value = sdhci_readl(host, SDHCI_GLI_9750_TUNING_CONTROL);
+
+	driving_value &= ~(SDHCI_GLI_9750_DRIVING_1);
+	driving_value &= ~(SDHCI_GLI_9750_DRIVING_2);
+	driving_value |= FIELD_PREP(SDHCI_GLI_9750_DRIVING_1,
+				    GLI_9750_DRIVING_1_VALUE);
+	driving_value |= FIELD_PREP(SDHCI_GLI_9750_DRIVING_2,
+				    GLI_9750_DRIVING_2_VALUE);
+	sdhci_writel(host, driving_value, SDHCI_GLI_9750_DRIVING);
+
+	sw_ctrl_value &= ~SDHCI_GLI_9750_SW_CTRL_4;
+	sw_ctrl_value |= FIELD_PREP(SDHCI_GLI_9750_SW_CTRL_4,
+				    GLI_9750_SW_CTRL_4_VALUE);
+	sdhci_writel(host, sw_ctrl_value, SDHCI_GLI_9750_SW_CTRL);
+
+	/* reset the tuning flow after reinit and before starting tuning */
+	pll_value &= ~SDHCI_GLI_9750_PLL_TX2_INV;
+	pll_value &= ~SDHCI_GLI_9750_PLL_TX2_DLY;
+	pll_value |= FIELD_PREP(SDHCI_GLI_9750_PLL_TX2_INV,
+				GLI_9750_PLL_TX2_INV_VALUE);
+	pll_value |= FIELD_PREP(SDHCI_GLI_9750_PLL_TX2_DLY,
+				GLI_9750_PLL_TX2_DLY_VALUE);
+
+	misc_value &= ~SDHCI_GLI_9750_MISC_TX1_INV;
+	misc_value &= ~SDHCI_GLI_9750_MISC_RX_INV;
+	misc_value &= ~SDHCI_GLI_9750_MISC_TX1_DLY;
+	misc_value |= FIELD_PREP(SDHCI_GLI_9750_MISC_TX1_INV,
+				 GLI_9750_MISC_TX1_INV_VALUE);
+	misc_value |= FIELD_PREP(SDHCI_GLI_9750_MISC_RX_INV,
+				 GLI_9750_MISC_RX_INV_VALUE);
+	misc_value |= FIELD_PREP(SDHCI_GLI_9750_MISC_TX1_DLY,
+				 GLI_9750_MISC_TX1_DLY_VALUE);
+
+	parameter_value &= ~SDHCI_GLI_9750_TUNING_PARAMETERS_RX_DLY;
+	parameter_value |= FIELD_PREP(SDHCI_GLI_9750_TUNING_PARAMETERS_RX_DLY,
+				      GLI_9750_TUNING_PARAMETERS_RX_DLY_VALUE);
+
+	control_value &= ~SDHCI_GLI_9750_TUNING_CONTROL_GLITCH_1;
+	control_value &= ~SDHCI_GLI_9750_TUNING_CONTROL_GLITCH_2;
+	control_value |= FIELD_PREP(SDHCI_GLI_9750_TUNING_CONTROL_GLITCH_1,
+				    GLI_9750_TUNING_CONTROL_GLITCH_1_VALUE);
+	control_value |= FIELD_PREP(SDHCI_GLI_9750_TUNING_CONTROL_GLITCH_2,
+				    GLI_9750_TUNING_CONTROL_GLITCH_2_VALUE);
+
+	sdhci_writel(host, pll_value, SDHCI_GLI_9750_PLL);
+	sdhci_writel(host, misc_value, SDHCI_GLI_9750_MISC);
+
+	/* disable tuned clk */
+	ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	ctrl2 &= ~SDHCI_CTRL_TUNED_CLK;
+	sdhci_writew(host, ctrl2, SDHCI_HOST_CONTROL2);
+
+	/* enable tuning parameters control */
+	control_value &= ~SDHCI_GLI_9750_TUNING_CONTROL_EN;
+	control_value |= FIELD_PREP(SDHCI_GLI_9750_TUNING_CONTROL_EN,
+				    GLI_9750_TUNING_CONTROL_EN_ON);
+	sdhci_writel(host, control_value, SDHCI_GLI_9750_TUNING_CONTROL);
+
+	/* write tuning parameters */
+	sdhci_writel(host, parameter_value, SDHCI_GLI_9750_TUNING_PARAMETERS);
+
+	/* disable tuning parameters control */
+	control_value &= ~SDHCI_GLI_9750_TUNING_CONTROL_EN;
+	control_value |= FIELD_PREP(SDHCI_GLI_9750_TUNING_CONTROL_EN,
+				    GLI_9750_TUNING_CONTROL_EN_OFF);
+	sdhci_writel(host, control_value, SDHCI_GLI_9750_TUNING_CONTROL);
+
+	/* clear tuned clk */
+	ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	ctrl2 &= ~SDHCI_CTRL_TUNED_CLK;
+	sdhci_writew(host, ctrl2, SDHCI_HOST_CONTROL2);
+
+	gl9750_wt_off(host);
+}
+
+static void gli_set_9750_rx_inv(struct sdhci_host *host, bool b)
+{
+	u32 misc_value;
+
+	gl9750_wt_on(host);
+
+	misc_value = sdhci_readl(host, SDHCI_GLI_9750_MISC);
+	misc_value &= ~SDHCI_GLI_9750_MISC_RX_INV;
+	if (b) {
+		misc_value |= FIELD_PREP(SDHCI_GLI_9750_MISC_RX_INV,
+					 GLI_9750_MISC_RX_INV_ON);
+	} else {
+		misc_value |= FIELD_PREP(SDHCI_GLI_9750_MISC_RX_INV,
+					 GLI_9750_MISC_RX_INV_OFF);
+	}
+	sdhci_writel(host, misc_value, SDHCI_GLI_9750_MISC);
+
+	gl9750_wt_off(host);
+}
+
+static int __sdhci_execute_tuning_9750(struct sdhci_host *host, u32 opcode)
+{
+	int i;
+	int rx_inv;
+
+	for (rx_inv = 0; rx_inv < 2; rx_inv++) {
+		gli_set_9750_rx_inv(host, !!rx_inv);
+		sdhci_start_tuning(host);
+
+		for (i = 0; i < GLI_MAX_TUNING_LOOP; i++) {
+			u16 ctrl;
+
+			sdhci_send_tuning(host, opcode);
+
+			if (!host->tuning_done) {
+				sdhci_abort_tuning(host, opcode);
+				break;
+			}
+
+			ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+			if (!(ctrl & SDHCI_CTRL_EXEC_TUNING)) {
+				if (ctrl & SDHCI_CTRL_TUNED_CLK)
+					return 0; /* Success! */
+				break;
+			}
+		}
+	}
+	if (!host->tuning_done) {
+		pr_info("%s: Tuning timeout, falling back to fixed sampling clock\n",
+			mmc_hostname(host->mmc));
+		return -ETIMEDOUT;
+	}
+
+	pr_info("%s: Tuning failed, falling back to fixed sampling clock\n",
+		mmc_hostname(host->mmc));
+	sdhci_reset_tuning(host);
+
+	return -EAGAIN;
+}
+
+static int gl9750_execute_tuning(struct sdhci_host *host, u32 opcode)
+{
+	host->mmc->retune_period = 0;
+	if (host->tuning_mode == SDHCI_TUNING_MODE_1)
+		host->mmc->retune_period = host->tuning_count;
+
+	gli_set_9750(host);
+	host->tuning_err = __sdhci_execute_tuning_9750(host, opcode);
+	sdhci_end_tuning(host);
+
+	return 0;
+}
+
+static int gli_probe_slot_gl9750(struct sdhci_pci_slot *slot)
+{
+	struct sdhci_host *host = slot->host;
+
+	slot->host->mmc->caps2 |= MMC_CAP2_NO_SDIO;
+	sdhci_enable_v4_mode(host);
+
+	return 0;
+}
+
+static int gli_probe_slot_gl9755(struct sdhci_pci_slot *slot)
+{
+	struct sdhci_host *host = slot->host;
+
+	slot->host->mmc->caps2 |= MMC_CAP2_NO_SDIO;
+	sdhci_enable_v4_mode(host);
+
+	return 0;
+}
+
+static void sdhci_gli_voltage_switch(struct sdhci_host *host)
+{
+	/*
+	 * According to Section 3.6.1 signal voltage switch procedure in
+	 * SD Host Controller Simplified Spec. 4.20, steps 6~8 are as
+	 * follows:
+	 * (6) Set 1.8V Signal Enable in the Host Control 2 register.
+	 * (7) Wait 5ms. 1.8V voltage regulator shall be stable within this
+	 *     period.
+	 * (8) If 1.8V Signal Enable is cleared by Host Controller, go to
+	 *     step (12).
+	 *
+	 * Wait 5ms after set 1.8V signal enable in Host Control 2 register
+	 * to ensure 1.8V signal enable bit is set by GL9750/GL9755.
+	 */
+	usleep_range(5000, 5500);
+}
+
+static void sdhci_gl9750_reset(struct sdhci_host *host, u8 mask)
+{
+	sdhci_reset(host, mask);
+	gli_set_9750(host);
+}
+
+static u32 sdhci_gl9750_readl(struct sdhci_host *host, int reg)
+{
+	u32 value;
+
+	value = readl(host->ioaddr + reg);
+	if (unlikely(reg == SDHCI_MAX_CURRENT && !(value & 0xff)))
+		value |= 0xc8;
+
+	return value;
+}
+
+static const struct sdhci_ops sdhci_gl9755_ops = {
+	.set_clock		= sdhci_set_clock,
+	.enable_dma		= sdhci_pci_enable_dma,
+	.set_bus_width		= sdhci_set_bus_width,
+	.reset			= sdhci_reset,
+	.set_uhs_signaling	= sdhci_set_uhs_signaling,
+	.voltage_switch		= sdhci_gli_voltage_switch,
+};
+
+const struct sdhci_pci_fixes sdhci_gl9755 = {
+	.quirks		= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
+	.quirks2	= SDHCI_QUIRK2_BROKEN_DDR50,
+	.probe_slot	= gli_probe_slot_gl9755,
+	.ops            = &sdhci_gl9755_ops,
+};
+
+static const struct sdhci_ops sdhci_gl9750_ops = {
+	.read_l                 = sdhci_gl9750_readl,
+	.set_clock		= sdhci_set_clock,
+	.enable_dma		= sdhci_pci_enable_dma,
+	.set_bus_width		= sdhci_set_bus_width,
+	.reset			= sdhci_gl9750_reset,
+	.set_uhs_signaling	= sdhci_set_uhs_signaling,
+	.voltage_switch		= sdhci_gli_voltage_switch,
+	.platform_execute_tuning = gl9750_execute_tuning,
+};
+
+const struct sdhci_pci_fixes sdhci_gl9750 = {
+	.quirks		= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
+	.quirks2	= SDHCI_QUIRK2_BROKEN_DDR50,
+	.probe_slot	= gli_probe_slot_gl9750,
+	.ops            = &sdhci_gl9750_ops,
+};

drivers/mmc/host/sdhci-pci.h

@@ -68,6 +68,9 @@
 
 #define PCI_DEVICE_ID_SYNOPSYS_DWC_MSHC 0xc202
 
+#define PCI_DEVICE_ID_GLI_9755		0x9755
+#define PCI_DEVICE_ID_GLI_9750		0x9750
+
 /*
  * PCI device class and mask
  */
@@ -188,5 +191,7 @@ int sdhci_pci_enable_dma(struct sdhci_host *host);
 extern const struct sdhci_pci_fixes sdhci_arasan;
 extern const struct sdhci_pci_fixes sdhci_snps;
 extern const struct sdhci_pci_fixes sdhci_o2;
+extern const struct sdhci_pci_fixes sdhci_gl9750;
+extern const struct sdhci_pci_fixes sdhci_gl9755;
 
 #endif /* __SDHCI_PCI_H */

drivers/mmc/host/sdhci-tegra.c

@@ -4,6 +4,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -104,6 +105,7 @@
 
 struct sdhci_tegra_soc_data {
 	const struct sdhci_pltfm_data *pdata;
+	u64 dma_mask;
 	u32 nvquirks;
 	u8 min_tap_delay;
 	u8 max_tap_delay;
@@ -1233,11 +1235,25 @@ static const struct cqhci_host_ops sdhci_tegra_cqhci_ops = {
 	.update_dcmd_desc = sdhci_tegra_update_dcmd_desc,
 };
 
+static int tegra_sdhci_set_dma_mask(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *platform = sdhci_priv(host);
+	struct sdhci_tegra *tegra = sdhci_pltfm_priv(platform);
+	const struct sdhci_tegra_soc_data *soc = tegra->soc_data;
+	struct device *dev = mmc_dev(host->mmc);
+
+	if (soc->dma_mask)
+		return dma_set_mask_and_coherent(dev, soc->dma_mask);
+
+	return 0;
+}
+
 static const struct sdhci_ops tegra_sdhci_ops = {
 	.get_ro     = tegra_sdhci_get_ro,
 	.read_w     = tegra_sdhci_readw,
 	.write_l    = tegra_sdhci_writel,
 	.set_clock  = tegra_sdhci_set_clock,
+	.set_dma_mask = tegra_sdhci_set_dma_mask,
 	.set_bus_width = sdhci_set_bus_width,
 	.reset      = tegra_sdhci_reset,
 	.platform_execute_tuning = tegra_sdhci_execute_tuning,
@@ -1257,6 +1273,7 @@ static const struct sdhci_pltfm_data sdhci_tegra20_pdata = {
 
 static const struct sdhci_tegra_soc_data soc_data_tegra20 = {
 	.pdata = &sdhci_tegra20_pdata,
+	.dma_mask = DMA_BIT_MASK(32),
 	.nvquirks = NVQUIRK_FORCE_SDHCI_SPEC_200 |
 		    NVQUIRK_ENABLE_BLOCK_GAP_DET,
 };
@@ -1283,6 +1300,7 @@ static const struct sdhci_pltfm_data sdhci_tegra30_pdata = {
 
 static const struct sdhci_tegra_soc_data soc_data_tegra30 = {
 	.pdata = &sdhci_tegra30_pdata,
+	.dma_mask = DMA_BIT_MASK(32),
 	.nvquirks = NVQUIRK_ENABLE_SDHCI_SPEC_300 |
 		    NVQUIRK_ENABLE_SDR50 |
 		    NVQUIRK_ENABLE_SDR104 |
@@ -1295,6 +1313,7 @@ static const struct sdhci_ops tegra114_sdhci_ops = {
 	.write_w    = tegra_sdhci_writew,
 	.write_l    = tegra_sdhci_writel,
 	.set_clock  = tegra_sdhci_set_clock,
+	.set_dma_mask = tegra_sdhci_set_dma_mask,
 	.set_bus_width = sdhci_set_bus_width,
 	.reset      = tegra_sdhci_reset,
 	.platform_execute_tuning = tegra_sdhci_execute_tuning,
@@ -1316,6 +1335,7 @@ static const struct sdhci_pltfm_data sdhci_tegra114_pdata = {
 
 static const struct sdhci_tegra_soc_data soc_data_tegra114 = {
 	.pdata = &sdhci_tegra114_pdata,
+	.dma_mask = DMA_BIT_MASK(32),
 };
 
 static const struct sdhci_pltfm_data sdhci_tegra124_pdata = {
@@ -1325,22 +1345,13 @@ static const struct sdhci_pltfm_data sdhci_tegra124_pdata = {
 		  SDHCI_QUIRK_NO_HISPD_BIT |
 		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
 		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
-	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
-		   /*
-		    * The TRM states that the SD/MMC controller found on
-		    * Tegra124 can address 34 bits (the maximum supported by
-		    * the Tegra memory controller), but tests show that DMA
-		    * to or from above 4 GiB doesn't work. This is possibly
-		    * caused by missing programming, though it's not obvious
-		    * what sequence is required. Mark 64-bit DMA broken for
-		    * now to fix this for existing users (e.g. Nyan boards).
-		    */
-		   SDHCI_QUIRK2_BROKEN_64_BIT_DMA,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 	.ops  = &tegra114_sdhci_ops,
 };
 
 static const struct sdhci_tegra_soc_data soc_data_tegra124 = {
 	.pdata = &sdhci_tegra124_pdata,
+	.dma_mask = DMA_BIT_MASK(34),
 };
 
 static const struct sdhci_ops tegra210_sdhci_ops = {
@@ -1349,6 +1360,7 @@ static const struct sdhci_ops tegra210_sdhci_ops = {
 	.write_w    = tegra210_sdhci_writew,
 	.write_l    = tegra_sdhci_writel,
 	.set_clock  = tegra_sdhci_set_clock,
+	.set_dma_mask = tegra_sdhci_set_dma_mask,
 	.set_bus_width = sdhci_set_bus_width,
 	.reset      = tegra_sdhci_reset,
 	.set_uhs_signaling = tegra_sdhci_set_uhs_signaling,
@@ -1369,6 +1381,7 @@ static const struct sdhci_pltfm_data sdhci_tegra210_pdata = {
 
 static const struct sdhci_tegra_soc_data soc_data_tegra210 = {
 	.pdata = &sdhci_tegra210_pdata,
+	.dma_mask = DMA_BIT_MASK(34),
 	.nvquirks = NVQUIRK_NEEDS_PAD_CONTROL |
 		    NVQUIRK_HAS_PADCALIB |
 		    NVQUIRK_DIS_CARD_CLK_CONFIG_TAP |
@@ -1383,6 +1396,7 @@ static const struct sdhci_ops tegra186_sdhci_ops = {
 	.read_w     = tegra_sdhci_readw,
 	.write_l    = tegra_sdhci_writel,
 	.set_clock  = tegra_sdhci_set_clock,
+	.set_dma_mask = tegra_sdhci_set_dma_mask,
 	.set_bus_width = sdhci_set_bus_width,
 	.reset      = tegra_sdhci_reset,
 	.set_uhs_signaling = tegra_sdhci_set_uhs_signaling,
@@ -1398,20 +1412,13 @@ static const struct sdhci_pltfm_data sdhci_tegra186_pdata = {
 		  SDHCI_QUIRK_NO_HISPD_BIT |
 		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
 		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
-	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
-		   /* SDHCI controllers on Tegra186 support 40-bit addressing.
-		    * IOVA addresses are 48-bit wide on Tegra186.
-		    * With 64-bit dma mask used for SDHCI, accesses can
-		    * be broken. Disable 64-bit dma, which would fall back
-		    * to 32-bit dma mask. Ideally 40-bit dma mask would work,
-		    * But it is not supported as of now.
-		    */
-		   SDHCI_QUIRK2_BROKEN_64_BIT_DMA,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 	.ops  = &tegra186_sdhci_ops,
 };
 
 static const struct sdhci_tegra_soc_data soc_data_tegra186 = {
 	.pdata = &sdhci_tegra186_pdata,
+	.dma_mask = DMA_BIT_MASK(40),
 	.nvquirks = NVQUIRK_NEEDS_PAD_CONTROL |
 		    NVQUIRK_HAS_PADCALIB |
 		    NVQUIRK_DIS_CARD_CLK_CONFIG_TAP |
@@ -1424,6 +1431,7 @@ static const struct sdhci_tegra_soc_data soc_data_tegra186 = {
 
 static const struct sdhci_tegra_soc_data soc_data_tegra194 = {
 	.pdata = &sdhci_tegra186_pdata,
+	.dma_mask = DMA_BIT_MASK(39),
 	.nvquirks = NVQUIRK_NEEDS_PAD_CONTROL |
 		    NVQUIRK_HAS_PADCALIB |
 		    NVQUIRK_DIS_CARD_CLK_CONFIG_TAP |

drivers/mmc/host/sdhci.c

@@ -2874,6 +2874,7 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *intmask_p)
 static void sdhci_adma_show_error(struct sdhci_host *host)
 {
 	void *desc = host->adma_table;
+	dma_addr_t dma = host->adma_addr;
 
 	sdhci_dumpregs(host);
 
@@ -2881,18 +2882,21 @@ static void sdhci_adma_show_error(struct sdhci_host *host)
 		struct sdhci_adma2_64_desc *dma_desc = desc;
 
 		if (host->flags & SDHCI_USE_64_BIT_DMA)
-			DBG("%p: DMA 0x%08x%08x, LEN 0x%04x, Attr=0x%02x\n",
-			    desc, le32_to_cpu(dma_desc->addr_hi),
+			SDHCI_DUMP("%08llx: DMA 0x%08x%08x, LEN 0x%04x, Attr=0x%02x\n",
+			    (unsigned long long)dma,
+			    le32_to_cpu(dma_desc->addr_hi),
 			    le32_to_cpu(dma_desc->addr_lo),
 			    le16_to_cpu(dma_desc->len),
 			    le16_to_cpu(dma_desc->cmd));
 		else
-			DBG("%p: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
-			    desc, le32_to_cpu(dma_desc->addr_lo),
+			SDHCI_DUMP("%08llx: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
+			    (unsigned long long)dma,
+			    le32_to_cpu(dma_desc->addr_lo),
 			    le16_to_cpu(dma_desc->len),
 			    le16_to_cpu(dma_desc->cmd));
 
 		desc += host->desc_sz;
+		dma += host->desc_sz;
 
 		if (dma_desc->cmd & cpu_to_le16(ADMA2_END))
 			break;
@@ -2968,7 +2972,8 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 			!= MMC_BUS_TEST_R)
 		host->data->error = -EILSEQ;
 	else if (intmask & SDHCI_INT_ADMA_ERROR) {
-		pr_err("%s: ADMA error\n", mmc_hostname(host->mmc));
+		pr_err("%s: ADMA error: 0x%08x\n", mmc_hostname(host->mmc),
+		       intmask);
 		sdhci_adma_show_error(host);
 		host->data->error = -EIO;
 		if (host->ops->adma_workaround)
@@ -3776,17 +3781,13 @@ int sdhci_setup_host(struct sdhci_host *host)
 		host->flags &= ~SDHCI_USE_ADMA;
 	}
 
-	/*
-	 * It is assumed that a 64-bit capable device has set a 64-bit DMA mask
-	 * and *must* do 64-bit DMA.  A driver has the opportunity to change
-	 * that during the first call to ->enable_dma().  Similarly
-	 * SDHCI_QUIRK2_BROKEN_64_BIT_DMA must be left to the drivers to
-	 * implement.
-	 */
 	if (sdhci_can_64bit_dma(host))
 		host->flags |= SDHCI_USE_64_BIT_DMA;
 
 	if (host->flags & (SDHCI_USE_SDMA | SDHCI_USE_ADMA)) {
+		if (host->ops->set_dma_mask)
+			ret = host->ops->set_dma_mask(host);
+		else
 			ret = sdhci_set_dma_mask(host);
 
 		if (!ret && host->ops->enable_dma)

drivers/mmc/host/sdhci.h

@@ -622,6 +622,7 @@ struct sdhci_ops {
 
 	u32		(*irq)(struct sdhci_host *host, u32 intmask);
 
+	int		(*set_dma_mask)(struct sdhci_host *host);
 	int		(*enable_dma)(struct sdhci_host *host);
 	unsigned int	(*get_max_clock)(struct sdhci_host *host);
 	unsigned int	(*get_min_clock)(struct sdhci_host *host);