diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index cd2c3d6d40e0..993fd31394c8 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -319,6 +319,7 @@ int acpi_device_fix_up_power(struct acpi_device *device)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(acpi_device_fix_up_power);
 
 int acpi_device_update_power(struct acpi_device *device, int *state_p)
 {
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index ddc96206288a..e62fde3ac431 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -618,6 +618,10 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
 
 	ioc_err = __mmc_blk_ioctl_cmd(card, md, idata);
 
+	/* Always switch back to main area after RPMB access */
+	if (md->area_type & MMC_BLK_DATA_AREA_RPMB)
+		mmc_blk_part_switch(card, dev_get_drvdata(&card->dev));
+
 	mmc_put_card(card);
 
 	err = mmc_blk_ioctl_copy_to_user(ic_ptr, idata);
@@ -685,6 +689,10 @@ static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev,
 	for (i = 0; i < num_of_cmds && !ioc_err; i++)
 		ioc_err = __mmc_blk_ioctl_cmd(card, md, idata[i]);
 
+	/* Always switch back to main area after RPMB access */
+	if (md->area_type & MMC_BLK_DATA_AREA_RPMB)
+		mmc_blk_part_switch(card, dev_get_drvdata(&card->dev));
+
 	mmc_put_card(card);
 
 	/* copy to user if data and response */
@@ -748,16 +756,25 @@ static inline int mmc_blk_part_switch(struct mmc_card *card,
 	if (mmc_card_mmc(card)) {
 		u8 part_config = card->ext_csd.part_config;
 
+		if (md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
+			mmc_retune_pause(card->host);
+
 		part_config &= ~EXT_CSD_PART_CONFIG_ACC_MASK;
 		part_config |= md->part_type;
 
 		ret = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				 EXT_CSD_PART_CONFIG, part_config,
 				 card->ext_csd.part_time);
-		if (ret)
+		if (ret) {
+			if (md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
+				mmc_retune_unpause(card->host);
 			return ret;
+		}
 
 		card->ext_csd.part_config = part_config;
+
+		if (main_md->part_curr == EXT_CSD_PART_CONFIG_ACC_RPMB)
+			mmc_retune_unpause(card->host);
 	}
 
 	main_md->part_curr = md->part_type;
@@ -2519,11 +2536,12 @@ static const struct mmc_fixup blk_fixups[] =
 		  MMC_QUIRK_BLK_NO_CMD23),
 
 	/*
-	 * Some Micron MMC cards needs longer data read timeout than
-	 * indicated in CSD.
+	 * Some MMC cards need longer data read timeout than indicated in CSD.
 	 */
 	MMC_FIXUP(CID_NAME_ANY, CID_MANFID_MICRON, 0x200, add_quirk_mmc,
 		  MMC_QUIRK_LONG_READ_TIME),
+	MMC_FIXUP("008GE0", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_LONG_READ_TIME),
 
 	/*
 	 * On these Samsung MoviNAND parts, performing secure erase or
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 99275e40bf2f..8b4dfd45433b 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -875,11 +875,11 @@ void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card)
 	/*
 	 * Some cards require longer data read timeout than indicated in CSD.
 	 * Address this by setting the read timeout to a "reasonably high"
-	 * value. For the cards tested, 300ms has proven enough. If necessary,
+	 * value. For the cards tested, 600ms has proven enough. If necessary,
 	 * this value can be increased if other problematic cards require this.
 	 */
 	if (mmc_card_long_read_time(card) && data->flags & MMC_DATA_READ) {
-		data->timeout_ns = 300000000;
+		data->timeout_ns = 600000000;
 		data->timeout_clks = 0;
 	}
 
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index e0a3ee16c0d3..1be42fab1a30 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -68,8 +68,32 @@ void mmc_retune_enable(struct mmc_host *host)
 			  jiffies + host->retune_period * HZ);
 }
 
+/*
+ * Pause re-tuning for a small set of operations.  The pause begins after the
+ * next command and after first doing re-tuning.
+ */
+void mmc_retune_pause(struct mmc_host *host)
+{
+	if (!host->retune_paused) {
+		host->retune_paused = 1;
+		mmc_retune_needed(host);
+		mmc_retune_hold(host);
+	}
+}
+EXPORT_SYMBOL(mmc_retune_pause);
+
+void mmc_retune_unpause(struct mmc_host *host)
+{
+	if (host->retune_paused) {
+		host->retune_paused = 0;
+		mmc_retune_release(host);
+	}
+}
+EXPORT_SYMBOL(mmc_retune_unpause);
+
 void mmc_retune_disable(struct mmc_host *host)
 {
+	mmc_retune_unpause(host);
 	host->can_retune = 0;
 	del_timer_sync(&host->retune_timer);
 	host->retune_now = 0;
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index 8c20b81cafd8..358b0dc853b0 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -66,6 +66,70 @@ static void dw_mci_rk3288_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 	/* Make sure we use phases which we can enumerate with */
 	if (!IS_ERR(priv->sample_clk))
 		clk_set_phase(priv->sample_clk, priv->default_sample_phase);
+
+	/*
+	 * Set the drive phase offset based on speed mode to achieve hold times.
+	 *
+	 * NOTE: this is _not_ a value that is dynamically tuned and is also
+	 * _not_ a value that will vary from board to board.  It is a value
+	 * that could vary between different SoC models if they had massively
+	 * different output clock delays inside their dw_mmc IP block (delay_o),
+	 * but since it's OK to overshoot a little we don't need to do complex
+	 * calculations and can pick values that will just work for everyone.
+	 *
+	 * When picking values we'll stick with picking 0/90/180/270 since
+	 * those can be made very accurately on all known Rockchip SoCs.
+	 *
+	 * Note that these values match values from the DesignWare Databook
+	 * tables for the most part except for SDR12 and "ID mode".  For those
+	 * two modes the databook calculations assume a clock in of 50MHz.  As
+	 * seen above, we always use a clock in rate that is exactly the
+	 * card's input clock (times RK3288_CLKGEN_DIV, but that gets divided
+	 * back out before the controller sees it).
+	 *
+	 * From measurement of a single device, it appears that delay_o is
+	 * about .5 ns.  Since we try to leave a bit of margin, it's expected
+	 * that numbers here will be fine even with much larger delay_o
+	 * (the 1.4 ns assumed by the DesignWare Databook would result in the
+	 * same results, for instance).
+	 */
+	if (!IS_ERR(priv->drv_clk)) {
+		int phase;
+
+		/*
+		 * In almost all cases a 90 degree phase offset will provide
+		 * sufficient hold times across all valid input clock rates
+		 * assuming delay_o is not absurd for a given SoC.  We'll use
+		 * that as a default.
+		 */
+		phase = 90;
+
+		switch (ios->timing) {
+		case MMC_TIMING_MMC_DDR52:
+			/*
+			 * Since clock in rate with MMC_DDR52 is doubled when
+			 * bus width is 8 we need to double the phase offset
+			 * to get the same timings.
+			 */
+			if (ios->bus_width == MMC_BUS_WIDTH_8)
+				phase = 180;
+			break;
+		case MMC_TIMING_UHS_SDR104:
+		case MMC_TIMING_MMC_HS200:
+			/*
+			 * In the case of 150 MHz clock (typical max for
+			 * Rockchip SoCs), 90 degree offset will add a delay
+			 * of 1.67 ns.  That will meet min hold time of .8 ns
+			 * as long as clock output delay is < .87 ns.  On
+			 * SoCs measured this seems to be OK, but it doesn't
+			 * hurt to give margin here, so we use 180.
+			 */
+			phase = 180;
+			break;
+		}
+
+		clk_set_phase(priv->drv_clk, phase);
+	}
 }
 
 #define NUM_PHASES			360
@@ -233,10 +297,10 @@ static int dw_mci_rockchip_init(struct dw_mci *host)
 
 /* Common capabilities of RK3288 SoC */
 static unsigned long dw_mci_rk3288_dwmmc_caps[4] = {
-	MMC_CAP_ERASE,
-	MMC_CAP_ERASE,
-	MMC_CAP_ERASE,
-	MMC_CAP_ERASE,
+	MMC_CAP_ERASE | MMC_CAP_CMD23,
+	MMC_CAP_ERASE | MMC_CAP_CMD23,
+	MMC_CAP_ERASE | MMC_CAP_CMD23,
+	MMC_CAP_ERASE | MMC_CAP_CMD23,
 };
 
 static const struct dw_mci_drv_data rk2928_drv_data = {
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 9dd1bd358434..829a6eebcdce 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -2595,13 +2595,13 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	/* Useful defaults if platform data is unset. */
 	if (host->use_dma == TRANS_MODE_IDMAC) {
 		mmc->max_segs = host->ring_size;
-		mmc->max_blk_size = 65536;
+		mmc->max_blk_size = 65535;
 		mmc->max_seg_size = 0x1000;
 		mmc->max_req_size = mmc->max_seg_size * host->ring_size;
 		mmc->max_blk_count = mmc->max_req_size / 512;
 	} else if (host->use_dma == TRANS_MODE_EDMAC) {
 		mmc->max_segs = 64;
-		mmc->max_blk_size = 65536;
+		mmc->max_blk_size = 65535;
 		mmc->max_blk_count = 65535;
 		mmc->max_req_size =
 				mmc->max_blk_size * mmc->max_blk_count;
@@ -2609,7 +2609,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	} else {
 		/* TRANS_MODE_PIO */
 		mmc->max_segs = 64;
-		mmc->max_blk_size = 65536; /* BLKSIZ is 16 bits */
+		mmc->max_blk_size = 65535; /* BLKSIZ is 16 bits */
 		mmc->max_blk_count = 512;
 		mmc->max_req_size = mmc->max_blk_size *
 				    mmc->max_blk_count;
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index b2d70ba6caa7..458ffb7637e5 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -274,7 +274,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_emmc = {
 	.chip    = &sdhci_acpi_chip_int,
 	.caps    = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
 		   MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
-		   MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+		   MMC_CAP_WAIT_WHILE_BUSY,
 	.caps2   = MMC_CAP2_HC_ERASE_SZ,
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
 	.quirks  = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
@@ -289,7 +289,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sdio = {
 		   SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2 = SDHCI_QUIRK2_HOST_OFF_CARD_ON,
 	.caps    = MMC_CAP_NONREMOVABLE | MMC_CAP_POWER_OFF_CARD |
-		   MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+		   MMC_CAP_WAIT_WHILE_BUSY,
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
 	.pm_caps = MMC_PM_KEEP_POWER,
 	.probe_slot	= sdhci_acpi_sdio_probe_slot,
@@ -301,7 +301,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sd = {
 	.quirks  = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2 = SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON |
 		   SDHCI_QUIRK2_STOP_WITH_TC,
-	.caps    = MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+	.caps    = MMC_CAP_WAIT_WHILE_BUSY,
 	.probe_slot	= sdhci_acpi_sd_probe_slot,
 };
 
@@ -378,7 +378,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	acpi_handle handle = ACPI_HANDLE(dev);
-	struct acpi_device *device;
+	struct acpi_device *device, *child;
 	struct sdhci_acpi_host *c;
 	struct sdhci_host *host;
 	struct resource *iomem;
@@ -390,6 +390,11 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	if (acpi_bus_get_device(handle, &device))
 		return -ENODEV;
 
+	/* Power on the SDHCI controller and its children */
+	acpi_device_fix_up_power(device);
+	list_for_each_entry(child, &device->children, node)
+		acpi_device_fix_up_power(child);
+
 	if (acpi_bus_get_status(device) || !device->status.present)
 		return -ENODEV;
 
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 97d4eebd6bf5..a4dbf7421edc 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -356,7 +356,6 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
 				 MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
-				 MMC_CAP_BUS_WIDTH_TEST |
 				 MMC_CAP_WAIT_WHILE_BUSY;
 	slot->host->mmc->caps2 |= MMC_CAP2_HC_ERASE_SZ;
 	slot->hw_reset = sdhci_pci_int_hw_reset;
@@ -372,15 +371,13 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_NONREMOVABLE |
-				 MMC_CAP_BUS_WIDTH_TEST |
 				 MMC_CAP_WAIT_WHILE_BUSY;
 	return 0;
 }
 
 static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
 {
-	slot->host->mmc->caps |= MMC_CAP_BUS_WIDTH_TEST |
-				 MMC_CAP_WAIT_WHILE_BUSY;
+	slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
 	slot->cd_con_id = NULL;
 	slot->cd_idx = 0;
 	slot->cd_override_level = true;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 85800b48241f..45cde8cd39f2 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -329,6 +329,7 @@ struct mmc_host {
 	unsigned int		can_retune:1;	/* re-tuning can be used */
 	unsigned int		doing_retune:1;	/* re-tuning in progress */
 	unsigned int		retune_now:1;	/* do re-tuning at next req */
+	unsigned int		retune_paused:1; /* re-tuning is temporarily disabled */
 
 	int			rescan_disable;	/* disable card detection */
 	int			rescan_entered;	/* used with nonremovable devices */
@@ -526,4 +527,7 @@ static inline void mmc_retune_recheck(struct mmc_host *host)
 		host->retune_now = 1;
 }
 
+void mmc_retune_pause(struct mmc_host *host);
+void mmc_retune_unpause(struct mmc_host *host);
+
 #endif /* LINUX_MMC_HOST_H */