Skip to contentSkip to conversation

Prepare sdhci-omap to support more SoCs

PATCH In review Tony Lindgren 2 participants 10 messages Sep 21, 2021 – Sep 24, 2021

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

cover Prepare sdhci-omap to support more SoCs

Hi,

Here are changes to prepare to add support for more SoCs to start deprecating the old omap_hsmmc driver. I'll send another series of changes to add support for more SoCs.

Regards,

Tony

Tony Lindgren (5):
mmc: sdhci-omap: Fix NULL pointer exception if regulator is not
configured
mmc: sdhci-omap: Fix context restore
mmc: sdhci-omap: Restore sysconfig after reset
mmc: sdhci-omap: Parse legacy ti,non-removable property
mmc: sdhci-omap: Check MMCHS_HL_HWINFO register for ADMA

 drivers/mmc/host/sdhci-omap.c | 61 ++++++++++++++++++++++++++++++++---
 1 file changed, 56 insertions(+), 5 deletions(-)
Signature · 1 line
2.33.0
#1 lore raw

PATCH 1/5 mmc: sdhci-omap: Fix NULL pointer exception if regulator is not configured

If sdhci-omap is configured for an unused device instance and the device is not set as disabled, we can get a NULL pointer dereference:

Unable to handle kernel NULL pointer dereference at virtual address

00000045
...
(regulator_set_voltage) from [<c07d7008>] (mmc_regulator_set_ocr+0x44/0xd0) (mmc_regulator_set_ocr) from [<c07e2d80>] (sdhci_set_ios+0xa4/0x490) (sdhci_set_ios) from [<c07ea690>] (sdhci_omap_set_ios+0x124/0x160) (sdhci_omap_set_ios) from [<c07c8e94>] (mmc_power_up.part.0+0x3c/0x154) (mmc_power_up.part.0) from [<c07c9d20>] (mmc_start_host+0x88/0x9c) (mmc_start_host) from [<c07cad34>] (mmc_add_host+0x58/0x7c) (mmc_add_host) from [<c07e2574>] (__sdhci_add_host+0xf0/0x22c) (__sdhci_add_host) from [<c07eaf68>] (sdhci_omap_probe+0x318/0x72c) (sdhci_omap_probe) from [<c06a39d8>] (platform_probe+0x58/0xb8)

AFAIK we are not seeing this with the devices configured in the mainline kernel but this can cause issues for folks bringing up their boards.

Fixes 7d326930d352 ("mmc: sdhci-omap: Add OMAP SDHCI driver")
---
 drivers/mmc/host/sdhci-omap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/mmc/host/sdhci-omap.c +2 -1
@@ -682,7 +682,8 @@ static void sdhci_omap_set_power(struct sdhci_host *host, unsigned char mode,
 {
 	struct mmc_host *mmc = host->mmc;
 
-	mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
+	if (!IS_ERR(mmc->supply.vmmc))
+		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
 }
 
 static int sdhci_omap_enable_dma(struct sdhci_host *host)
Signature · 1 line
2.33.0
#2 lore raw

PATCH 2/5 mmc: sdhci-omap: Fix context restore

In reply to Tony Lindgren

We need to restore context in a specified order with HCTL set in two phases. This is similar to what omap_hsmmc_context_restore() is doing. Otherwise SDIO can stop working on resume.

And for PM runtime and SDIO cards, we need to also save SYSCTL, IE and ISE.

This should not be a problem currently, and these patches can be applied whenever suitable.

Fixes ee0f309263a6 ("mmc: sdhci-omap: Add Support for Suspend/Resume")
---
 drivers/mmc/host/sdhci-omap.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)
drivers/mmc/host/sdhci-omap.c +14 -1
@@ -62,6 +62,8 @@
 #define SDHCI_OMAP_IE		0x234
 #define INT_CC_EN		BIT(0)
 
+#define SDHCI_OMAP_ISE		0x238
+
 #define SDHCI_OMAP_AC12		0x23c
 #define AC12_V1V8_SIGEN		BIT(19)
 #define AC12_SCLK_SEL		BIT(23)
@@ -113,6 +115,8 @@ struct sdhci_omap_host {
 	u32			hctl;
 	u32			sysctl;
 	u32			capa;
+	u32			ie;
+	u32			ise;
 };
 
 static void sdhci_omap_start_clock(struct sdhci_omap_host *omap_host);
@@ -1245,14 +1249,23 @@ static void sdhci_omap_context_save(struct sdhci_omap_host *omap_host)
 {
 	omap_host->con = sdhci_omap_readl(omap_host, SDHCI_OMAP_CON);
 	omap_host->hctl = sdhci_omap_readl(omap_host, SDHCI_OMAP_HCTL);
+	omap_host->sysctl = sdhci_omap_readl(omap_host, SDHCI_OMAP_SYSCTL);
 	omap_host->capa = sdhci_omap_readl(omap_host, SDHCI_OMAP_CAPA);
+	omap_host->ie = sdhci_omap_readl(omap_host, SDHCI_OMAP_IE);
+	omap_host->ise = sdhci_omap_readl(omap_host, SDHCI_OMAP_ISE);
 }
 
+/* Order matters here, HCTL must be restored in two phases */
 static void sdhci_omap_context_restore(struct sdhci_omap_host *omap_host)
 {
-	sdhci_omap_writel(omap_host, SDHCI_OMAP_CON, omap_host->con);
 	sdhci_omap_writel(omap_host, SDHCI_OMAP_HCTL, omap_host->hctl);
 	sdhci_omap_writel(omap_host, SDHCI_OMAP_CAPA, omap_host->capa);
+	sdhci_omap_writel(omap_host, SDHCI_OMAP_HCTL, omap_host->hctl);
+
+	sdhci_omap_writel(omap_host, SDHCI_OMAP_SYSCTL, omap_host->sysctl);
+	sdhci_omap_writel(omap_host, SDHCI_OMAP_CON, omap_host->con);
+	sdhci_omap_writel(omap_host, SDHCI_OMAP_IE, omap_host->ie);
+	sdhci_omap_writel(omap_host, SDHCI_OMAP_ISE, omap_host->ise);
 }
 
 static int __maybe_unused sdhci_omap_suspend(struct device *dev)
Signature · 1 line
2.33.0
#3 lore raw

PATCH 3/5 mmc: sdhci-omap: Restore sysconfig after reset

In reply to Tony Lindgren

The sysconfig register is managed in a generic way by PM runtime for us by the interconnect target module layer code. SDHCI_RESET_ALL also resets the target module configuration, so we need to restore sysconfig after reset.

Note that there is no need to save and restore sysconfig during PM runtime, the PM runtime layer will do that for us.

Not sure if this issue is a problem with the current configurations, I noticed the issue while adding support for older TI SoCs and testing with wlcore SDIO wlan device.

---
 drivers/mmc/host/sdhci-omap.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)
drivers/mmc/host/sdhci-omap.c +13 -1
@@ -21,6 +21,8 @@
 
 #include "sdhci-pltfm.h"
 
+#define SDHCI_OMAP_SYSCONFIG	0x110
+
 #define SDHCI_OMAP_CON		0x12c
 #define CON_DW8			BIT(5)
 #define CON_DMA_MASTER		BIT(20)
@@ -797,6 +799,11 @@ static void sdhci_omap_reset(struct sdhci_host *host, u8 mask)
 	struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host);
 	unsigned long limit = MMC_TIMEOUT_US;
 	unsigned long i = 0;
+	u32 sysc;
+
+	/* Save target module sysconfig configured by SoC PM layer */
+	if (mask & SDHCI_RESET_ALL)
+		sysc = sdhci_omap_readl(omap_host, SDHCI_OMAP_SYSCONFIG);
 
 	/* Don't reset data lines during tuning operation */
 	if (omap_host->is_tuning)
@@ -816,10 +823,15 @@ static void sdhci_omap_reset(struct sdhci_host *host, u8 mask)
 			dev_err(mmc_dev(host->mmc),
 				"Timeout waiting on controller reset in %s\n",
 				__func__);
-		return;
+
+		goto restore_sysc;
 	}
 
 	sdhci_reset(host, mask);
+
+restore_sysc:
+	if (mask & SDHCI_RESET_ALL)
+		sdhci_omap_writel(omap_host, SDHCI_OMAP_SYSCONFIG, sysc);
 }
 
 #define CMD_ERR_MASK (SDHCI_INT_CRC | SDHCI_INT_END_BIT | SDHCI_INT_INDEX |\
Signature · 1 line
2.33.0
#4 lore raw

PATCH 4/5 mmc: sdhci-omap: Parse legacy ti,non-removable property

In reply to Tony Lindgren

We need to support the legacy ti,non-removable property too. Let's warn about the legacy property and mark the device as non-removable.

Naturally all the mainline kernel devicetree files will get updated to use the standard non-removable property with the sdhci-omap conversion. But we also have folks updating their kernels with custom devicetree files that we need to consider.

---
 drivers/mmc/host/sdhci-omap.c | 5 +++++
 1 file changed, 5 insertions(+)
drivers/mmc/host/sdhci-omap.c +5 -0
@@ -1213,6 +1213,11 @@ static int sdhci_omap_probe(struct platform_device *pdev)
 	if (of_find_property(dev->of_node, "dmas", NULL))
 		sdhci_switch_external_dma(host, true);
 
+	if (device_property_read_bool(dev, "ti,non-removable")) {
+		dev_warn_once(dev, "using old ti,non-removable property\n");
+		mmc->caps |= MMC_CAP_NONREMOVABLE;
+	}
+
 	/* R1B responses is required to properly manage HW busy detection. */
 	mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
 
Signature · 1 line
2.33.0
#5 lore raw

Re: [PATCH 4/5] mmc: sdhci-omap: Parse legacy ti,non-removable property

Quoted 18 lines · Tony Lindgren

We need to support the legacy ti,non-removable property too. Let's warn about the legacy property and mark the device as non-removable.

Naturally all the mainline kernel devicetree files will get updated to use the standard non-removable property with the sdhci-omap conversion. But we also have folks updating their kernels with custom devicetree files that we need to consider.

---
 drivers/mmc/host/sdhci-omap.c | 5 +++++
 1 file changed, 5 insertions(+)

drivers/mmc/host/sdhci-omap.c static int sdhci_omap_probe(struct platform_device *pdev) · line 1217

Quoted 5 lines
drivers/mmc/host/sdhci-omap.c +2 -0
@@ -1213,6 +1213,11 @@ static int sdhci_omap_probe(struct platform_device *pdev)
        if (of_find_property(dev->of_node, "dmas", NULL))
                sdhci_switch_external_dma(host, true);
 
+       if (device_property_read_bool(dev, "ti,non-removable")) {
+               dev_warn_once(dev, "using old ti,non-removable property\n");

Perhaps we should document this property for sdhci-omap and thus also set it as deprecated. What do you think?

Quoted 8 lines
drivers/mmc/host/sdhci-omap.c +3 -1
+               mmc->caps |= MMC_CAP_NONREMOVABLE;
+       }
+
        /* R1B responses is required to properly manage HW busy detection. */
        mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
 
--

2.33.0

Kind regards
Uffe

#6 lore raw

Re: [PATCH 4/5] mmc: sdhci-omap: Parse legacy ti,non-removable property

Quoted 7 lines · Ulf Hansson
Quoted 6 lines · Tony Lindgren
drivers/mmc/host/sdhci-omap.c +0 -0
@@ -1213,6 +1213,11 @@ static int sdhci_omap_probe(struct platform_device *pdev)
        if (of_find_property(dev->of_node, "dmas", NULL))
                sdhci_switch_external_dma(host, true);
 
Quoted 5 lines

drivers/mmc/host/sdhci-omap.c static int sdhci_omap_probe(struct platform_device *pdev) · line 1217

Quoted 2 lines
drivers/mmc/host/sdhci-omap.c +2 -0
+       if (device_property_read_bool(dev, "ti,non-removable")) {
+               dev_warn_once(dev, "using old ti,non-removable property\n");

Perhaps we should document this property for sdhci-omap and thus also set it as deprecated. What do you think?

Yes good idea, I'll send a patch for that.

Regards,

Tony

#7 lore raw

PATCH 5/5 mmc: sdhci-omap: Check MMCHS_HL_HWINFO register for ADMA

In reply to Tony Lindgren

ADMA is only available on controller instances that are connected to the L3 interconnect and are bus mastering capable.

As the MMCHS_HL_HWINFO is in the module registers before omap registers and sdhci registers, and the omap registers and sdhci registers can be at different offsets depending on the SoC, let's read MMCHS_HL_HWINFO directly.

Let's also switch to using device_property_present() while at it.

---
 drivers/mmc/host/sdhci-omap.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)
drivers/mmc/host/sdhci-omap.c +22 -2
@@ -692,6 +692,22 @@ static void sdhci_omap_set_power(struct sdhci_host *host, unsigned char mode,
 		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
 }
 
+/*
+ * MMCHS_HL_HWINFO has the MADMA_EN bit set if the controller instance
+ * is connected to L3 interconnect and is bus master capable. Note that
+ * the MMCHS_HL_HWINFO register is in the module registers before the
+ * omap registers and sdhci registers. The offset can vary for omap
+ * registers depending on the SoC. Do not use sdhci_omap_readl() here.
+ */
+static bool sdhci_omap_has_adma(struct sdhci_omap_host *omap_host, int offset)
+{
+	/* MMCHS_HL_HWINFO register is only available on omap4 and later */
+	if (offset < 0x200)
+		return false;
+
+	return readl(omap_host->base + 4) & 1;
+}
+
 static int sdhci_omap_enable_dma(struct sdhci_host *host)
 {
 	u32 reg;
@@ -1209,8 +1225,12 @@ static int sdhci_omap_probe(struct platform_device *pdev)
 	host->mmc_host_ops.execute_tuning = sdhci_omap_execute_tuning;
 	host->mmc_host_ops.enable_sdio_irq = sdhci_omap_enable_sdio_irq;
 
-	/* Switch to external DMA only if there is the "dmas" property */
-	if (of_find_property(dev->of_node, "dmas", NULL))
+	/*
+	 * Switch to external DMA only if there is the "dmas" property and
+	 * ADMA is not available on the controller instance.
+	 */
+	if (device_property_present(dev, "dmas") &&
+	    !sdhci_omap_has_adma(omap_host, offset))
 		sdhci_switch_external_dma(host, true);
 
 	if (device_property_read_bool(dev, "ti,non-removable")) {
Signature · 1 line
2.33.0
#8 lore raw
In reply to Tony Lindgren
Quoted 20 lines · Tony Lindgren

Hi,

Here are changes to prepare to add support for more SoCs to start deprecating the old omap_hsmmc driver. I'll send another series of changes to add support for more SoCs.

Regards,

Tony

Tony Lindgren (5):
mmc: sdhci-omap: Fix NULL pointer exception if regulator is not
configured
mmc: sdhci-omap: Fix context restore
mmc: sdhci-omap: Restore sysconfig after reset
mmc: sdhci-omap: Parse legacy ti,non-removable property
mmc: sdhci-omap: Check MMCHS_HL_HWINFO register for ADMA

Quoted 5 lines
 drivers/mmc/host/sdhci-omap.c | 61 ++++++++++++++++++++++++++++++++---
 1 file changed, 56 insertions(+), 5 deletions(-)

--
2.33.0

Applied for next, thanks!

Please tell me, if there are any of these changes that you think deserves to be tagged for stable kernels.

Kind regards
Uffe

#9 lore raw
Quoted 1 line · Ulf Hansson

Applied for next, thanks!

Thanks!

Quoted 2 lines

Please tell me, if there are any of these changes that you think deserves to be tagged for stable kernels.

As the issues have not been seen so far with mainline kernels, I think the fixes tags will be enough and no stable tags are needed.

Regaqrds,

Tony