Merge tag 'mmc-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc

Pull MMC updates from Ulf Hansson:
 "MMC core:
   - Don't force a retune before eMMC RPMB switch
   - Add optional HS400 tuning in HS400es initialization
   - Add a sysfs node to for write-protect-group-size
   - Add re-tuning test to the mmc-test module
   - Use mrq.sbc to support close-ended ioctl requests

  MMC host:
   - mmci: Add support for SDIO in-band irqs for the stm32 variant
   - mmc_spi: Remove broken support custom DMA mapped buffers
   - mtk-sd: Improve and extend the support for tunings
   - renesas_sdhi: Document support for the RZ/Five variant
   - sdhci_am654: Drop support for the ti,otap-del-sel DT property
   - sdhci-brcmstb: Add support for the brcm 74165b0 variant
   - sdhci-msm: Add compatibles for IPQ4019 and IPQ8074
   - sdhci-of-dwcmshc: Add support for the T-Head TH1520 variant
   - sdhci-xenon: Add support for the Marvell ac5 variant"

* tag 'mmc-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc: (27 commits)
  mmc: xenon: Add ac5 support via bounce buffer
  dt-bindings: mmc: add Marvell ac5
  mmc: sdhci-brcmstb: add new sdhci reset sequence for brcm 74165b0
  dt-bindings: mmc: brcm,sdhci-brcmstb: Add support for 74165b0
  mmc: core: Do not force a retune before RPMB switch
  mmc: core: Add HS400 tuning in HS400es initialization
  mmc: sdhci_omap: Fix TI SoC dependencies
  mmc: sdhci_am654: Fix TI SoC dependencies
  mmc: core: Add wp_grp_size sysfs node
  mmc: mmc_test: Add re-tuning test
  mmc: mmc_spi: remove custom DMA mapped buffers
  dt-bindings: mmc: sdhci-msm: document dedicated IPQ4019 and IPQ8074
  dt-bindings: mmc: synopsys-dw-mshc: add iommus for Intel SocFPGA
  mmc: mtk-sd: Extend number of tuning steps
  dt-bindings: mmc: mtk-sd: add tuning steps related property
  mmc: sdhci-omap: don't misuse kernel-doc marker
  mmc: mtk-sd: Increase the verbosity of msdc_track_cmd_data
  mmc: core: Use mrq.sbc in close-ended ffu
  mmc: sdhci_am654: Drop lookup for deprecated ti,otap-del-sel
  mmc: sdhci-of-dwcmshc: Use logical OR instead of bitwise OR in dwcmshc_probe()
  ...

Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml

@@ -226,8 +226,8 @@ examples:
           interrupt-parent = <&gic>;
           interrupts = <0 48 4>;
           reg = <0xff160000 0x1000>;
-          clocks = <&clk200>, <&clk200>;
-          clock-names = "clk_xin", "clk_ahb";
+          clocks = <&clk200>, <&clk200>, <&clk1200>;
+          clock-names = "clk_xin", "clk_ahb", "gate";
           clock-output-names = "clk_out_sd0", "clk_in_sd0";
           #clock-cells = <1>;
           clk-phase-sd-hs = <63>, <72>;
@@ -239,8 +239,8 @@ examples:
           interrupt-parent = <&gic>;
           interrupts = <0 126 4>;
           reg = <0xf1040000 0x10000>;
-          clocks = <&clk200>, <&clk200>;
-          clock-names = "clk_xin", "clk_ahb";
+          clocks = <&clk200>, <&clk200>, <&clk1200>;
+          clock-names = "clk_xin", "clk_ahb", "gate";
           clock-output-names = "clk_out_sd0", "clk_in_sd0";
           #clock-cells = <1>;
           clk-phase-sd-hs = <132>, <60>;

Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml

@@ -20,10 +20,8 @@ properties:
           - const: brcm,sdhci-brcmstb
       - items:
           - enum:
+              - brcm,bcm74165b0-sdhci
               - brcm,bcm7445-sdhci
-          - const: brcm,sdhci-brcmstb
-      - items:
-          - enum:
               - brcm,bcm7425-sdhci
           - const: brcm,sdhci-brcmstb
 

Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml

@@ -27,7 +27,9 @@ properties:
           - marvell,armada-ap806-sdhci
 
       - items:
-          - const: marvell,armada-ap807-sdhci
+          - enum:
+              - marvell,armada-ap807-sdhci
+              - marvell,ac5-sdhci
           - const: marvell,armada-ap806-sdhci
 
       - items:

Documentation/devicetree/bindings/mmc/mtk-sd.yaml

@@ -145,6 +145,15 @@ properties:
     minimum: 0
     maximum: 7
 
+  mediatek,tuning-step:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Some SoCs need extend tuning step for better delay value to avoid CRC issue.
+      If not present, default tuning step is 32. For eMMC and SD, this can yield
+      satisfactory calibration results in most cases.
+    enum: [32, 64]
+    default: 32
+
   resets:
     maxItems: 1
 

Documentation/devicetree/bindings/mmc/renesas,sdhi.yaml

@@ -56,7 +56,7 @@ properties:
               - renesas,sdhi-r8a77980  # R-Car V3H
               - renesas,sdhi-r8a77990  # R-Car E3
               - renesas,sdhi-r8a77995  # R-Car D3
-              - renesas,sdhi-r9a07g043 # RZ/G2UL
+              - renesas,sdhi-r9a07g043 # RZ/G2UL and RZ/Five
               - renesas,sdhi-r9a07g044 # RZ/G2{L,LC}
               - renesas,sdhi-r9a07g054 # RZ/V2L
               - renesas,sdhi-r9a08g045 # RZ/G3S

Documentation/devicetree/bindings/mmc/sdhci-msm.yaml

@@ -22,6 +22,8 @@ properties:
       - items:
           - enum:
               - qcom,apq8084-sdhci
+              - qcom,ipq4019-sdhci
+              - qcom,ipq8074-sdhci
               - qcom,msm8226-sdhci
               - qcom,msm8953-sdhci
               - qcom,msm8974-sdhci

Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml

@@ -19,6 +19,7 @@ properties:
       - rockchip,rk3568-dwcmshc
       - rockchip,rk3588-dwcmshc
       - snps,dwcmshc-sdhci
+      - thead,th1520-dwcmshc
 
   reg:
     maxItems: 1

Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.yaml

@@ -35,6 +35,9 @@ properties:
       - const: biu
       - const: ciu
 
+  iommus:
+    maxItems: 1
+
   altr,sysmgr-syscon:
     $ref: /schemas/types.yaml#/definitions/phandle-array
     items:
@@ -62,6 +65,7 @@ allOf:
         altr,sysmgr-syscon: true
     else:
       properties:
+        iommus: false
         altr,sysmgr-syscon: false
 
 required:

drivers/mmc/core/block.c

@@ -400,6 +400,10 @@ struct mmc_blk_ioc_data {
 	struct mmc_ioc_cmd ic;
 	unsigned char *buf;
 	u64 buf_bytes;
+	unsigned int flags;
+#define MMC_BLK_IOC_DROP	BIT(0)	/* drop this mrq */
+#define MMC_BLK_IOC_SBC	BIT(1)	/* use mrq.sbc */
+
 	struct mmc_rpmb_data *rpmb;
 };
 
@@ -465,7 +469,7 @@ static int mmc_blk_ioctl_copy_to_user(struct mmc_ioc_cmd __user *ic_ptr,
 }
 
 static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
-			       struct mmc_blk_ioc_data *idata)
+			       struct mmc_blk_ioc_data **idatas, int i)
 {
 	struct mmc_command cmd = {}, sbc = {};
 	struct mmc_data data = {};
@@ -475,10 +479,18 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 	unsigned int busy_timeout_ms;
 	int err;
 	unsigned int target_part;
+	struct mmc_blk_ioc_data *idata = idatas[i];
+	struct mmc_blk_ioc_data *prev_idata = NULL;
 
 	if (!card || !md || !idata)
 		return -EINVAL;
 
+	if (idata->flags & MMC_BLK_IOC_DROP)
+		return 0;
+
+	if (idata->flags & MMC_BLK_IOC_SBC)
+		prev_idata = idatas[i - 1];
+
 	/*
 	 * The RPMB accesses comes in from the character device, so we
 	 * need to target these explicitly. Else we just target the
@@ -532,7 +544,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 			return err;
 	}
 
-	if (idata->rpmb) {
+	if (idata->rpmb || prev_idata) {
 		sbc.opcode = MMC_SET_BLOCK_COUNT;
 		/*
 		 * We don't do any blockcount validation because the max size
@@ -540,6 +552,8 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 		 * 'Reliable Write' bit here.
 		 */
 		sbc.arg = data.blocks | (idata->ic.write_flag & BIT(31));
+		if (prev_idata)
+			sbc.arg = prev_idata->ic.arg;
 		sbc.flags = MMC_RSP_R1 | MMC_CMD_AC;
 		mrq.sbc = &sbc;
 	}
@@ -557,6 +571,15 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 	mmc_wait_for_req(card->host, &mrq);
 	memcpy(&idata->ic.response, cmd.resp, sizeof(cmd.resp));
 
+	if (prev_idata) {
+		memcpy(&prev_idata->ic.response, sbc.resp, sizeof(sbc.resp));
+		if (sbc.error) {
+			dev_err(mmc_dev(card->host), "%s: sbc error %d\n",
+							__func__, sbc.error);
+			return sbc.error;
+		}
+	}
+
 	if (cmd.error) {
 		dev_err(mmc_dev(card->host), "%s: cmd error %d\n",
 						__func__, cmd.error);
@@ -1034,6 +1057,20 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type)
 	md->reset_done &= ~type;
 }
 
+static void mmc_blk_check_sbc(struct mmc_queue_req *mq_rq)
+{
+	struct mmc_blk_ioc_data **idata = mq_rq->drv_op_data;
+	int i;
+
+	for (i = 1; i < mq_rq->ioc_count; i++) {
+		if (idata[i - 1]->ic.opcode == MMC_SET_BLOCK_COUNT &&
+		    mmc_op_multi(idata[i]->ic.opcode)) {
+			idata[i - 1]->flags |= MMC_BLK_IOC_DROP;
+			idata[i]->flags |= MMC_BLK_IOC_SBC;
+		}
+	}
+}
+
 /*
  * The non-block commands come back from the block layer after it queued it and
  * processed it with all other requests and then they get issued in this
@@ -1061,11 +1098,14 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req)
 			if (ret)
 				break;
 		}
+
+		mmc_blk_check_sbc(mq_rq);
+
 		fallthrough;
 	case MMC_DRV_OP_IOCTL_RPMB:
 		idata = mq_rq->drv_op_data;
 		for (i = 0, ret = 0; i < mq_rq->ioc_count; i++) {
-			ret = __mmc_blk_ioctl_cmd(card, md, idata[i]);
+			ret = __mmc_blk_ioctl_cmd(card, md, idata, i);
 			if (ret)
 				break;
 		}

drivers/mmc/core/host.c

@@ -119,13 +119,12 @@ void mmc_retune_enable(struct mmc_host *host)
 
 /*
  * Pause re-tuning for a small set of operations.  The pause begins after the
- * next command and after first doing re-tuning.
+ * next command.
  */
 void mmc_retune_pause(struct mmc_host *host)
 {
 	if (!host->retune_paused) {
 		host->retune_paused = 1;
-		mmc_retune_needed(host);
 		mmc_retune_hold(host);
 	}
 }

drivers/mmc/core/mmc.c

@@ -136,6 +136,17 @@ static void mmc_set_erase_size(struct mmc_card *card)
 	mmc_init_erase(card);
 }
 
+
+static void mmc_set_wp_grp_size(struct mmc_card *card)
+{
+	if (card->ext_csd.erase_group_def & 1)
+		card->wp_grp_size = card->ext_csd.hc_erase_size *
+			card->ext_csd.raw_hc_erase_gap_size;
+	else
+		card->wp_grp_size = card->csd.erase_size *
+			(card->csd.wp_grp_size + 1);
+}
+
 /*
  * Given a 128-bit response, decode to our card CSD structure.
  */
@@ -186,6 +197,7 @@ static int mmc_decode_csd(struct mmc_card *card)
 		b = UNSTUFF_BITS(resp, 37, 5);
 		csd->erase_size = (a + 1) * (b + 1);
 		csd->erase_size <<= csd->write_blkbits - 9;
+		csd->wp_grp_size = UNSTUFF_BITS(resp, 32, 5);
 	}
 
 	return 0;
@@ -613,11 +625,6 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		} else {
 			card->ext_csd.data_tag_unit_size = 0;
 		}
-
-		card->ext_csd.max_packed_writes =
-			ext_csd[EXT_CSD_MAX_PACKED_WRITES];
-		card->ext_csd.max_packed_reads =
-			ext_csd[EXT_CSD_MAX_PACKED_READS];
 	} else {
 		card->ext_csd.data_sector_size = 512;
 	}
@@ -790,6 +797,7 @@ MMC_DEV_ATTR(csd, "%08x%08x%08x%08x\n", card->raw_csd[0], card->raw_csd[1],
 MMC_DEV_ATTR(date, "%02d/%04d\n", card->cid.month, card->cid.year);
 MMC_DEV_ATTR(erase_size, "%u\n", card->erase_size << 9);
 MMC_DEV_ATTR(preferred_erase_size, "%u\n", card->pref_erase << 9);
+MMC_DEV_ATTR(wp_grp_size, "%u\n", card->wp_grp_size << 9);
 MMC_DEV_ATTR(ffu_capable, "%d\n", card->ext_csd.ffu_capable);
 MMC_DEV_ATTR(hwrev, "0x%x\n", card->cid.hwrev);
 MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid);
@@ -850,6 +858,7 @@ static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_date.attr,
 	&dev_attr_erase_size.attr,
 	&dev_attr_preferred_erase_size.attr,
+	&dev_attr_wp_grp_size.attr,
 	&dev_attr_fwrev.attr,
 	&dev_attr_ffu_capable.attr,
 	&dev_attr_hwrev.attr,
@@ -1764,7 +1773,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 			mmc_set_erase_size(card);
 		}
 	}
-
+	mmc_set_wp_grp_size(card);
 	/*
 	 * Ensure eMMC user default partition is enabled
 	 */
@@ -1822,8 +1831,13 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 
 		if (err)
 			goto free_card;
-
-	} else if (!mmc_card_hs400es(card)) {
+	} else if (mmc_card_hs400es(card)) {
+		if (host->ops->execute_hs400_tuning) {
+			err = host->ops->execute_hs400_tuning(host, card);
+			if (err)
+				goto free_card;
+		}
+	} else {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
 		if (err > 0 && mmc_card_hs(card)) {

drivers/mmc/core/mmc_test.c

@@ -1904,7 +1904,7 @@ static unsigned int mmc_test_rnd_num(unsigned int rnd_cnt)
 }
 
 static int mmc_test_rnd_perf(struct mmc_test_card *test, int write, int print,
-			     unsigned long sz)
+			     unsigned long sz, int secs, int force_retuning)
 {
 	unsigned int dev_addr, cnt, rnd_addr, range1, range2, last_ea = 0, ea;
 	unsigned int ssz;
@@ -1921,7 +1921,7 @@ static int mmc_test_rnd_perf(struct mmc_test_card *test, int write, int print,
 	for (cnt = 0; cnt < UINT_MAX; cnt++) {
 		ktime_get_ts64(&ts2);
 		ts = timespec64_sub(ts2, ts1);
-		if (ts.tv_sec >= 10)
+		if (ts.tv_sec >= secs)
 			break;
 		ea = mmc_test_rnd_num(range1);
 		if (ea == last_ea)
@@ -1929,6 +1929,8 @@ static int mmc_test_rnd_perf(struct mmc_test_card *test, int write, int print,
 		last_ea = ea;
 		dev_addr = rnd_addr + test->card->pref_erase * ea +
 			   ssz * mmc_test_rnd_num(range2);
+		if (force_retuning)
+			mmc_retune_needed(test->card->host);
 		ret = mmc_test_area_io(test, sz, dev_addr, write, 0, 0);
 		if (ret)
 			return ret;
@@ -1953,24 +1955,35 @@ static int mmc_test_random_perf(struct mmc_test_card *test, int write)
 		 */
 		if (write) {
 			next = rnd_next;
-			ret = mmc_test_rnd_perf(test, write, 0, sz);
+			ret = mmc_test_rnd_perf(test, write, 0, sz, 10, 0);
 			if (ret)
 				return ret;
 			rnd_next = next;
 		}
-		ret = mmc_test_rnd_perf(test, write, 1, sz);
+		ret = mmc_test_rnd_perf(test, write, 1, sz, 10, 0);
 		if (ret)
 			return ret;
 	}
 	sz = t->max_tfr;
 	if (write) {
 		next = rnd_next;
-		ret = mmc_test_rnd_perf(test, write, 0, sz);
+		ret = mmc_test_rnd_perf(test, write, 0, sz, 10, 0);
 		if (ret)
 			return ret;
 		rnd_next = next;
 	}
-	return mmc_test_rnd_perf(test, write, 1, sz);
+	return mmc_test_rnd_perf(test, write, 1, sz, 10, 0);
+}
+
+static int mmc_test_retuning(struct mmc_test_card *test)
+{
+	if (!mmc_can_retune(test->card->host)) {
+		pr_info("%s: No retuning - test skipped\n",
+			mmc_hostname(test->card->host));
+		return RESULT_UNSUP_HOST;
+	}
+
+	return mmc_test_rnd_perf(test, 0, 0, 8192, 30, 1);
 }
 
 /*
@@ -2921,6 +2934,14 @@ static const struct mmc_test_case mmc_test_cases[] = {
 		.run = mmc_test_cmds_during_write_cmd23_nonblock,
 		.cleanup = mmc_test_area_cleanup,
 	},
+
+	{
+		.name = "Re-tuning reliability",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_retuning,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
 };
 
 static DEFINE_MUTEX(mmc_test_lock);

drivers/mmc/host/Kconfig

@@ -1026,14 +1026,15 @@ config MMC_SDHCI_XENON
 
 config MMC_SDHCI_OMAP
 	tristate "TI SDHCI Controller Support"
+	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
 	depends on MMC_SDHCI_PLTFM && OF
 	select THERMAL
 	imply TI_SOC_THERMAL
 	select MMC_SDHCI_EXTERNAL_DMA if DMA_ENGINE
 	help
 	  This selects the Secure Digital Host Controller Interface (SDHCI)
-	  support present in TI's DRA7 SOCs. The controller supports
-	  SD/MMC/SDIO devices.
+	  support present in TI's Keystone/OMAP2+/DRA7 SOCs. The controller
+	  supports SD/MMC/SDIO devices.
 
 	  If you have a controller with this interface, say Y or M here.
 
@@ -1041,14 +1042,15 @@ config MMC_SDHCI_OMAP
 
 config MMC_SDHCI_AM654
 	tristate "Support for the SDHCI Controller in TI's AM654 SOCs"
+	depends on ARCH_K3 || COMPILE_TEST
 	depends on MMC_SDHCI_PLTFM && OF
 	select MMC_SDHCI_IO_ACCESSORS
 	select MMC_CQHCI
 	select REGMAP_MMIO
 	help
 	  This selects the Secure Digital Host Controller Interface (SDHCI)
-	  support present in TI's AM654 SOCs. The controller supports
-	  SD/MMC/SDIO devices.
+	  support present in TI's AM65x/AM64x/AM62x/J721E SOCs. The controller
+	  supports SD/MMC/SDIO devices.
 
 	  If you have a controller with this interface, say Y or M here.
 

drivers/mmc/host/mmci.c

@@ -273,6 +273,7 @@ static struct variant_data variant_stm32_sdmmc = {
 	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
 	.stm32_idmabsize_mask	= GENMASK(12, 5),
 	.stm32_idmabsize_align	= BIT(5),
+	.supports_sdio_irq	= true,
 	.busy_timeout		= true,
 	.busy_detect		= true,
 	.busy_detect_flag	= MCI_STM32_BUSYD0,
@@ -300,6 +301,7 @@ static struct variant_data variant_stm32_sdmmcv2 = {
 	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
 	.stm32_idmabsize_mask	= GENMASK(16, 5),
 	.stm32_idmabsize_align	= BIT(5),
+	.supports_sdio_irq	= true,
 	.dma_lli		= true,
 	.busy_timeout		= true,
 	.busy_detect		= true,
@@ -328,6 +330,7 @@ static struct variant_data variant_stm32_sdmmcv3 = {
 	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
 	.stm32_idmabsize_mask	= GENMASK(16, 6),
 	.stm32_idmabsize_align	= BIT(6),
+	.supports_sdio_irq	= true,
 	.dma_lli		= true,
 	.busy_timeout		= true,
 	.busy_detect		= true,
@@ -421,8 +424,9 @@ void mmci_write_pwrreg(struct mmci_host *host, u32 pwr)
  */
 static void mmci_write_datactrlreg(struct mmci_host *host, u32 datactrl)
 {
-	/* Keep busy mode in DPSM if enabled */
-	datactrl |= host->datactrl_reg & host->variant->busy_dpsm_flag;
+	/* Keep busy mode in DPSM and SDIO mask if enabled */
+	datactrl |= host->datactrl_reg & (host->variant->busy_dpsm_flag |
+					  host->variant->datactrl_mask_sdio);
 
 	if (host->datactrl_reg != datactrl) {
 		host->datactrl_reg = datactrl;
@@ -1762,6 +1766,25 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void mmci_write_sdio_irq_bit(struct mmci_host *host, int enable)
+{
+	void __iomem *base = host->base;
+	u32 mask = readl_relaxed(base + MMCIMASK0);
+
+	if (enable)
+		writel_relaxed(mask | MCI_ST_SDIOITMASK, base + MMCIMASK0);
+	else
+		writel_relaxed(mask & ~MCI_ST_SDIOITMASK, base + MMCIMASK0);
+}
+
+static void mmci_signal_sdio_irq(struct mmci_host *host, u32 status)
+{
+	if (status & MCI_ST_SDIOIT) {
+		mmci_write_sdio_irq_bit(host, 0);
+		sdio_signal_irq(host->mmc);
+	}
+}
+
 /*
  * Handle completion of command and data transfers.
  */
@@ -1806,6 +1829,9 @@ static irqreturn_t mmci_irq(int irq, void *dev_id)
 			mmci_data_irq(host, host->data, status);
 		}
 
+		if (host->variant->supports_sdio_irq)
+			mmci_signal_sdio_irq(host, status);
+
 		/*
 		 * Busy detection has been handled by mmci_cmd_irq() above.
 		 * Clear the status bit to prevent polling in IRQ context.
@@ -2042,6 +2068,35 @@ static int mmci_sig_volt_switch(struct mmc_host *mmc, struct mmc_ios *ios)
 	return ret;
 }
 
+static void mmci_enable_sdio_irq(struct mmc_host *mmc, int enable)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+
+	if (enable)
+		/* Keep the SDIO mode bit if SDIO irqs are enabled */
+		pm_runtime_get_sync(mmc_dev(mmc));
+
+	spin_lock_irqsave(&host->lock, flags);
+	mmci_write_sdio_irq_bit(host, enable);
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (!enable) {
+		pm_runtime_mark_last_busy(mmc_dev(mmc));
+		pm_runtime_put_autosuspend(mmc_dev(mmc));
+	}
+}
+
+static void mmci_ack_sdio_irq(struct mmc_host *mmc)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+	mmci_write_sdio_irq_bit(host, 1);
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
 static struct mmc_host_ops mmci_ops = {
 	.request	= mmci_request,
 	.pre_req	= mmci_pre_request,
@@ -2317,6 +2372,16 @@ static int mmci_probe(struct amba_device *dev,
 		mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
 	}
 
+	if (variant->supports_sdio_irq && host->mmc->caps & MMC_CAP_SDIO_IRQ) {
+		mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
+
+		mmci_ops.enable_sdio_irq = mmci_enable_sdio_irq;
+		mmci_ops.ack_sdio_irq	= mmci_ack_sdio_irq;
+
+		mmci_write_datactrlreg(host,
+				       host->variant->datactrl_mask_sdio);
+	}
+
 	/* Variants with mandatory busy timeout in HW needs R1B responses. */
 	if (variant->busy_timeout)
 		mmc->caps |= MMC_CAP_NEED_RSP_BUSY;

drivers/mmc/host/mmci.h

@@ -331,6 +331,7 @@ enum mmci_busy_state {
  *	       register.
  * @opendrain: bitmask identifying the OPENDRAIN bit inside MMCIPOWER register
  * @dma_lli: true if variant has dma link list feature.
+ * @supports_sdio_irq: allow SD I/O card to interrupt the host
  * @stm32_idmabsize_mask: stm32 sdmmc idma buffer size.
  * @dma_flow_controller: use peripheral as flow controller for DMA.
  */
@@ -377,6 +378,7 @@ struct variant_data {
 	u32			start_err;
 	u32			opendrain;
 	u8			dma_lli:1;
+	bool			supports_sdio_irq;
 	u32			stm32_idmabsize_mask;
 	u32			stm32_idmabsize_align;
 	bool			dma_flow_controller;

drivers/mmc/host/sdhci-brcmstb.c

@@ -6,6 +6,7 @@
  */
 
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/mmc/host.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -44,8 +45,13 @@ struct brcmstb_match_priv {
 
 static inline void enable_clock_gating(struct sdhci_host *host)
 {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host);
 	u32 reg;
 
+	if (!(priv->flags & BRCMSTB_PRIV_FLAGS_GATE_CLOCK))
+		return;
+
 	reg = sdhci_readl(host, SDHCI_VENDOR);
 	reg |= SDHCI_VENDOR_GATE_SDCLK_EN;
 	sdhci_writel(host, reg, SDHCI_VENDOR);
@@ -53,13 +59,52 @@ static inline void enable_clock_gating(struct sdhci_host *host)
 
 static void brcmstb_reset(struct sdhci_host *host, u8 mask)
 {
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host);
-
 	sdhci_and_cqhci_reset(host, mask);
 
 	/* Reset will clear this, so re-enable it */
-	if (priv->flags & BRCMSTB_PRIV_FLAGS_GATE_CLOCK)
+	enable_clock_gating(host);
+}
+
+static void brcmstb_sdhci_reset_cmd_data(struct sdhci_host *host, u8 mask)
+{
+	u32 new_mask = (mask &  (SDHCI_RESET_CMD | SDHCI_RESET_DATA)) << 24;
+	int ret;
+	u32 reg;
+
+	/*
+	 * SDHCI_CLOCK_CONTROL register CARD_EN and CLOCK_INT_EN bits shall
+	 * be set along with SOFTWARE_RESET register RESET_CMD or RESET_DATA
+	 * bits, hence access SDHCI_CLOCK_CONTROL register as 32-bit register
+	 */
+	new_mask |= SDHCI_CLOCK_CARD_EN | SDHCI_CLOCK_INT_EN;
+	reg = sdhci_readl(host, SDHCI_CLOCK_CONTROL);
+	sdhci_writel(host, reg | new_mask, SDHCI_CLOCK_CONTROL);
+
+	reg = sdhci_readb(host, SDHCI_SOFTWARE_RESET);
+
+	ret = read_poll_timeout_atomic(sdhci_readb, reg, !(reg & mask),
+				       10, 10000, false,
+				       host, SDHCI_SOFTWARE_RESET);
+
+	if (ret) {
+		pr_err("%s: Reset 0x%x never completed.\n",
+		       mmc_hostname(host->mmc), (int)mask);
+		sdhci_err_stats_inc(host, CTRL_TIMEOUT);
+		sdhci_dumpregs(host);
+	}
+}
+
+static void brcmstb_reset_74165b0(struct sdhci_host *host, u8 mask)
+{
+	/* take care of RESET_ALL as usual */
+	if (mask & SDHCI_RESET_ALL)
+		sdhci_and_cqhci_reset(host, SDHCI_RESET_ALL);
+
+	/* cmd and/or data treated differently on this core */
+	if (mask & (SDHCI_RESET_CMD | SDHCI_RESET_DATA))
+		brcmstb_sdhci_reset_cmd_data(host, mask);
+
+	/* Reset will clear this, so re-enable it */
 	enable_clock_gating(host);
 }
 
@@ -162,6 +207,13 @@ static struct sdhci_ops sdhci_brcmstb_ops_7216 = {
 	.set_uhs_signaling = sdhci_brcmstb_set_uhs_signaling,
 };
 
+static struct sdhci_ops sdhci_brcmstb_ops_74165b0 = {
+	.set_clock = sdhci_brcmstb_set_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = brcmstb_reset_74165b0,
+	.set_uhs_signaling = sdhci_brcmstb_set_uhs_signaling,
+};
+
 static struct brcmstb_match_priv match_priv_7425 = {
 	.flags = BRCMSTB_MATCH_FLAGS_NO_64BIT |
 	BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT,
@@ -179,10 +231,17 @@ static const struct brcmstb_match_priv match_priv_7216 = {
 	.ops = &sdhci_brcmstb_ops_7216,
 };
 
+static struct brcmstb_match_priv match_priv_74165b0 = {
+	.flags = BRCMSTB_MATCH_FLAGS_HAS_CLOCK_GATE,
+	.hs400es = sdhci_brcmstb_hs400es,
+	.ops = &sdhci_brcmstb_ops_74165b0,
+};
+
 static const struct of_device_id __maybe_unused sdhci_brcm_of_match[] = {
 	{ .compatible = "brcm,bcm7425-sdhci", .data = &match_priv_7425 },
 	{ .compatible = "brcm,bcm7445-sdhci", .data = &match_priv_7445 },
 	{ .compatible = "brcm,bcm7216-sdhci", .data = &match_priv_7216 },
+	{ .compatible = "brcm,bcm74165b0-sdhci", .data = &match_priv_74165b0 },
 	{},
 };
 

drivers/mmc/host/sdhci-omap.c

 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * SDHCI Controller driver for TI's OMAP SoCs
  *
  * Copyright (C) 2017 Texas Instruments

drivers/mmc/host/sdhci-xenon.c

@@ -18,6 +18,8 @@
 #include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
 
 #include "sdhci-pltfm.h"
 #include "sdhci-xenon.h"
@@ -422,6 +424,7 @@ static int xenon_probe_params(struct platform_device *pdev)
 	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
 	u32 sdhc_id, nr_sdhc;
 	u32 tuning_count;
+	struct sysinfo si;
 
 	/* Disable HS200 on Armada AP806 */
 	if (priv->hw_version == XENON_AP806)
@@ -450,6 +453,23 @@ static int xenon_probe_params(struct platform_device *pdev)
 	}
 	priv->tuning_count = tuning_count;
 
+	/*
+	 * AC5/X/IM HW has only 31-bits passed in the crossbar switch.
+	 * If we have more than 2GB of memory, this means we might pass
+	 * memory pointers which are above 2GB and which cannot be properly
+	 * represented. In this case, disable ADMA, 64-bit DMA and allow only SDMA.
+	 * This effectively will enable bounce buffer quirk in the
+	 * generic SDHCI driver, which will make sure DMA is only done
+	 * from supported memory regions:
+	 */
+	if (priv->hw_version == XENON_AC5) {
+		si_meminfo(&si);
+		if (si.totalram * si.mem_unit > SZ_2G) {
+			host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;
+			host->quirks2 |= SDHCI_QUIRK2_BROKEN_64_BIT_DMA;
+		}
+	}
+
 	return xenon_phy_parse_params(dev, host);
 }
 
@@ -562,6 +582,16 @@ static int xenon_probe(struct platform_device *pdev)
 		goto remove_sdhc;
 
 	pm_runtime_put_autosuspend(&pdev->dev);
+	/*
+	 * If we previously detected AC5 with over 2GB of memory,
+	 * then we disable ADMA and 64-bit DMA.
+	 * This means generic SDHCI driver has set the DMA mask to
+	 * 32-bit. Since DDR starts at 0x2_0000_0000, we must use
+	 * 34-bit DMA mask to access this DDR memory:
+	 */
+	if (priv->hw_version == XENON_AC5 &&
+	    host->quirks2 & SDHCI_QUIRK2_BROKEN_64_BIT_DMA)
+		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(34));
 
 	return 0;
 
@@ -680,6 +710,7 @@ static const struct of_device_id sdhci_xenon_dt_ids[] = {
 	{ .compatible = "marvell,armada-ap807-sdhci", .data = (void *)XENON_AP807},
 	{ .compatible = "marvell,armada-cp110-sdhci", .data =  (void *)XENON_CP110},
 	{ .compatible = "marvell,armada-3700-sdhci", .data =  (void *)XENON_A3700},
+	{ .compatible = "marvell,ac5-sdhci",	     .data =  (void *)XENON_AC5},
 	{}
 };
 MODULE_DEVICE_TABLE(of, sdhci_xenon_dt_ids);

drivers/mmc/host/sdhci-xenon.h

@@ -57,7 +57,8 @@ enum xenon_variant {
 	XENON_A3700,
 	XENON_AP806,
 	XENON_AP807,
-	XENON_CP110
+	XENON_CP110,
+	XENON_AC5
 };
 
 struct xenon_priv {

drivers/mmc/host/sdhci.c

@@ -2841,7 +2841,7 @@ void sdhci_send_tuning(struct sdhci_host *host, u32 opcode)
 }
 EXPORT_SYMBOL_GPL(sdhci_send_tuning);
 
-static int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode)
+int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
 	int i;
 
@@ -2879,6 +2879,7 @@ static int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode)
 	sdhci_reset_tuning(host);
 	return -EAGAIN;
 }
+EXPORT_SYMBOL_GPL(__sdhci_execute_tuning);
 
 int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {

drivers/mmc/host/sdhci.h

@@ -793,6 +793,7 @@ void sdhci_set_bus_width(struct sdhci_host *host, int width);
 void sdhci_reset(struct sdhci_host *host, u8 mask);
 void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing);
 int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
+int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode);
 void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios);
 int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
 				      struct mmc_ios *ios);

drivers/mmc/host/sdhci_am654.c

@@ -141,7 +141,6 @@ static const struct timing_data td[] = {
 
 struct sdhci_am654_data {
 	struct regmap *base;
-	bool legacy_otapdly;
 	int otap_del_sel[ARRAY_SIZE(td)];
 	int itap_del_sel[ARRAY_SIZE(td)];
 	int clkbuf_sel;
@@ -272,11 +271,7 @@ static void sdhci_am654_set_clock(struct sdhci_host *host, unsigned int clock)
 	sdhci_set_clock(host, clock);
 
 	/* Setup DLL Output TAP delay */
-	if (sdhci_am654->legacy_otapdly)
-		otap_del_sel = sdhci_am654->otap_del_sel[0];
-	else
 	otap_del_sel = sdhci_am654->otap_del_sel[timing];
-
 	otap_del_ena = (timing > MMC_TIMING_UHS_SDR25) ? 1 : 0;
 
 	mask = OTAPDLYENA_MASK | OTAPDLYSEL_MASK;
@@ -314,9 +309,6 @@ static void sdhci_j721e_4bit_set_clock(struct sdhci_host *host,
 	u32 mask, val;
 
 	/* Setup DLL Output TAP delay */
-	if (sdhci_am654->legacy_otapdly)
-		otap_del_sel = sdhci_am654->otap_del_sel[0];
-	else
 	otap_del_sel = sdhci_am654->otap_del_sel[timing];
 
 	mask = OTAPDLYENA_MASK | OTAPDLYSEL_MASK;
@@ -577,32 +569,15 @@ static int sdhci_am654_get_otap_delay(struct sdhci_host *host,
 	int i;
 	int ret;
 
-	ret = device_property_read_u32(dev, td[MMC_TIMING_LEGACY].otap_binding,
-				 &sdhci_am654->otap_del_sel[MMC_TIMING_LEGACY]);
-	if (ret) {
-		/*
-		 * ti,otap-del-sel-legacy is mandatory, look for old binding
-		 * if not found.
-		 */
-		ret = device_property_read_u32(dev, "ti,otap-del-sel",
-					       &sdhci_am654->otap_del_sel[0]);
-		if (ret) {
-			dev_err(dev, "Couldn't find otap-del-sel\n");
-
-			return ret;
-		}
-
-		dev_info(dev, "Using legacy binding ti,otap-del-sel\n");
-		sdhci_am654->legacy_otapdly = true;
-
-		return 0;
-	}
-
 	for (i = MMC_TIMING_LEGACY; i <= MMC_TIMING_MMC_HS400; i++) {
 
 		ret = device_property_read_u32(dev, td[i].otap_binding,
 					       &sdhci_am654->otap_del_sel[i]);
 		if (ret) {
+			if (i == MMC_TIMING_LEGACY) {
+				dev_err(dev, "Couldn't find mandatory ti,otap-del-sel-legacy\n");
+				return ret;
+			}
 			dev_dbg(dev, "Couldn't find %s\n",
 				td[i].otap_binding);
 			/*

include/linux/mmc/card.h

@@ -32,6 +32,7 @@ struct mmc_csd {
 	unsigned int		r2w_factor;
 	unsigned int		max_dtr;
 	unsigned int		erase_size;		/* In sectors */
+	unsigned int		wp_grp_size;
 	unsigned int		read_blkbits;
 	unsigned int		write_blkbits;
 	unsigned int		capacity;
@@ -52,9 +53,6 @@ struct mmc_ext_csd {
 	u8			part_config;
 	u8			cache_ctrl;
 	u8			rst_n_function;
-	u8			max_packed_writes;
-	u8			max_packed_reads;
-	u8			packed_event_en;
 	unsigned int		part_time;		/* Units: ms */
 	unsigned int		sa_timeout;		/* Units: 100ns */
 	unsigned int		generic_cmd6_time;	/* Units: 10ms */
@@ -306,6 +304,7 @@ struct mmc_card {
 	unsigned int		eg_boundary;	/* don't cross erase-group boundaries */
 	unsigned int		erase_arg;	/* erase / trim / discard */
  	u8			erased_byte;	/* value of erased bytes */
+	unsigned int		wp_grp_size;	/* write group size in sectors */
 
 	u32			raw_cid[4];	/* raw card CID */
 	u32			raw_csd[4];	/* raw card CSD */

include/linux/mmc/core.h

@@ -27,7 +27,6 @@ struct mmc_command {
 	u32			opcode;
 	u32			arg;
 #define MMC_CMD23_ARG_REL_WR	(1 << 31)
-#define MMC_CMD23_ARG_PACKED	((0 << 31) | (1 << 30))
 #define MMC_CMD23_ARG_TAG_REQ	(1 << 29)
 	u32			resp[4];
 	unsigned int		flags;		/* expected response type */

include/linux/mmc/mmc.h

@@ -257,8 +257,6 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_FLUSH_CACHE		32      /* W */
 #define EXT_CSD_CACHE_CTRL		33      /* R/W */
 #define EXT_CSD_POWER_OFF_NOTIFICATION	34	/* R/W */
-#define EXT_CSD_PACKED_FAILURE_INDEX	35	/* RO */
-#define EXT_CSD_PACKED_CMD_STATUS	36	/* RO */
 #define EXT_CSD_EXP_EVENTS_STATUS	54	/* RO, 2 bytes */
 #define EXT_CSD_EXP_EVENTS_CTRL		56	/* R/W, 2 bytes */
 #define EXT_CSD_DATA_SECTOR_SIZE	61	/* R */
@@ -321,8 +319,6 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_SUPPORTED_MODE		493	/* RO */
 #define EXT_CSD_TAG_UNIT_SIZE		498	/* RO */
 #define EXT_CSD_DATA_TAG_SUPPORT	499	/* RO */
-#define EXT_CSD_MAX_PACKED_WRITES	500	/* RO */
-#define EXT_CSD_MAX_PACKED_READS	501	/* RO */
 #define EXT_CSD_BKOPS_SUPPORT		502	/* RO */
 #define EXT_CSD_HPI_FEATURES		503	/* RO */
 
@@ -402,18 +398,12 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_PWR_CL_8BIT_SHIFT	4
 #define EXT_CSD_PWR_CL_4BIT_SHIFT	0
 
-#define EXT_CSD_PACKED_EVENT_EN	BIT(3)
-
 /*
  * EXCEPTION_EVENT_STATUS field
  */
 #define EXT_CSD_URGENT_BKOPS		BIT(0)
 #define EXT_CSD_DYNCAP_NEEDED		BIT(1)
 #define EXT_CSD_SYSPOOL_EXHAUSTED	BIT(2)
-#define EXT_CSD_PACKED_FAILURE		BIT(3)
-
-#define EXT_CSD_PACKED_GENERIC_ERROR	BIT(0)
-#define EXT_CSD_PACKED_INDEXED_ERROR	BIT(1)
 
 /*
  * BKOPS status level