Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc: (78 commits)
  mmc: MAINTAINERS: add myself as a tmio-mmc maintainer
  mmc: print debug messages for runtime PM actions
  mmc: fix runtime PM with -ENOSYS suspend case
  mmc: at91_mci: move register header from include/ to drivers/
  mmc: mxs-mmc: fix clock rate setting
  mmc: tmio: fix a deadlock
  mmc: tmio: fix a recently introduced bug in DMA code
  mmc: sh_mmcif: maximize power saving
  mmc: tmio: maximize power saving
  mmc: tmio: fix recursive spinlock, don't schedule with interrupts disabled
  mmc: Added quirks for Ricoh 1180:e823 lower base clock frequency
  mmc: omap_hsmmc: fix oops in omap_hsmmc_dma_cb()
  mmc: omap_hsmmc: refactor duplicated code
  mmc: omap_hsmmc: fix a few bugs when setting the clock divisor
  mmc: omap_hsmmc: introduce start_clock and re-use stop_clock
  mmc: omap_hsmmc: split duplicate code to calc_divisor() function
  mmc: omap_hsmmc: move hardcoded frequency constants to defines
  mmc: omap_hsmmc: correct debug report error status mnemonics
  mmc: block: fixed NULL pointer dereference
  mmc: documentation of mmc non-blocking request usage and design.
  ...

Documentation/mmc/00-INDEX

@@ -4,3 +4,5 @@ mmc-dev-attrs.txt
         - info on SD and MMC device attributes
 mmc-dev-parts.txt
         - info on SD and MMC device partitions
+mmc-async-req.txt
+        - info on mmc asynchronous requests

Documentation/mmc/mmc-async-req.txt

+Rationale
+=========
+
+How significant is the cache maintenance overhead?
+It depends. Fast eMMC and multiple cache levels with speculative cache
+pre-fetch makes the cache overhead relatively significant. If the DMA
+preparations for the next request are done in parallel with the current
+transfer, the DMA preparation overhead would not affect the MMC performance.
+The intention of non-blocking (asynchronous) MMC requests is to minimize the
+time between when an MMC request ends and another MMC request begins.
+Using mmc_wait_for_req(), the MMC controller is idle while dma_map_sg and
+dma_unmap_sg are processing. Using non-blocking MMC requests makes it
+possible to prepare the caches for next job in parallel with an active
+MMC request.
+
+MMC block driver
+================
+
+The mmc_blk_issue_rw_rq() in the MMC block driver is made non-blocking.
+The increase in throughput is proportional to the time it takes to
+prepare (major part of preparations are dma_map_sg() and dma_unmap_sg())
+a request and how fast the memory is. The faster the MMC/SD is the
+more significant the prepare request time becomes. Roughly the expected
+performance gain is 5% for large writes and 10% on large reads on a L2 cache
+platform. In power save mode, when clocks run on a lower frequency, the DMA
+preparation may cost even more. As long as these slower preparations are run
+in parallel with the transfer performance won't be affected.
+
+Details on measurements from IOZone and mmc_test
+================================================
+
+https://wiki.linaro.org/WorkingGroups/Kernel/Specs/StoragePerfMMC-async-req
+
+MMC core API extension
+======================
+
+There is one new public function mmc_start_req().
+It starts a new MMC command request for a host. The function isn't
+truly non-blocking. If there is an ongoing async request it waits
+for completion of that request and starts the new one and returns. It
+doesn't wait for the new request to complete. If there is no ongoing
+request it starts the new request and returns immediately.
+
+MMC host extensions
+===================
+
+There are two optional members in the mmc_host_ops -- pre_req() and
+post_req() -- that the host driver may implement in order to move work
+to before and after the actual mmc_host_ops.request() function is called.
+In the DMA case pre_req() may do dma_map_sg() and prepare the DMA
+descriptor, and post_req() runs the dma_unmap_sg().
+
+Optimize for the first request
+==============================
+
+The first request in a series of requests can't be prepared in parallel
+with the previous transfer, since there is no previous request.
+The argument is_first_req in pre_req() indicates that there is no previous
+request. The host driver may optimize for this scenario to minimize
+the performance loss. A way to optimize for this is to split the current
+request in two chunks, prepare the first chunk and start the request,
+and finally prepare the second chunk and start the transfer.
+
+Pseudocode to handle is_first_req scenario with minimal prepare overhead:
+
+if (is_first_req && req->size > threshold)
+   /* start MMC transfer for the complete transfer size */
+   mmc_start_command(MMC_CMD_TRANSFER_FULL_SIZE);
+
+   /*
+    * Begin to prepare DMA while cmd is being processed by MMC.
+    * The first chunk of the request should take the same time
+    * to prepare as the "MMC process command time".
+    * If prepare time exceeds MMC cmd time
+    * the transfer is delayed, guesstimate max 4k as first chunk size.
+    */
+    prepare_1st_chunk_for_dma(req);
+    /* flush pending desc to the DMAC (dmaengine.h) */
+    dma_issue_pending(req->dma_desc);
+
+    prepare_2nd_chunk_for_dma(req);
+    /*
+     * The second issue_pending should be called before MMC runs out
+     * of the first chunk. If the MMC runs out of the first data chunk
+     * before this call, the transfer is delayed.
+     */
+    dma_issue_pending(req->dma_desc);

MAINTAINERS

@@ -4585,9 +4585,8 @@ S:	Maintained
 F:	drivers/mmc/host/omap.c
 
 OMAP HS MMC SUPPORT
-M:	Madhusudhan Chikkature <madhu.cr@ti.com>
 L:	linux-omap@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/mmc/host/omap_hsmmc.c
 
 OMAP RANDOM NUMBER GENERATOR SUPPORT
@@ -6243,9 +6242,14 @@ F:	drivers/char/toshiba.c
 F:	include/linux/toshiba.h
 
 TMIO MMC DRIVER
+M:	Guennadi Liakhovetski <g.liakhovetski@gmx.de>
 M:	Ian Molton <ian@mnementh.co.uk>
+L:	linux-mmc@vger.kernel.org
 S:	Maintained
-F:	drivers/mmc/host/tmio_mmc.*
+F:	drivers/mmc/host/tmio_mmc*
+F:	drivers/mmc/host/sh_mobile_sdhi.c
+F:	include/linux/mmc/tmio.h
+F:	include/linux/mmc/sh_mobile_sdhi.h
 
 TMPFS (SHMEM FILESYSTEM)
 M:	Hugh Dickins <hughd@google.com>

arch/arm/configs/mmp2_defconfig

@@ -8,6 +8,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_ARCH_MMP=y
+CONFIG_MACH_BROWNSTONE=y
 CONFIG_MACH_FLINT=y
 CONFIG_MACH_MARVELL_JASPER=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -63,10 +64,16 @@ CONFIG_BACKLIGHT_MAX8925=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MAX8925=y
+CONFIG_MMC=y
 # CONFIG_DNOTIFY is not set
 CONFIG_INOTIFY=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=437
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
@@ -81,7 +88,7 @@ CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_PREEMPT is not set
 CONFIG_DEBUG_INFO=y
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_DYNAMIC_DEBUG=y
+# CONFIG_DYNAMIC_DEBUG is not set
 CONFIG_DEBUG_USER=y
 CONFIG_DEBUG_ERRORS=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set

arch/arm/mach-mmp/brownstone.c

@@ -177,9 +177,16 @@ static struct i2c_board_info brownstone_twsi1_info[] = {
 };
 
 static struct sdhci_pxa_platdata mmp2_sdh_platdata_mmc0 = {
-	.max_speed	= 25000000,
+	.clk_delay_cycles = 0x1f,
 };
 
+static struct sdhci_pxa_platdata mmp2_sdh_platdata_mmc2 = {
+	.clk_delay_cycles = 0x1f,
+	.flags = PXA_FLAG_CARD_PERMANENT
+		| PXA_FLAG_SD_8_BIT_CAPABLE_SLOT,
+};
+
+
 static void __init brownstone_init(void)
 {
 	mfp_config(ARRAY_AND_SIZE(brownstone_pin_config));
@@ -189,6 +196,7 @@ static void __init brownstone_init(void)
 	mmp2_add_uart(3);
 	mmp2_add_twsi(1, NULL, ARRAY_AND_SIZE(brownstone_twsi1_info));
 	mmp2_add_sdhost(0, &mmp2_sdh_platdata_mmc0); /* SD/MMC */
+	mmp2_add_sdhost(2, &mmp2_sdh_platdata_mmc2); /* eMMC */
 
 	/* enable 5v regulator */
 	platform_device_register(&brownstone_v_5vp_device);

arch/arm/mach-mmp/include/mach/mmp2.h

 #ifndef __ASM_MACH_MMP2_H
 #define __ASM_MACH_MMP2_H
 
-#include <plat/sdhci.h>
+#include <linux/platform_data/pxa_sdhci.h>
 
 struct sys_timer;
 

arch/arm/mach-mmp/jasper.c

@@ -154,7 +154,7 @@ static struct i2c_board_info jasper_twsi1_info[] = {
 };
 
 static struct sdhci_pxa_platdata mmp2_sdh_platdata_mmc0 = {
-	.max_speed	= 25000000,
+	.clk_delay_cycles = 0x1f,
 };
 
 static void __init jasper_init(void)

arch/arm/mach-mmp/mmp2.c

@@ -168,10 +168,10 @@ static struct clk_lookup mmp2_clkregs[] = {
 	INIT_CLKREG(&clk_twsi5, "pxa2xx-i2c.4", NULL),
 	INIT_CLKREG(&clk_twsi6, "pxa2xx-i2c.5", NULL),
 	INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL),
-	INIT_CLKREG(&clk_sdh0, "sdhci-pxa.0", "PXA-SDHCLK"),
-	INIT_CLKREG(&clk_sdh1, "sdhci-pxa.1", "PXA-SDHCLK"),
-	INIT_CLKREG(&clk_sdh2, "sdhci-pxa.2", "PXA-SDHCLK"),
-	INIT_CLKREG(&clk_sdh3, "sdhci-pxa.3", "PXA-SDHCLK"),
+	INIT_CLKREG(&clk_sdh0, "sdhci-pxav3.0", "PXA-SDHCLK"),
+	INIT_CLKREG(&clk_sdh1, "sdhci-pxav3.1", "PXA-SDHCLK"),
+	INIT_CLKREG(&clk_sdh2, "sdhci-pxav3.2", "PXA-SDHCLK"),
+	INIT_CLKREG(&clk_sdh3, "sdhci-pxav3.3", "PXA-SDHCLK"),
 };
 
 static int __init mmp2_init(void)
@@ -222,8 +222,8 @@ MMP2_DEVICE(twsi4, "pxa2xx-i2c", 3, TWSI4, 0xd4033000, 0x70);
 MMP2_DEVICE(twsi5, "pxa2xx-i2c", 4, TWSI5, 0xd4033800, 0x70);
 MMP2_DEVICE(twsi6, "pxa2xx-i2c", 5, TWSI6, 0xd4034000, 0x70);
 MMP2_DEVICE(nand, "pxa3xx-nand", -1, NAND, 0xd4283000, 0x100, 28, 29);
-MMP2_DEVICE(sdh0, "sdhci-pxa", 0, MMC, 0xd4280000, 0x120);
-MMP2_DEVICE(sdh1, "sdhci-pxa", 1, MMC2, 0xd4280800, 0x120);
-MMP2_DEVICE(sdh2, "sdhci-pxa", 2, MMC3, 0xd4281000, 0x120);
-MMP2_DEVICE(sdh3, "sdhci-pxa", 3, MMC4, 0xd4281800, 0x120);
+MMP2_DEVICE(sdh0, "sdhci-pxav3", 0, MMC, 0xd4280000, 0x120);
+MMP2_DEVICE(sdh1, "sdhci-pxav3", 1, MMC2, 0xd4280800, 0x120);
+MMP2_DEVICE(sdh2, "sdhci-pxav3", 2, MMC3, 0xd4281000, 0x120);
+MMP2_DEVICE(sdh3, "sdhci-pxav3", 3, MMC4, 0xd4281800, 0x120);
 

drivers/mmc/card/queue.c

@@ -52,14 +52,18 @@ static int mmc_queue_thread(void *d)
 	down(&mq->thread_sem);
 	do {
 		struct request *req = NULL;
+		struct mmc_queue_req *tmp;
 
 		spin_lock_irq(q->queue_lock);
 		set_current_state(TASK_INTERRUPTIBLE);
 		req = blk_fetch_request(q);
-		mq->req = req;
+		mq->mqrq_cur->req = req;
 		spin_unlock_irq(q->queue_lock);
 
-		if (!req) {
+		if (req || mq->mqrq_prev->req) {
+			set_current_state(TASK_RUNNING);
+			mq->issue_fn(mq, req);
+		} else {
 			if (kthread_should_stop()) {
 				set_current_state(TASK_RUNNING);
 				break;
@@ -67,11 +71,14 @@ static int mmc_queue_thread(void *d)
 			up(&mq->thread_sem);
 			schedule();
 			down(&mq->thread_sem);
-			continue;
 		}
-		set_current_state(TASK_RUNNING);
 
-		mq->issue_fn(mq, req);
+		/* Current request becomes previous request and vice versa. */
+		mq->mqrq_prev->brq.mrq.data = NULL;
+		mq->mqrq_prev->req = NULL;
+		tmp = mq->mqrq_prev;
+		mq->mqrq_prev = mq->mqrq_cur;
+		mq->mqrq_cur = tmp;
 	} while (1);
 	up(&mq->thread_sem);
 
@@ -97,10 +104,46 @@ static void mmc_request(struct request_queue *q)
 		return;
 	}
 
-	if (!mq->req)
+	if (!mq->mqrq_cur->req && !mq->mqrq_prev->req)
 		wake_up_process(mq->thread);
 }
 
+struct scatterlist *mmc_alloc_sg(int sg_len, int *err)
+{
+	struct scatterlist *sg;
+
+	sg = kmalloc(sizeof(struct scatterlist)*sg_len, GFP_KERNEL);
+	if (!sg)
+		*err = -ENOMEM;
+	else {
+		*err = 0;
+		sg_init_table(sg, sg_len);
+	}
+
+	return sg;
+}
+
+static void mmc_queue_setup_discard(struct request_queue *q,
+				    struct mmc_card *card)
+{
+	unsigned max_discard;
+
+	max_discard = mmc_calc_max_discard(card);
+	if (!max_discard)
+		return;
+
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+	q->limits.max_discard_sectors = max_discard;
+	if (card->erased_byte == 0)
+		q->limits.discard_zeroes_data = 1;
+	q->limits.discard_granularity = card->pref_erase << 9;
+	/* granularity must not be greater than max. discard */
+	if (card->pref_erase > max_discard)
+		q->limits.discard_granularity = 0;
+	if (mmc_can_secure_erase_trim(card))
+		queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q);
+}
+
 /**
  * mmc_init_queue - initialise a queue structure.
  * @mq: mmc queue
@@ -116,6 +159,8 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	struct mmc_host *host = card->host;
 	u64 limit = BLK_BOUNCE_HIGH;
 	int ret;
+	struct mmc_queue_req *mqrq_cur = &mq->mqrq[0];
+	struct mmc_queue_req *mqrq_prev = &mq->mqrq[1];
 
 	if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
 		limit = *mmc_dev(host)->dma_mask;
@@ -125,21 +170,16 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	if (!mq->queue)
 		return -ENOMEM;
 
+	memset(&mq->mqrq_cur, 0, sizeof(mq->mqrq_cur));
+	memset(&mq->mqrq_prev, 0, sizeof(mq->mqrq_prev));
+	mq->mqrq_cur = mqrq_cur;
+	mq->mqrq_prev = mqrq_prev;
 	mq->queue->queuedata = mq;
-	mq->req = NULL;
 
 	blk_queue_prep_rq(mq->queue, mmc_prep_request);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);
-	if (mmc_can_erase(card)) {
-		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mq->queue);
-		mq->queue->limits.max_discard_sectors = UINT_MAX;
-		if (card->erased_byte == 0)
-			mq->queue->limits.discard_zeroes_data = 1;
-		mq->queue->limits.discard_granularity = card->pref_erase << 9;
-		if (mmc_can_secure_erase_trim(card))
-			queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD,
-						mq->queue);
-	}
+	if (mmc_can_erase(card))
+		mmc_queue_setup_discard(mq->queue, card);
 
 #ifdef CONFIG_MMC_BLOCK_BOUNCE
 	if (host->max_segs == 1) {
@@ -155,53 +195,64 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 			bouncesz = host->max_blk_count * 512;
 
 		if (bouncesz > 512) {
-			mq->bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
-			if (!mq->bounce_buf) {
+			mqrq_cur->bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
+			if (!mqrq_cur->bounce_buf) {
+				printk(KERN_WARNING "%s: unable to "
+					"allocate bounce cur buffer\n",
+					mmc_card_name(card));
+			}
+			mqrq_prev->bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
+			if (!mqrq_prev->bounce_buf) {
 				printk(KERN_WARNING "%s: unable to "
-					"allocate bounce buffer\n",
+					"allocate bounce prev buffer\n",
 					mmc_card_name(card));
+				kfree(mqrq_cur->bounce_buf);
+				mqrq_cur->bounce_buf = NULL;
 			}
 		}
 
-		if (mq->bounce_buf) {
+		if (mqrq_cur->bounce_buf && mqrq_prev->bounce_buf) {
 			blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY);
 			blk_queue_max_hw_sectors(mq->queue, bouncesz / 512);
 			blk_queue_max_segments(mq->queue, bouncesz / 512);
 			blk_queue_max_segment_size(mq->queue, bouncesz);
 
-			mq->sg = kmalloc(sizeof(struct scatterlist),
-				GFP_KERNEL);
-			if (!mq->sg) {
-				ret = -ENOMEM;
+			mqrq_cur->sg = mmc_alloc_sg(1, &ret);
+			if (ret)
 				goto cleanup_queue;
-			}
-			sg_init_table(mq->sg, 1);
 
-			mq->bounce_sg = kmalloc(sizeof(struct scatterlist) *
-				bouncesz / 512, GFP_KERNEL);
-			if (!mq->bounce_sg) {
-				ret = -ENOMEM;
+			mqrq_cur->bounce_sg =
+				mmc_alloc_sg(bouncesz / 512, &ret);
+			if (ret)
+				goto cleanup_queue;
+
+			mqrq_prev->sg = mmc_alloc_sg(1, &ret);
+			if (ret)
+				goto cleanup_queue;
+
+			mqrq_prev->bounce_sg =
+				mmc_alloc_sg(bouncesz / 512, &ret);
+			if (ret)
 				goto cleanup_queue;
-			}
-			sg_init_table(mq->bounce_sg, bouncesz / 512);
 		}
 	}
 #endif
 
-	if (!mq->bounce_buf) {
+	if (!mqrq_cur->bounce_buf && !mqrq_prev->bounce_buf) {
 		blk_queue_bounce_limit(mq->queue, limit);
 		blk_queue_max_hw_sectors(mq->queue,
 			min(host->max_blk_count, host->max_req_size / 512));
 		blk_queue_max_segments(mq->queue, host->max_segs);
 		blk_queue_max_segment_size(mq->queue, host->max_seg_size);
 
-		mq->sg = kmalloc(sizeof(struct scatterlist) *
-			host->max_segs, GFP_KERNEL);
-		if (!mq->sg) {
-			ret = -ENOMEM;
+		mqrq_cur->sg = mmc_alloc_sg(host->max_segs, &ret);
+		if (ret)
+			goto cleanup_queue;
+
+
+		mqrq_prev->sg = mmc_alloc_sg(host->max_segs, &ret);
+		if (ret)
 			goto cleanup_queue;
-		}
-		sg_init_table(mq->sg, host->max_segs);
 	}
 
 	sema_init(&mq->thread_sem, 1);
@@ -216,16 +267,22 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 
 	return 0;
  free_bounce_sg:
- 	if (mq->bounce_sg)
- 		kfree(mq->bounce_sg);
- 	mq->bounce_sg = NULL;
+	kfree(mqrq_cur->bounce_sg);
+	mqrq_cur->bounce_sg = NULL;
+	kfree(mqrq_prev->bounce_sg);
+	mqrq_prev->bounce_sg = NULL;
+
  cleanup_queue:
- 	if (mq->sg)
-		kfree(mq->sg);
-	mq->sg = NULL;
-	if (mq->bounce_buf)
-		kfree(mq->bounce_buf);
-	mq->bounce_buf = NULL;
+	kfree(mqrq_cur->sg);
+	mqrq_cur->sg = NULL;
+	kfree(mqrq_cur->bounce_buf);
+	mqrq_cur->bounce_buf = NULL;
+
+	kfree(mqrq_prev->sg);
+	mqrq_prev->sg = NULL;
+	kfree(mqrq_prev->bounce_buf);
+	mqrq_prev->bounce_buf = NULL;
+
 	blk_cleanup_queue(mq->queue);
 	return ret;
 }
@@ -234,6 +291,8 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 {
 	struct request_queue *q = mq->queue;
 	unsigned long flags;
+	struct mmc_queue_req *mqrq_cur = mq->mqrq_cur;
+	struct mmc_queue_req *mqrq_prev = mq->mqrq_prev;
 
 	/* Make sure the queue isn't suspended, as that will deadlock */
 	mmc_queue_resume(mq);
@@ -247,16 +306,23 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 	blk_start_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
- 	if (mq->bounce_sg)
- 		kfree(mq->bounce_sg);
- 	mq->bounce_sg = NULL;
+	kfree(mqrq_cur->bounce_sg);
+	mqrq_cur->bounce_sg = NULL;
+
+	kfree(mqrq_cur->sg);
+	mqrq_cur->sg = NULL;
+
+	kfree(mqrq_cur->bounce_buf);
+	mqrq_cur->bounce_buf = NULL;
 
-	kfree(mq->sg);
-	mq->sg = NULL;
+	kfree(mqrq_prev->bounce_sg);
+	mqrq_prev->bounce_sg = NULL;
 
-	if (mq->bounce_buf)
-		kfree(mq->bounce_buf);
-	mq->bounce_buf = NULL;
+	kfree(mqrq_prev->sg);
+	mqrq_prev->sg = NULL;
+
+	kfree(mqrq_prev->bounce_buf);
+	mqrq_prev->bounce_buf = NULL;
 
 	mq->card = NULL;
 }
@@ -309,27 +375,27 @@ void mmc_queue_resume(struct mmc_queue *mq)
 /*
  * Prepare the sg list(s) to be handed of to the host driver
  */
-unsigned int mmc_queue_map_sg(struct mmc_queue *mq)
+unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq)
 {
 	unsigned int sg_len;
 	size_t buflen;
 	struct scatterlist *sg;
 	int i;
 
-	if (!mq->bounce_buf)
-		return blk_rq_map_sg(mq->queue, mq->req, mq->sg);
+	if (!mqrq->bounce_buf)
+		return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg);
 
-	BUG_ON(!mq->bounce_sg);
+	BUG_ON(!mqrq->bounce_sg);
 
-	sg_len = blk_rq_map_sg(mq->queue, mq->req, mq->bounce_sg);
+	sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg);
 
-	mq->bounce_sg_len = sg_len;
+	mqrq->bounce_sg_len = sg_len;
 
 	buflen = 0;
-	for_each_sg(mq->bounce_sg, sg, sg_len, i)
+	for_each_sg(mqrq->bounce_sg, sg, sg_len, i)
 		buflen += sg->length;
 
-	sg_init_one(mq->sg, mq->bounce_buf, buflen);
+	sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen);
 
 	return 1;
 }
@@ -338,31 +404,30 @@ unsigned int mmc_queue_map_sg(struct mmc_queue *mq)
  * If writing, bounce the data to the buffer before the request
  * is sent to the host driver
  */
-void mmc_queue_bounce_pre(struct mmc_queue *mq)
+void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq)
 {
-	if (!mq->bounce_buf)
+	if (!mqrq->bounce_buf)
 		return;
 
-	if (rq_data_dir(mq->req) != WRITE)
+	if (rq_data_dir(mqrq->req) != WRITE)
 		return;
 
-	sg_copy_to_buffer(mq->bounce_sg, mq->bounce_sg_len,
-		mq->bounce_buf, mq->sg[0].length);
+	sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
+		mqrq->bounce_buf, mqrq->sg[0].length);
 }
 
 /*
  * If reading, bounce the data from the buffer after the request
  * has been handled by the host driver
  */
-void mmc_queue_bounce_post(struct mmc_queue *mq)
+void mmc_queue_bounce_post(struct mmc_queue_req *mqrq)
 {
-	if (!mq->bounce_buf)
+	if (!mqrq->bounce_buf)
 		return;
 
-	if (rq_data_dir(mq->req) != READ)
+	if (rq_data_dir(mqrq->req) != READ)
 		return;
 
-	sg_copy_from_buffer(mq->bounce_sg, mq->bounce_sg_len,
-		mq->bounce_buf, mq->sg[0].length);
+	sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
+		mqrq->bounce_buf, mqrq->sg[0].length);
 }
-

drivers/mmc/card/queue.h

@@ -4,19 +4,35 @@
 struct request;
 struct task_struct;
 
+struct mmc_blk_request {
+	struct mmc_request	mrq;
+	struct mmc_command	sbc;
+	struct mmc_command	cmd;
+	struct mmc_command	stop;
+	struct mmc_data		data;
+};
+
+struct mmc_queue_req {
+	struct request		*req;
+	struct mmc_blk_request	brq;
+	struct scatterlist	*sg;
+	char			*bounce_buf;
+	struct scatterlist	*bounce_sg;
+	unsigned int		bounce_sg_len;
+	struct mmc_async_req	mmc_active;
+};
+
 struct mmc_queue {
 	struct mmc_card		*card;
 	struct task_struct	*thread;
 	struct semaphore	thread_sem;
 	unsigned int		flags;
-	struct request		*req;
 	int			(*issue_fn)(struct mmc_queue *, struct request *);
 	void			*data;
 	struct request_queue	*queue;
-	struct scatterlist	*sg;
-	char			*bounce_buf;
-	struct scatterlist	*bounce_sg;
-	unsigned int		bounce_sg_len;
+	struct mmc_queue_req	mqrq[2];
+	struct mmc_queue_req	*mqrq_cur;
+	struct mmc_queue_req	*mqrq_prev;
 };
 
 extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
@@ -25,8 +41,9 @@ extern void mmc_cleanup_queue(struct mmc_queue *);
 extern void mmc_queue_suspend(struct mmc_queue *);
 extern void mmc_queue_resume(struct mmc_queue *);
 
-extern unsigned int mmc_queue_map_sg(struct mmc_queue *);
-extern void mmc_queue_bounce_pre(struct mmc_queue *);
-extern void mmc_queue_bounce_post(struct mmc_queue *);
+extern unsigned int mmc_queue_map_sg(struct mmc_queue *,
+				     struct mmc_queue_req *);
+extern void mmc_queue_bounce_pre(struct mmc_queue_req *);
+extern void mmc_queue_bounce_post(struct mmc_queue_req *);
 
 #endif

drivers/mmc/core/core.c

@@ -198,9 +198,109 @@ mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 
 static void mmc_wait_done(struct mmc_request *mrq)
 {
-	complete(mrq->done_data);
+	complete(&mrq->completion);
+}
+
+static void __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq)
+{
+	init_completion(&mrq->completion);
+	mrq->done = mmc_wait_done;
+	mmc_start_request(host, mrq);
+}
+
+static void mmc_wait_for_req_done(struct mmc_host *host,
+				  struct mmc_request *mrq)
+{
+	wait_for_completion(&mrq->completion);
 }
 
+/**
+ *	mmc_pre_req - Prepare for a new request
+ *	@host: MMC host to prepare command
+ *	@mrq: MMC request to prepare for
+ *	@is_first_req: true if there is no previous started request
+ *                     that may run in parellel to this call, otherwise false
+ *
+ *	mmc_pre_req() is called in prior to mmc_start_req() to let
+ *	host prepare for the new request. Preparation of a request may be
+ *	performed while another request is running on the host.
+ */
+static void mmc_pre_req(struct mmc_host *host, struct mmc_request *mrq,
+		 bool is_first_req)
+{
+	if (host->ops->pre_req)
+		host->ops->pre_req(host, mrq, is_first_req);
+}
+
+/**
+ *	mmc_post_req - Post process a completed request
+ *	@host: MMC host to post process command
+ *	@mrq: MMC request to post process for
+ *	@err: Error, if non zero, clean up any resources made in pre_req
+ *
+ *	Let the host post process a completed request. Post processing of
+ *	a request may be performed while another reuqest is running.
+ */
+static void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq,
+			 int err)
+{
+	if (host->ops->post_req)
+		host->ops->post_req(host, mrq, err);
+}
+
+/**
+ *	mmc_start_req - start a non-blocking request
+ *	@host: MMC host to start command
+ *	@areq: async request to start
+ *	@error: out parameter returns 0 for success, otherwise non zero
+ *
+ *	Start a new MMC custom command request for a host.
+ *	If there is on ongoing async request wait for completion
+ *	of that request and start the new one and return.
+ *	Does not wait for the new request to complete.
+ *
+ *      Returns the completed request, NULL in case of none completed.
+ *	Wait for the an ongoing request (previoulsy started) to complete and
+ *	return the completed request. If there is no ongoing request, NULL
+ *	is returned without waiting. NULL is not an error condition.
+ */
+struct mmc_async_req *mmc_start_req(struct mmc_host *host,
+				    struct mmc_async_req *areq, int *error)
+{
+	int err = 0;
+	struct mmc_async_req *data = host->areq;
+
+	/* Prepare a new request */
+	if (areq)
+		mmc_pre_req(host, areq->mrq, !host->areq);
+
+	if (host->areq) {
+		mmc_wait_for_req_done(host, host->areq->mrq);
+		err = host->areq->err_check(host->card, host->areq);
+		if (err) {
+			mmc_post_req(host, host->areq->mrq, 0);
+			if (areq)
+				mmc_post_req(host, areq->mrq, -EINVAL);
+
+			host->areq = NULL;
+			goto out;
+		}
+	}
+
+	if (areq)
+		__mmc_start_req(host, areq->mrq);
+
+	if (host->areq)
+		mmc_post_req(host, host->areq->mrq, 0);
+
+	host->areq = areq;
+ out:
+	if (error)
+		*error = err;
+	return data;
+}
+EXPORT_SYMBOL(mmc_start_req);
+
 /**
  *	mmc_wait_for_req - start a request and wait for completion
  *	@host: MMC host to start command
@@ -212,16 +312,9 @@ static void mmc_wait_done(struct mmc_request *mrq)
  */
 void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq)
 {
-	DECLARE_COMPLETION_ONSTACK(complete);
-
-	mrq->done_data = &complete;
-	mrq->done = mmc_wait_done;
-
-	mmc_start_request(host, mrq);
-
-	wait_for_completion(&complete);
+	__mmc_start_req(host, mrq);
+	mmc_wait_for_req_done(host, mrq);
 }
-
 EXPORT_SYMBOL(mmc_wait_for_req);
 
 /**
@@ -1516,6 +1609,82 @@ int mmc_erase_group_aligned(struct mmc_card *card, unsigned int from,
 }
 EXPORT_SYMBOL(mmc_erase_group_aligned);
 
+static unsigned int mmc_do_calc_max_discard(struct mmc_card *card,
+					    unsigned int arg)
+{
+	struct mmc_host *host = card->host;
+	unsigned int max_discard, x, y, qty = 0, max_qty, timeout;
+	unsigned int last_timeout = 0;
+
+	if (card->erase_shift)
+		max_qty = UINT_MAX >> card->erase_shift;
+	else if (mmc_card_sd(card))
+		max_qty = UINT_MAX;
+	else
+		max_qty = UINT_MAX / card->erase_size;
+
+	/* Find the largest qty with an OK timeout */
+	do {
+		y = 0;
+		for (x = 1; x && x <= max_qty && max_qty - x >= qty; x <<= 1) {
+			timeout = mmc_erase_timeout(card, arg, qty + x);
+			if (timeout > host->max_discard_to)
+				break;
+			if (timeout < last_timeout)
+				break;
+			last_timeout = timeout;
+			y = x;
+		}
+		qty += y;
+	} while (y);
+
+	if (!qty)
+		return 0;
+
+	if (qty == 1)
+		return 1;
+
+	/* Convert qty to sectors */
+	if (card->erase_shift)
+		max_discard = --qty << card->erase_shift;
+	else if (mmc_card_sd(card))
+		max_discard = qty;
+	else
+		max_discard = --qty * card->erase_size;
+
+	return max_discard;
+}
+
+unsigned int mmc_calc_max_discard(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	unsigned int max_discard, max_trim;
+
+	if (!host->max_discard_to)
+		return UINT_MAX;
+
+	/*
+	 * Without erase_group_def set, MMC erase timeout depends on clock
+	 * frequence which can change.  In that case, the best choice is
+	 * just the preferred erase size.
+	 */
+	if (mmc_card_mmc(card) && !(card->ext_csd.erase_group_def & 1))
+		return card->pref_erase;
+
+	max_discard = mmc_do_calc_max_discard(card, MMC_ERASE_ARG);
+	if (mmc_can_trim(card)) {
+		max_trim = mmc_do_calc_max_discard(card, MMC_TRIM_ARG);
+		if (max_trim < max_discard)
+			max_discard = max_trim;
+	} else if (max_discard < card->erase_size) {
+		max_discard = 0;
+	}
+	pr_debug("%s: calculated max. discard sectors %u for timeout %u ms\n",
+		 mmc_hostname(host), max_discard, host->max_discard_to);
+	return max_discard;
+}
+EXPORT_SYMBOL(mmc_calc_max_discard);
+
 int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen)
 {
 	struct mmc_command cmd = {0};
@@ -1663,6 +1832,10 @@ int mmc_power_save_host(struct mmc_host *host)
 {
 	int ret = 0;
 
+#ifdef CONFIG_MMC_DEBUG
+	pr_info("%s: %s: powering down\n", mmc_hostname(host), __func__);
+#endif
+
 	mmc_bus_get(host);
 
 	if (!host->bus_ops || host->bus_dead || !host->bus_ops->power_restore) {
@@ -1685,6 +1858,10 @@ int mmc_power_restore_host(struct mmc_host *host)
 {
 	int ret;
 
+#ifdef CONFIG_MMC_DEBUG
+	pr_info("%s: %s: powering up\n", mmc_hostname(host), __func__);
+#endif
+
 	mmc_bus_get(host);
 
 	if (!host->bus_ops || host->bus_dead || !host->bus_ops->power_restore) {

drivers/mmc/core/sd.c

@@ -409,52 +409,62 @@ int mmc_sd_switch_hs(struct mmc_card *card)
 
 static int sd_select_driver_type(struct mmc_card *card, u8 *status)
 {
-	int host_drv_type = 0, card_drv_type = 0;
+	int host_drv_type = SD_DRIVER_TYPE_B;
+	int card_drv_type = SD_DRIVER_TYPE_B;
+	int drive_strength;
 	int err;
 
 	/*
 	 * If the host doesn't support any of the Driver Types A,C or D,
-	 * default Driver Type B is used.
+	 * or there is no board specific handler then default Driver
+	 * Type B is used.
 	 */
 	if (!(card->host->caps & (MMC_CAP_DRIVER_TYPE_A | MMC_CAP_DRIVER_TYPE_C
 	    | MMC_CAP_DRIVER_TYPE_D)))
 		return 0;
 
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_A) {
-		host_drv_type = MMC_SET_DRIVER_TYPE_A;
+	if (!card->host->ops->select_drive_strength)
+		return 0;
+
+	if (card->host->caps & MMC_CAP_DRIVER_TYPE_A)
+		host_drv_type |= SD_DRIVER_TYPE_A;
+
+	if (card->host->caps & MMC_CAP_DRIVER_TYPE_C)
+		host_drv_type |= SD_DRIVER_TYPE_C;
+
+	if (card->host->caps & MMC_CAP_DRIVER_TYPE_D)
+		host_drv_type |= SD_DRIVER_TYPE_D;
+
 	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_A)
-			card_drv_type = MMC_SET_DRIVER_TYPE_A;
-		else if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_B)
-			card_drv_type = MMC_SET_DRIVER_TYPE_B;
-		else if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C)
-			card_drv_type = MMC_SET_DRIVER_TYPE_C;
-	} else if (card->host->caps & MMC_CAP_DRIVER_TYPE_C) {
-		host_drv_type = MMC_SET_DRIVER_TYPE_C;
+		card_drv_type |= SD_DRIVER_TYPE_A;
+
 	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C)
-			card_drv_type = MMC_SET_DRIVER_TYPE_C;
-	} else if (!(card->host->caps & MMC_CAP_DRIVER_TYPE_D)) {
+		card_drv_type |= SD_DRIVER_TYPE_C;
+
+	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_D)
+		card_drv_type |= SD_DRIVER_TYPE_D;
+
 	/*
-		 * If we are here, that means only the default driver type
-		 * B is supported by the host.
+	 * The drive strength that the hardware can support
+	 * depends on the board design.  Pass the appropriate
+	 * information and let the hardware specific code
+	 * return what is possible given the options
 	 */
-		host_drv_type = MMC_SET_DRIVER_TYPE_B;
-		if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_B)
-			card_drv_type = MMC_SET_DRIVER_TYPE_B;
-		else if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C)
-			card_drv_type = MMC_SET_DRIVER_TYPE_C;
-	}
+	drive_strength = card->host->ops->select_drive_strength(
+		card->sw_caps.uhs_max_dtr,
+		host_drv_type, card_drv_type);
 
-	err = mmc_sd_switch(card, 1, 2, card_drv_type, status);
+	err = mmc_sd_switch(card, 1, 2, drive_strength, status);
 	if (err)
 		return err;
 
-	if ((status[15] & 0xF) != card_drv_type) {
-		printk(KERN_WARNING "%s: Problem setting driver strength!\n",
+	if ((status[15] & 0xF) != drive_strength) {
+		printk(KERN_WARNING "%s: Problem setting drive strength!\n",
 			mmc_hostname(card->host));
 		return 0;
 	}
 
-	mmc_set_driver_type(card->host, host_drv_type);
+	mmc_set_driver_type(card->host, drive_strength);
 
 	return 0;
 }

drivers/mmc/core/sdio_bus.c

@@ -167,11 +167,8 @@ static int sdio_bus_remove(struct device *dev)
 	int ret = 0;
 
 	/* Make sure card is powered before invoking ->remove() */
-	if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD) {
-		ret = pm_runtime_get_sync(dev);
-		if (ret < 0)
-			goto out;
-	}
+	if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD)
+		pm_runtime_get_sync(dev);
 
 	drv->remove(func);
 
@@ -191,7 +188,6 @@ static int sdio_bus_remove(struct device *dev)
 	if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD)
 		pm_runtime_put_sync(dev);
 
-out:
 	return ret;
 }
 

drivers/mmc/host/Kconfig

@@ -81,28 +81,32 @@ config MMC_RICOH_MMC
 
 	  If unsure, say Y.
 
-config MMC_SDHCI_OF
-	tristate "SDHCI support on OpenFirmware platforms"
-	depends on MMC_SDHCI && OF
+config MMC_SDHCI_PLTFM
+	tristate "SDHCI platform and OF driver helper"
+	depends on MMC_SDHCI
 	help
-	  This selects the OF support for Secure Digital Host Controller
-	  Interfaces.
+	  This selects the common helper functions support for Secure Digital
+	  Host Controller Interface based platform and OF drivers.
+
+	  If you have a controller with this interface, say Y or M here.
 
 	  If unsure, say N.
 
 config MMC_SDHCI_OF_ESDHC
-	bool "SDHCI OF support for the Freescale eSDHC controller"
-	depends on MMC_SDHCI_OF
+	tristate "SDHCI OF support for the Freescale eSDHC controller"
+	depends on MMC_SDHCI_PLTFM
 	depends on PPC_OF
 	select MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER
 	help
 	  This selects the Freescale eSDHC controller support.
 
+	  If you have a controller with this interface, say Y or M here.
+
 	  If unsure, say N.
 
 config MMC_SDHCI_OF_HLWD
-	bool "SDHCI OF support for the Nintendo Wii SDHCI controllers"
-	depends on MMC_SDHCI_OF
+	tristate "SDHCI OF support for the Nintendo Wii SDHCI controllers"
+	depends on MMC_SDHCI_PLTFM
 	depends on PPC_OF
 	select MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER
 	help
@@ -110,40 +114,36 @@ config MMC_SDHCI_OF_HLWD
 	  found in the "Hollywood" chipset of the Nintendo Wii video game
 	  console.
 
-	  If unsure, say N.
-
-config MMC_SDHCI_PLTFM
-	tristate "SDHCI support on the platform specific bus"
-	depends on MMC_SDHCI
-	help
-	  This selects the platform specific bus support for Secure Digital Host
-	  Controller Interface.
-
 	  If you have a controller with this interface, say Y or M here.
 
 	  If unsure, say N.
 
 config MMC_SDHCI_CNS3XXX
-	bool "SDHCI support on the Cavium Networks CNS3xxx SoC"
+	tristate "SDHCI support on the Cavium Networks CNS3xxx SoC"
 	depends on ARCH_CNS3XXX
 	depends on MMC_SDHCI_PLTFM
 	help
 	  This selects the SDHCI support for CNS3xxx System-on-Chip devices.
 
+	  If you have a controller with this interface, say Y or M here.
+
 	  If unsure, say N.
 
 config MMC_SDHCI_ESDHC_IMX
-	bool "SDHCI platform support for the Freescale eSDHC i.MX controller"
-	depends on MMC_SDHCI_PLTFM && (ARCH_MX25 || ARCH_MX35 || ARCH_MX5)
+	tristate "SDHCI platform support for the Freescale eSDHC i.MX controller"
+	depends on ARCH_MX25 || ARCH_MX35 || ARCH_MX5
+	depends on MMC_SDHCI_PLTFM
 	select MMC_SDHCI_IO_ACCESSORS
 	help
 	  This selects the Freescale eSDHC controller support on the platform
 	  bus, found on platforms like mx35/51.
 
+	  If you have a controller with this interface, say Y or M here.
+
 	  If unsure, say N.
 
 config MMC_SDHCI_DOVE
-	bool "SDHCI support on Marvell's Dove SoC"
+	tristate "SDHCI support on Marvell's Dove SoC"
 	depends on ARCH_DOVE
 	depends on MMC_SDHCI_PLTFM
 	select MMC_SDHCI_IO_ACCESSORS
@@ -151,11 +151,14 @@ config MMC_SDHCI_DOVE
 	  This selects the Secure Digital Host Controller Interface in
 	  Marvell's Dove SoC.
 
+	  If you have a controller with this interface, say Y or M here.
+
 	  If unsure, say N.
 
 config MMC_SDHCI_TEGRA
-	bool "SDHCI platform support for the Tegra SD/MMC Controller"
-	depends on MMC_SDHCI_PLTFM && ARCH_TEGRA
+	tristate "SDHCI platform support for the Tegra SD/MMC Controller"
+	depends on ARCH_TEGRA
+	depends on MMC_SDHCI_PLTFM
 	select MMC_SDHCI_IO_ACCESSORS
 	help
 	  This selects the Tegra SD/MMC controller. If you have a Tegra
@@ -178,14 +181,28 @@ config MMC_SDHCI_S3C
 
 	  If unsure, say N.
 
-config MMC_SDHCI_PXA
-	tristate "Marvell PXA168/PXA910/MMP2 SD Host Controller support"
-	depends on ARCH_PXA || ARCH_MMP
+config MMC_SDHCI_PXAV3
+	tristate "Marvell MMP2 SD Host Controller support (PXAV3)"
+	depends on CLKDEV_LOOKUP
 	select MMC_SDHCI
-	select MMC_SDHCI_IO_ACCESSORS
+	select MMC_SDHCI_PLTFM
+	default CPU_MMP2
+	help
+	  This selects the Marvell(R) PXAV3 SD Host Controller.
+	  If you have a MMP2 platform with SD Host Controller
+	  and a card slot, say Y or M here.
+
+	  If unsure, say N.
+
+config MMC_SDHCI_PXAV2
+	tristate "Marvell PXA9XX SD Host Controller support (PXAV2)"
+	depends on CLKDEV_LOOKUP
+	select MMC_SDHCI
+	select MMC_SDHCI_PLTFM
+	default CPU_PXA910
 	help
-	  This selects the Marvell(R) PXA168/PXA910/MMP2 SD Host Controller.
-	  If you have a PXA168/PXA910/MMP2 platform with SD Host Controller
+	  This selects the Marvell(R) PXAV2 SD Host Controller.
+	  If you have a PXA9XX platform with SD Host Controller
 	  and a card slot, say Y or M here.
 
 	  If unsure, say N.
@@ -281,13 +298,12 @@ config MMC_ATMELMCI
 endchoice
 
 config MMC_ATMELMCI_DMA
-	bool "Atmel MCI DMA support (EXPERIMENTAL)"
-	depends on MMC_ATMELMCI && (AVR32 || ARCH_AT91SAM9G45) && DMA_ENGINE && EXPERIMENTAL
+	bool "Atmel MCI DMA support"
+	depends on MMC_ATMELMCI && (AVR32 || ARCH_AT91SAM9G45) && DMA_ENGINE
 	help
 	  Say Y here to have the Atmel MCI driver use a DMA engine to
 	  do data transfers and thus increase the throughput and
-	  reduce the CPU utilization. Note that this is highly
-	  experimental and may cause the driver to lock up.
+	  reduce the CPU utilization.
 
 	  If unsure, say N.
 

drivers/mmc/host/Makefile

@@ -9,7 +9,8 @@ obj-$(CONFIG_MMC_MXC)		+= mxcmmc.o
 obj-$(CONFIG_MMC_MXS)		+= mxs-mmc.o
 obj-$(CONFIG_MMC_SDHCI)		+= sdhci.o
 obj-$(CONFIG_MMC_SDHCI_PCI)	+= sdhci-pci.o
-obj-$(CONFIG_MMC_SDHCI_PXA)	+= sdhci-pxa.o
+obj-$(CONFIG_MMC_SDHCI_PXAV3)	+= sdhci-pxav3.o
+obj-$(CONFIG_MMC_SDHCI_PXAV2)	+= sdhci-pxav2.o
 obj-$(CONFIG_MMC_SDHCI_S3C)	+= sdhci-s3c.o
 obj-$(CONFIG_MMC_SDHCI_SPEAR)	+= sdhci-spear.o
 obj-$(CONFIG_MMC_WBSD)		+= wbsd.o
@@ -31,9 +32,7 @@ obj-$(CONFIG_MMC_SDRICOH_CS)	+= sdricoh_cs.o
 obj-$(CONFIG_MMC_TMIO)		+= tmio_mmc.o
 obj-$(CONFIG_MMC_TMIO_CORE)	+= tmio_mmc_core.o
 tmio_mmc_core-y			:= tmio_mmc_pio.o
-ifneq ($(CONFIG_MMC_SDHI),n)
-tmio_mmc_core-y			+= tmio_mmc_dma.o
-endif
+tmio_mmc_core-$(subst m,y,$(CONFIG_MMC_SDHI))	+= tmio_mmc_dma.o
 obj-$(CONFIG_MMC_SDHI)		+= sh_mobile_sdhi.o
 obj-$(CONFIG_MMC_CB710)		+= cb710-mmc.o
 obj-$(CONFIG_MMC_VIA_SDMMC)	+= via-sdmmc.o
@@ -44,17 +43,13 @@ obj-$(CONFIG_MMC_JZ4740)	+= jz4740_mmc.o
 obj-$(CONFIG_MMC_VUB300)	+= vub300.o
 obj-$(CONFIG_MMC_USHC)		+= ushc.o
 
-obj-$(CONFIG_MMC_SDHCI_PLTFM)			+= sdhci-platform.o
-sdhci-platform-y				:= sdhci-pltfm.o
-sdhci-platform-$(CONFIG_MMC_SDHCI_CNS3XXX)	+= sdhci-cns3xxx.o
-sdhci-platform-$(CONFIG_MMC_SDHCI_ESDHC_IMX)	+= sdhci-esdhc-imx.o
-sdhci-platform-$(CONFIG_MMC_SDHCI_DOVE)		+= sdhci-dove.o
-sdhci-platform-$(CONFIG_MMC_SDHCI_TEGRA)	+= sdhci-tegra.o
-
-obj-$(CONFIG_MMC_SDHCI_OF)	+= sdhci-of.o
-sdhci-of-y				:= sdhci-of-core.o
-sdhci-of-$(CONFIG_MMC_SDHCI_OF_ESDHC)	+= sdhci-of-esdhc.o
-sdhci-of-$(CONFIG_MMC_SDHCI_OF_HLWD)	+= sdhci-of-hlwd.o
+obj-$(CONFIG_MMC_SDHCI_PLTFM)		+= sdhci-pltfm.o
+obj-$(CONFIG_MMC_SDHCI_CNS3XXX)		+= sdhci-cns3xxx.o
+obj-$(CONFIG_MMC_SDHCI_ESDHC_IMX)	+= sdhci-esdhc-imx.o
+obj-$(CONFIG_MMC_SDHCI_DOVE)		+= sdhci-dove.o
+obj-$(CONFIG_MMC_SDHCI_TEGRA)		+= sdhci-tegra.o
+obj-$(CONFIG_MMC_SDHCI_OF_ESDHC)	+= sdhci-of-esdhc.o
+obj-$(CONFIG_MMC_SDHCI_OF_HLWD)		+= sdhci-of-hlwd.o
 
 ifeq ($(CONFIG_CB710_DEBUG),y)
 	CFLAGS-cb710-mmc	+= -DDEBUG

drivers/mmc/host/at91_mci.c

@@ -77,7 +77,8 @@
 
 #include <mach/board.h>
 #include <mach/cpu.h>
-#include <mach/at91_mci.h>
+
+#include "at91_mci.h"
 
 #define DRIVER_NAME "at91_mci"
 

arch/arm/mach-at91/include/mach/at91_mci.h → drivers/mmc/host/at91_mci.h

 /*
- * arch/arm/mach-at91/include/mach/at91_mci.h
+ * drivers/mmc/host/at91_mci.h
  *
  * Copyright (C) 2005 Ivan Kokshaysky
  * Copyright (C) SAN People

drivers/mmc/host/atmel-mci.c

@@ -203,6 +203,7 @@ struct atmel_mci_slot {
 #define ATMCI_CARD_PRESENT	0
 #define ATMCI_CARD_NEED_INIT	1
 #define ATMCI_SHUTDOWN		2
+#define ATMCI_SUSPENDED		3
 
 	int			detect_pin;
 	int			wp_pin;
@@ -1878,10 +1879,72 @@ static int __exit atmci_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int atmci_suspend(struct device *dev)
+{
+	struct atmel_mci *host = dev_get_drvdata(dev);
+	int i;
+
+	 for (i = 0; i < ATMEL_MCI_MAX_NR_SLOTS; i++) {
+		struct atmel_mci_slot *slot = host->slot[i];
+		int ret;
+
+		if (!slot)
+			continue;
+		ret = mmc_suspend_host(slot->mmc);
+		if (ret < 0) {
+			while (--i >= 0) {
+				slot = host->slot[i];
+				if (slot
+				&& test_bit(ATMCI_SUSPENDED, &slot->flags)) {
+					mmc_resume_host(host->slot[i]->mmc);
+					clear_bit(ATMCI_SUSPENDED, &slot->flags);
+				}
+			}
+			return ret;
+		} else {
+			set_bit(ATMCI_SUSPENDED, &slot->flags);
+		}
+	}
+
+	return 0;
+}
+
+static int atmci_resume(struct device *dev)
+{
+	struct atmel_mci *host = dev_get_drvdata(dev);
+	int i;
+	int ret = 0;
+
+	for (i = 0; i < ATMEL_MCI_MAX_NR_SLOTS; i++) {
+		struct atmel_mci_slot *slot = host->slot[i];
+		int err;
+
+		slot = host->slot[i];
+		if (!slot)
+			continue;
+		if (!test_bit(ATMCI_SUSPENDED, &slot->flags))
+			continue;
+		err = mmc_resume_host(slot->mmc);
+		if (err < 0)
+			ret = err;
+		else
+			clear_bit(ATMCI_SUSPENDED, &slot->flags);
+	}
+
+	return ret;
+}
+static SIMPLE_DEV_PM_OPS(atmci_pm, atmci_suspend, atmci_resume);
+#define ATMCI_PM_OPS	(&atmci_pm)
+#else
+#define ATMCI_PM_OPS	NULL
+#endif
+
 static struct platform_driver atmci_driver = {
 	.remove		= __exit_p(atmci_remove),
 	.driver		= {
 		.name		= "atmel_mci",
+		.pm		= ATMCI_PM_OPS,
 	},
 };
 

drivers/mmc/host/dw_mmc.h

@@ -118,7 +118,6 @@
 #define SDMMC_CMD_INDX(n)		((n) & 0x1F)
 /* Status register defines */
 #define SDMMC_GET_FCNT(x)		(((x)>>17) & 0x1FF)
-#define SDMMC_FIFO_SZ			32
 /* Internal DMAC interrupt defines */
 #define SDMMC_IDMAC_INT_AI		BIT(9)
 #define SDMMC_IDMAC_INT_NI		BIT(8)
@@ -134,22 +133,22 @@
 
 /* Register access macros */
 #define mci_readl(dev, reg)			\
-	__raw_readl(dev->regs + SDMMC_##reg)
+	__raw_readl((dev)->regs + SDMMC_##reg)
 #define mci_writel(dev, reg, value)			\
-	__raw_writel((value), dev->regs + SDMMC_##reg)
+	__raw_writel((value), (dev)->regs + SDMMC_##reg)
 
 /* 16-bit FIFO access macros */
 #define mci_readw(dev, reg)			\
-	__raw_readw(dev->regs + SDMMC_##reg)
+	__raw_readw((dev)->regs + SDMMC_##reg)
 #define mci_writew(dev, reg, value)			\
-	__raw_writew((value), dev->regs + SDMMC_##reg)
+	__raw_writew((value), (dev)->regs + SDMMC_##reg)
 
 /* 64-bit FIFO access macros */
 #ifdef readq
 #define mci_readq(dev, reg)			\
-	__raw_readq(dev->regs + SDMMC_##reg)
+	__raw_readq((dev)->regs + SDMMC_##reg)
 #define mci_writeq(dev, reg, value)			\
-	__raw_writeq((value), dev->regs + SDMMC_##reg)
+	__raw_writeq((value), (dev)->regs + SDMMC_##reg)
 #else
 /*
  * Dummy readq implementation for architectures that don't define it.
@@ -160,9 +159,9 @@
  * rest of the code free from ifdefs.
  */
 #define mci_readq(dev, reg)			\
-	(*(volatile u64 __force *)(dev->regs + SDMMC_##reg))
+	(*(volatile u64 __force *)((dev)->regs + SDMMC_##reg))
 #define mci_writeq(dev, reg, value)			\
-	(*(volatile u64 __force *)(dev->regs + SDMMC_##reg) = value)
+	(*(volatile u64 __force *)((dev)->regs + SDMMC_##reg) = (value))
 #endif
 
 #endif /* _DW_MMC_H_ */

drivers/mmc/host/mmci.c

@@ -226,6 +226,9 @@ static void __devinit mmci_dma_setup(struct mmci_host *host)
 		return;
 	}
 
+	/* initialize pre request cookie */
+	host->next_data.cookie = 1;
+
 	/* Try to acquire a generic DMA engine slave channel */
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
@@ -335,6 +338,7 @@ static void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data)
 		dir = DMA_FROM_DEVICE;
 	}
 
+	if (!data->host_cookie)
 		dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir);
 
 	/*
@@ -353,7 +357,8 @@ static void mmci_dma_data_error(struct mmci_host *host)
 	dmaengine_terminate_all(host->dma_current);
 }
 
-static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
+static int mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
+			      struct mmci_host_next *next)
 {
 	struct variant_data *variant = host->variant;
 	struct dma_slave_config conf = {
@@ -364,13 +369,20 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 		.src_maxburst = variant->fifohalfsize >> 2, /* # of words */
 		.dst_maxburst = variant->fifohalfsize >> 2, /* # of words */
 	};
-	struct mmc_data *data = host->data;
 	struct dma_chan *chan;
 	struct dma_device *device;
 	struct dma_async_tx_descriptor *desc;
 	int nr_sg;
 
+	/* Check if next job is already prepared */
+	if (data->host_cookie && !next &&
+	    host->dma_current && host->dma_desc_current)
+		return 0;
+
+	if (!next) {
 		host->dma_current = NULL;
+		host->dma_desc_current = NULL;
+	}
 
 	if (data->flags & MMC_DATA_READ) {
 		conf.direction = DMA_FROM_DEVICE;
@@ -385,7 +397,7 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 		return -EINVAL;
 
 	/* If less than or equal to the fifo size, don't bother with DMA */
-	if (host->size <= variant->fifosize)
+	if (data->blksz * data->blocks <= variant->fifosize)
 		return -EINVAL;
 
 	device = chan->device;
@@ -399,14 +411,38 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 	if (!desc)
 		goto unmap_exit;
 
-	/* Okay, go for it. */
+	if (next) {
+		next->dma_chan = chan;
+		next->dma_desc = desc;
+	} else {
 		host->dma_current = chan;
+		host->dma_desc_current = desc;
+	}
+
+	return 0;
+
+ unmap_exit:
+	if (!next)
+		dmaengine_terminate_all(chan);
+	dma_unmap_sg(device->dev, data->sg, data->sg_len, conf.direction);
+	return -ENOMEM;
+}
+
+static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
+{
+	int ret;
+	struct mmc_data *data = host->data;
 
+	ret = mmci_dma_prep_data(host, host->data, NULL);
+	if (ret)
+		return ret;
+
+	/* Okay, go for it. */
 	dev_vdbg(mmc_dev(host->mmc),
 		 "Submit MMCI DMA job, sglen %d blksz %04x blks %04x flags %08x\n",
 		 data->sg_len, data->blksz, data->blocks, data->flags);
-	dmaengine_submit(desc);
-	dma_async_issue_pending(chan);
+	dmaengine_submit(host->dma_desc_current);
+	dma_async_issue_pending(host->dma_current);
 
 	datactrl |= MCI_DPSM_DMAENABLE;
 
@@ -421,14 +457,90 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 	writel(readl(host->base + MMCIMASK0) | MCI_DATAENDMASK,
 	       host->base + MMCIMASK0);
 	return 0;
+}
+
+static void mmci_get_next_data(struct mmci_host *host, struct mmc_data *data)
+{
+	struct mmci_host_next *next = &host->next_data;
+
+	if (data->host_cookie && data->host_cookie != next->cookie) {
+		printk(KERN_WARNING "[%s] invalid cookie: data->host_cookie %d"
+		       " host->next_data.cookie %d\n",
+		       __func__, data->host_cookie, host->next_data.cookie);
+		data->host_cookie = 0;
+	}
+
+	if (!data->host_cookie)
+		return;
+
+	host->dma_desc_current = next->dma_desc;
+	host->dma_current = next->dma_chan;
+
+	next->dma_desc = NULL;
+	next->dma_chan = NULL;
+}
+
+static void mmci_pre_request(struct mmc_host *mmc, struct mmc_request *mrq,
+			     bool is_first_req)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+	struct mmci_host_next *nd = &host->next_data;
+
+	if (!data)
+		return;
+
+	if (data->host_cookie) {
+		data->host_cookie = 0;
+		return;
+	}
+
+	/* if config for dma */
+	if (((data->flags & MMC_DATA_WRITE) && host->dma_tx_channel) ||
+	    ((data->flags & MMC_DATA_READ) && host->dma_rx_channel)) {
+		if (mmci_dma_prep_data(host, data, nd))
+			data->host_cookie = 0;
+		else
+			data->host_cookie = ++nd->cookie < 0 ? 1 : nd->cookie;
+	}
+}
+
+static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq,
+			      int err)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+	struct dma_chan *chan;
+	enum dma_data_direction dir;
+
+	if (!data)
+		return;
 
-unmap_exit:
+	if (data->flags & MMC_DATA_READ) {
+		dir = DMA_FROM_DEVICE;
+		chan = host->dma_rx_channel;
+	} else {
+		dir = DMA_TO_DEVICE;
+		chan = host->dma_tx_channel;
+	}
+
+
+	/* if config for dma */
+	if (chan) {
+		if (err)
 			dmaengine_terminate_all(chan);
-	dma_unmap_sg(device->dev, data->sg, data->sg_len, conf.direction);
-	return -ENOMEM;
+		if (err || data->host_cookie)
+			dma_unmap_sg(mmc_dev(host->mmc), data->sg,
+				     data->sg_len, dir);
+		mrq->data->host_cookie = 0;
+	}
 }
+
 #else
 /* Blank functions if the DMA engine is not available */
+static void mmci_get_next_data(struct mmci_host *host, struct mmc_data *data)
+{
+}
 static inline void mmci_dma_setup(struct mmci_host *host)
 {
 }
@@ -449,6 +561,10 @@ static inline int mmci_dma_start_data(struct mmci_host *host, unsigned int datac
 {
 	return -ENOSYS;
 }
+
+#define mmci_pre_request NULL
+#define mmci_post_request NULL
+
 #endif
 
 static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
@@ -872,6 +988,9 @@ static void mmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	host->mrq = mrq;
 
+	if (mrq->data)
+		mmci_get_next_data(host, mrq->data);
+
 	if (mrq->data && mrq->data->flags & MMC_DATA_READ)
 		mmci_start_data(host, mrq->data);
 
@@ -986,6 +1105,8 @@ static irqreturn_t mmci_cd_irq(int irq, void *dev_id)
 
 static const struct mmc_host_ops mmci_ops = {
 	.request	= mmci_request,
+	.pre_req	= mmci_pre_request,
+	.post_req	= mmci_post_request,
 	.set_ios	= mmci_set_ios,
 	.get_ro		= mmci_get_ro,
 	.get_cd		= mmci_get_cd,

drivers/mmc/host/mmci.h

@@ -166,6 +166,12 @@ struct clk;
 struct variant_data;
 struct dma_chan;
 
+struct mmci_host_next {
+	struct dma_async_tx_descriptor	*dma_desc;
+	struct dma_chan			*dma_chan;
+	s32				cookie;
+};
+
 struct mmci_host {
 	phys_addr_t		phybase;
 	void __iomem		*base;
@@ -203,6 +209,8 @@ struct mmci_host {
 	struct dma_chan		*dma_current;
 	struct dma_chan		*dma_rx_channel;
 	struct dma_chan		*dma_tx_channel;
+	struct dma_async_tx_descriptor	*dma_desc_current;
+	struct mmci_host_next	next_data;
 
 #define dma_inprogress(host)	((host)->dma_current)
 #else

drivers/mmc/host/mxs-mmc.c

@@ -564,40 +564,38 @@ static void mxs_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 static void mxs_mmc_set_clk_rate(struct mxs_mmc_host *host, unsigned int rate)
 {
-	unsigned int ssp_rate, bit_rate;
-	u32 div1, div2;
+	unsigned int ssp_clk, ssp_sck;
+	u32 clock_divide, clock_rate;
 	u32 val;
 
-	ssp_rate = clk_get_rate(host->clk);
+	ssp_clk = clk_get_rate(host->clk);
 
-	for (div1 = 2; div1 < 254; div1 += 2) {
-		div2 = ssp_rate / rate / div1;
-		if (div2 < 0x100)
+	for (clock_divide = 2; clock_divide <= 254; clock_divide += 2) {
+		clock_rate = DIV_ROUND_UP(ssp_clk, rate * clock_divide);
+		clock_rate = (clock_rate > 0) ? clock_rate - 1 : 0;
+		if (clock_rate <= 255)
 			break;
 	}
 
-	if (div1 >= 254) {
+	if (clock_divide > 254) {
 		dev_err(mmc_dev(host->mmc),
 			"%s: cannot set clock to %d\n", __func__, rate);
 		return;
 	}
 
-	if (div2 == 0)
-		bit_rate = ssp_rate / div1;
-	else
-		bit_rate = ssp_rate / div1 / div2;
+	ssp_sck = ssp_clk / clock_divide / (1 + clock_rate);
 
 	val = readl(host->base + HW_SSP_TIMING);
 	val &= ~(BM_SSP_TIMING_CLOCK_DIVIDE | BM_SSP_TIMING_CLOCK_RATE);
-	val |= BF_SSP(div1, TIMING_CLOCK_DIVIDE);
-	val |= BF_SSP(div2 - 1, TIMING_CLOCK_RATE);
+	val |= BF_SSP(clock_divide, TIMING_CLOCK_DIVIDE);
+	val |= BF_SSP(clock_rate, TIMING_CLOCK_RATE);
 	writel(val, host->base + HW_SSP_TIMING);
 
-	host->clk_rate = bit_rate;
+	host->clk_rate = ssp_sck;
 
 	dev_dbg(mmc_dev(host->mmc),
-		"%s: div1 %d, div2 %d, ssp %d, bit %d, rate %d\n",
-		__func__, div1, div2, ssp_rate, bit_rate, rate);
+		"%s: clock_divide %d, clock_rate %d, ssp_clk %d, rate_actual %d, rate_requested %d\n",
+		__func__, clock_divide, clock_rate, ssp_clk, ssp_sck, rate);
 }
 
 static void mxs_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)

drivers/mmc/host/sdhci-cns3xxx.c

@@ -15,9 +15,7 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/mmc/host.h>
-#include <linux/mmc/sdhci-pltfm.h>
 #include <mach/cns3xxx.h>
-#include "sdhci.h"
 #include "sdhci-pltfm.h"
 
 static unsigned int sdhci_cns3xxx_get_max_clk(struct sdhci_host *host)
@@ -86,7 +84,7 @@ static struct sdhci_ops sdhci_cns3xxx_ops = {
 	.set_clock	= sdhci_cns3xxx_set_clock,
 };
 
-struct sdhci_pltfm_data sdhci_cns3xxx_pdata = {
+static struct sdhci_pltfm_data sdhci_cns3xxx_pdata = {
 	.ops = &sdhci_cns3xxx_ops,
 	.quirks = SDHCI_QUIRK_BROKEN_DMA |
 		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
@@ -95,3 +93,43 @@ struct sdhci_pltfm_data sdhci_cns3xxx_pdata = {
 		  SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
 		  SDHCI_QUIRK_NONSTANDARD_CLOCK,
 };
+
+static int __devinit sdhci_cns3xxx_probe(struct platform_device *pdev)
+{
+	return sdhci_pltfm_register(pdev, &sdhci_cns3xxx_pdata);
+}
+
+static int __devexit sdhci_cns3xxx_remove(struct platform_device *pdev)
+{
+	return sdhci_pltfm_unregister(pdev);
+}
+
+static struct platform_driver sdhci_cns3xxx_driver = {
+	.driver		= {
+		.name	= "sdhci-cns3xxx",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= sdhci_cns3xxx_probe,
+	.remove		= __devexit_p(sdhci_cns3xxx_remove),
+#ifdef CONFIG_PM
+	.suspend	= sdhci_pltfm_suspend,
+	.resume		= sdhci_pltfm_resume,
+#endif
+};
+
+static int __init sdhci_cns3xxx_init(void)
+{
+	return platform_driver_register(&sdhci_cns3xxx_driver);
+}
+module_init(sdhci_cns3xxx_init);
+
+static void __exit sdhci_cns3xxx_exit(void)
+{
+	platform_driver_unregister(&sdhci_cns3xxx_driver);
+}
+module_exit(sdhci_cns3xxx_exit);
+
+MODULE_DESCRIPTION("SDHCI driver for CNS3xxx");
+MODULE_AUTHOR("Scott Shu, "
+	      "Anton Vorontsov <avorontsov@mvista.com>");
+MODULE_LICENSE("GPL v2");

drivers/mmc/host/sdhci-dove.c

@@ -22,7 +22,6 @@
 #include <linux/io.h>
 #include <linux/mmc/host.h>
 
-#include "sdhci.h"
 #include "sdhci-pltfm.h"
 
 static u16 sdhci_dove_readw(struct sdhci_host *host, int reg)
@@ -61,10 +60,50 @@ static struct sdhci_ops sdhci_dove_ops = {
 	.read_l	= sdhci_dove_readl,
 };
 
-struct sdhci_pltfm_data sdhci_dove_pdata = {
+static struct sdhci_pltfm_data sdhci_dove_pdata = {
 	.ops	= &sdhci_dove_ops,
 	.quirks	= SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER |
 		  SDHCI_QUIRK_NO_BUSY_IRQ |
 		  SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
 		  SDHCI_QUIRK_FORCE_DMA,
 };
+
+static int __devinit sdhci_dove_probe(struct platform_device *pdev)
+{
+	return sdhci_pltfm_register(pdev, &sdhci_dove_pdata);
+}
+
+static int __devexit sdhci_dove_remove(struct platform_device *pdev)
+{
+	return sdhci_pltfm_unregister(pdev);
+}
+
+static struct platform_driver sdhci_dove_driver = {
+	.driver		= {
+		.name	= "sdhci-dove",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= sdhci_dove_probe,
+	.remove		= __devexit_p(sdhci_dove_remove),
+#ifdef CONFIG_PM
+	.suspend	= sdhci_pltfm_suspend,
+	.resume		= sdhci_pltfm_resume,
+#endif
+};
+
+static int __init sdhci_dove_init(void)
+{
+	return platform_driver_register(&sdhci_dove_driver);
+}
+module_init(sdhci_dove_init);
+
+static void __exit sdhci_dove_exit(void)
+{
+	platform_driver_unregister(&sdhci_dove_driver);
+}
+module_exit(sdhci_dove_exit);
+
+MODULE_DESCRIPTION("SDHCI driver for Dove");
+MODULE_AUTHOR("Saeed Bishara <saeed@marvell.com>, "
+	      "Mike Rapoport <mike@compulab.co.il>");
+MODULE_LICENSE("GPL v2");

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

@@ -18,12 +18,10 @@
 #include <linux/gpio.h>
 #include <linux/slab.h>
 #include <linux/mmc/host.h>
-#include <linux/mmc/sdhci-pltfm.h>
 #include <linux/mmc/mmc.h>
 #include <linux/mmc/sdio.h>
 #include <mach/hardware.h>
 #include <mach/esdhc.h>
-#include "sdhci.h"
 #include "sdhci-pltfm.h"
 #include "sdhci-esdhc.h"
 
@@ -31,7 +29,7 @@
 #define SDHCI_VENDOR_SPEC		0xC0
 #define  SDHCI_VENDOR_SPEC_SDIO_QUIRK	0x00000002
 
-#define ESDHC_FLAG_GPIO_FOR_CD_WP	(1 << 0)
+#define ESDHC_FLAG_GPIO_FOR_CD		(1 << 0)
 /*
  * The CMDTYPE of the CMD register (offset 0xE) should be set to
  * "11" when the STOP CMD12 is issued on imx53 to abort one
@@ -67,14 +65,14 @@ static u32 esdhc_readl_le(struct sdhci_host *host, int reg)
 	u32 val = readl(host->ioaddr + reg);
 
 	if (unlikely((reg == SDHCI_PRESENT_STATE)
-			&& (imx_data->flags & ESDHC_FLAG_GPIO_FOR_CD_WP))) {
+			&& (imx_data->flags & ESDHC_FLAG_GPIO_FOR_CD))) {
 		struct esdhc_platform_data *boarddata =
 				host->mmc->parent->platform_data;
 
 		if (boarddata && gpio_is_valid(boarddata->cd_gpio)
 				&& gpio_get_value(boarddata->cd_gpio))
 			/* no card, if a valid gpio says so... */
-			val &= SDHCI_CARD_PRESENT;
+			val &= ~SDHCI_CARD_PRESENT;
 		else
 			/* ... in all other cases assume card is present */
 			val |= SDHCI_CARD_PRESENT;
@@ -89,7 +87,7 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
 	struct pltfm_imx_data *imx_data = pltfm_host->priv;
 
 	if (unlikely((reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE)
-			&& (imx_data->flags & ESDHC_FLAG_GPIO_FOR_CD_WP)))
+			&& (imx_data->flags & ESDHC_FLAG_GPIO_FOR_CD)))
 		/*
 		 * these interrupts won't work with a custom card_detect gpio
 		 * (only applied to mx25/35)
@@ -191,16 +189,6 @@ static unsigned int esdhc_pltfm_get_min_clock(struct sdhci_host *host)
 	return clk_get_rate(pltfm_host->clk) / 256 / 16;
 }
 
-static unsigned int esdhc_pltfm_get_ro(struct sdhci_host *host)
-{
-	struct esdhc_platform_data *boarddata = host->mmc->parent->platform_data;
-
-	if (boarddata && gpio_is_valid(boarddata->wp_gpio))
-		return gpio_get_value(boarddata->wp_gpio);
-	else
-		return -ENOSYS;
-}
-
 static struct sdhci_ops sdhci_esdhc_ops = {
 	.read_l = esdhc_readl_le,
 	.read_w = esdhc_readw_le,
@@ -212,6 +200,24 @@ static struct sdhci_ops sdhci_esdhc_ops = {
 	.get_min_clock = esdhc_pltfm_get_min_clock,
 };
 
+static struct sdhci_pltfm_data sdhci_esdhc_imx_pdata = {
+	.quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_ADMA
+			| SDHCI_QUIRK_BROKEN_CARD_DETECTION,
+	/* ADMA has issues. Might be fixable */
+	.ops = &sdhci_esdhc_ops,
+};
+
+static unsigned int esdhc_pltfm_get_ro(struct sdhci_host *host)
+{
+	struct esdhc_platform_data *boarddata =
+			host->mmc->parent->platform_data;
+
+	if (boarddata && gpio_is_valid(boarddata->wp_gpio))
+		return gpio_get_value(boarddata->wp_gpio);
+	else
+		return -ENOSYS;
+}
+
 static irqreturn_t cd_irq(int irq, void *data)
 {
 	struct sdhci_host *sdhost = (struct sdhci_host *)data;
@@ -220,30 +226,35 @@ static irqreturn_t cd_irq(int irq, void *data)
 	return IRQ_HANDLED;
 };
 
-static int esdhc_pltfm_init(struct sdhci_host *host, struct sdhci_pltfm_data *pdata)
+static int __devinit sdhci_esdhc_imx_probe(struct platform_device *pdev)
 {
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct esdhc_platform_data *boarddata = host->mmc->parent->platform_data;
+	struct sdhci_pltfm_host *pltfm_host;
+	struct sdhci_host *host;
+	struct esdhc_platform_data *boarddata;
 	struct clk *clk;
 	int err;
 	struct pltfm_imx_data *imx_data;
 
+	host = sdhci_pltfm_init(pdev, &sdhci_esdhc_imx_pdata);
+	if (IS_ERR(host))
+		return PTR_ERR(host);
+
+	pltfm_host = sdhci_priv(host);
+
+	imx_data = kzalloc(sizeof(struct pltfm_imx_data), GFP_KERNEL);
+	if (!imx_data)
+		return -ENOMEM;
+	pltfm_host->priv = imx_data;
+
 	clk = clk_get(mmc_dev(host->mmc), NULL);
 	if (IS_ERR(clk)) {
 		dev_err(mmc_dev(host->mmc), "clk err\n");
-		return PTR_ERR(clk);
+		err = PTR_ERR(clk);
+		goto err_clk_get;
 	}
 	clk_enable(clk);
 	pltfm_host->clk = clk;
 
-	imx_data = kzalloc(sizeof(struct pltfm_imx_data), GFP_KERNEL);
-	if (!imx_data) {
-		clk_disable(pltfm_host->clk);
-		clk_put(pltfm_host->clk);
-		return -ENOMEM;
-	}
-	pltfm_host->priv = imx_data;
-
 	if (!cpu_is_mx25())
 		host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL;
 
@@ -257,6 +268,7 @@ static int esdhc_pltfm_init(struct sdhci_host *host, struct sdhci_pltfm_data *pd
 	if (!(cpu_is_mx25() || cpu_is_mx35() || cpu_is_mx51()))
 		imx_data->flags |= ESDHC_FLAG_MULTIBLK_NO_INT;
 
+	boarddata = host->mmc->parent->platform_data;
 	if (boarddata) {
 		err = gpio_request_one(boarddata->wp_gpio, GPIOF_IN, "ESDHC_WP");
 		if (err) {
@@ -284,11 +296,15 @@ static int esdhc_pltfm_init(struct sdhci_host *host, struct sdhci_pltfm_data *pd
 			goto no_card_detect_irq;
 		}
 
-		imx_data->flags |= ESDHC_FLAG_GPIO_FOR_CD_WP;
+		imx_data->flags |= ESDHC_FLAG_GPIO_FOR_CD;
 		/* Now we have a working card_detect again */
 		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
 	}
 
+	err = sdhci_add_host(host);
+	if (err)
+		goto err_add_host;
+
 	return 0;
 
  no_card_detect_irq:
@@ -297,14 +313,23 @@ static int esdhc_pltfm_init(struct sdhci_host *host, struct sdhci_pltfm_data *pd
 	boarddata->cd_gpio = err;
  not_supported:
 	kfree(imx_data);
-	return 0;
+ err_add_host:
+	clk_disable(pltfm_host->clk);
+	clk_put(pltfm_host->clk);
+ err_clk_get:
+	sdhci_pltfm_free(pdev);
+	return err;
 }
 
-static void esdhc_pltfm_exit(struct sdhci_host *host)
+static int __devexit sdhci_esdhc_imx_remove(struct platform_device *pdev)
 {
+	struct sdhci_host *host = platform_get_drvdata(pdev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct esdhc_platform_data *boarddata = host->mmc->parent->platform_data;
 	struct pltfm_imx_data *imx_data = pltfm_host->priv;
+	int dead = (readl(host->ioaddr + SDHCI_INT_STATUS) == 0xffffffff);
+
+	sdhci_remove_host(host, dead);
 
 	if (boarddata && gpio_is_valid(boarddata->wp_gpio))
 		gpio_free(boarddata->wp_gpio);
@@ -319,13 +344,37 @@ static void esdhc_pltfm_exit(struct sdhci_host *host)
 	clk_disable(pltfm_host->clk);
 	clk_put(pltfm_host->clk);
 	kfree(imx_data);
+
+	sdhci_pltfm_free(pdev);
+
+	return 0;
 }
 
-struct sdhci_pltfm_data sdhci_esdhc_imx_pdata = {
-	.quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_ADMA
-			| SDHCI_QUIRK_BROKEN_CARD_DETECTION,
-	/* ADMA has issues. Might be fixable */
-	.ops = &sdhci_esdhc_ops,
-	.init = esdhc_pltfm_init,
-	.exit = esdhc_pltfm_exit,
+static struct platform_driver sdhci_esdhc_imx_driver = {
+	.driver		= {
+		.name	= "sdhci-esdhc-imx",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= sdhci_esdhc_imx_probe,
+	.remove		= __devexit_p(sdhci_esdhc_imx_remove),
+#ifdef CONFIG_PM
+	.suspend	= sdhci_pltfm_suspend,
+	.resume		= sdhci_pltfm_resume,
+#endif
 };
+
+static int __init sdhci_esdhc_imx_init(void)
+{
+	return platform_driver_register(&sdhci_esdhc_imx_driver);
+}
+module_init(sdhci_esdhc_imx_init);
+
+static void __exit sdhci_esdhc_imx_exit(void)
+{
+	platform_driver_unregister(&sdhci_esdhc_imx_driver);
+}
+module_exit(sdhci_esdhc_imx_exit);
+
+MODULE_DESCRIPTION("SDHCI driver for Freescale i.MX eSDHC");
+MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>");
+MODULE_LICENSE("GPL v2");

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

@@ -21,8 +21,7 @@
 
 #include <linux/delay.h>
 #include <linux/mmc/host.h>
-#include "sdhci-of.h"
-#include "sdhci.h"
+#include "sdhci-pltfm.h"
 
 /*
  * Ops and quirks for the Nintendo Wii SDHCI controllers.
@@ -51,15 +50,63 @@ static void sdhci_hlwd_writeb(struct sdhci_host *host, u8 val, int reg)
 	udelay(SDHCI_HLWD_WRITE_DELAY);
 }
 
-struct sdhci_of_data sdhci_hlwd = {
-	.quirks = SDHCI_QUIRK_32BIT_DMA_ADDR |
-		  SDHCI_QUIRK_32BIT_DMA_SIZE,
-	.ops = {
+static struct sdhci_ops sdhci_hlwd_ops = {
 	.read_l = sdhci_be32bs_readl,
 	.read_w = sdhci_be32bs_readw,
 	.read_b = sdhci_be32bs_readb,
 	.write_l = sdhci_hlwd_writel,
 	.write_w = sdhci_hlwd_writew,
 	.write_b = sdhci_hlwd_writeb,
+};
+
+static struct sdhci_pltfm_data sdhci_hlwd_pdata = {
+	.quirks = SDHCI_QUIRK_32BIT_DMA_ADDR |
+		  SDHCI_QUIRK_32BIT_DMA_SIZE,
+	.ops = &sdhci_hlwd_ops,
+};
+
+static int __devinit sdhci_hlwd_probe(struct platform_device *pdev)
+{
+	return sdhci_pltfm_register(pdev, &sdhci_hlwd_pdata);
+}
+
+static int __devexit sdhci_hlwd_remove(struct platform_device *pdev)
+{
+	return sdhci_pltfm_unregister(pdev);
+}
+
+static const struct of_device_id sdhci_hlwd_of_match[] = {
+	{ .compatible = "nintendo,hollywood-sdhci" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sdhci_hlwd_of_match);
+
+static struct platform_driver sdhci_hlwd_driver = {
+	.driver = {
+		.name = "sdhci-hlwd",
+		.owner = THIS_MODULE,
+		.of_match_table = sdhci_hlwd_of_match,
 	},
+	.probe = sdhci_hlwd_probe,
+	.remove = __devexit_p(sdhci_hlwd_remove),
+#ifdef CONFIG_PM
+	.suspend = sdhci_pltfm_suspend,
+	.resume = sdhci_pltfm_resume,
+#endif
 };
+
+static int __init sdhci_hlwd_init(void)
+{
+	return platform_driver_register(&sdhci_hlwd_driver);
+}
+module_init(sdhci_hlwd_init);
+
+static void __exit sdhci_hlwd_exit(void)
+{
+	platform_driver_unregister(&sdhci_hlwd_driver);
+}
+module_exit(sdhci_hlwd_exit);
+
+MODULE_DESCRIPTION("Nintendo Wii SDHCI OF driver");
+MODULE_AUTHOR("The GameCube Linux Team, Albert Herranz");
+MODULE_LICENSE("GPL v2");

drivers/mmc/host/tmio_mmc_dma.c

@@ -22,11 +22,14 @@
 
 #define TMIO_MMC_MIN_DMA_LEN 8
 
-static void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable)
+void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable)
 {
+	if (!host->chan_tx || !host->chan_rx)
+		return;
+
 #if defined(CONFIG_SUPERH) || defined(CONFIG_ARCH_SHMOBILE)
 	/* Switch DMA mode on or off - SuperH specific? */
-	writew(enable ? 2 : 0, host->ctl + (0xd8 << host->bus_shift));
+	sd_ctrl_write16(host, CTL_DMA_ENABLE, enable ? 2 : 0);
 #endif
 }