Previously there has only been one function mmc_wait_for_req() to start and wait for a request. This patch adds * mmc_start_req() - starts a request wihtout waiting If there is on ongoing request wait for completion of that request and start the new one and return. Does not wait for the new command to complete.

This patch also adds new function members in struct mmc_host_ops only called from core.c * pre_req - asks the host driver to prepare for the next job * post_req - asks the host driver to clean up after a completed job

The intention is to use pre_req() and post_req() to do cache maintenance while a request is active. pre_req() can be called while a request is active to minimize latency to start next job. post_req() can be used after the next job is started to clean up the request. This will minimize the host driver request end latency. post_req() is typically used before ending the block request and handing over the buffer to the block layer.

Add a host-private member in mmc_data to be used by pre_req to mark the data. The host driver will then check this mark to see if the data is prepared or not.

Signed-off-by: Per Forlin per.forlin@linaro.org --- drivers/mmc/core/core.c | 111 +++++++++++++++++++++++++++++++++++++++++---- include/linux/mmc/core.h | 6 ++- include/linux/mmc/host.h | 21 +++++++++ 3 files changed, 127 insertions(+), 11 deletions(-)

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 68091dd..331c69e 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -198,10 +198,108 @@ 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: non zero in case of error + * + * 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 async request, NULL in case of none completed. + */ +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; + if (error) + *error = err; + return data; + } + } + + if (areq) + __mmc_start_req(host, areq->mrq); + + if (host->areq) + mmc_post_req(host, host->areq->mrq, 0); + + host->areq = areq; + 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 * @mrq: MMC request to start @@ -212,16 +310,9 @@ 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);

/** diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 791f060..57ee19e 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -117,6 +117,7 @@ struct mmc_data {

unsigned int sg_len; /* size of scatter list */ struct scatterlist *sg; /* I/O scatter list */ + s32 host_cookie; /* host private data */ };

struct mmc_request { @@ -125,13 +126,16 @@ struct mmc_request { struct mmc_data *data; struct mmc_command *stop;

- void *done_data; /* completion data */ + struct completion completion; void (*done)(struct mmc_request *);/* completion function */ };

struct mmc_host; struct mmc_card; +struct mmc_async_req;

+extern struct mmc_async_req *mmc_start_req(struct mmc_host *, + struct mmc_async_req *, int *); extern void mmc_wait_for_req(struct mmc_host *, struct mmc_request *); extern int mmc_wait_for_cmd(struct mmc_host *, struct mmc_command *, int); extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index ac3fbac..59db6f2 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -106,6 +106,15 @@ struct mmc_host_ops { */ int (*enable)(struct mmc_host *host); int (*disable)(struct mmc_host *host, int lazy); + /* + * It is optional for the host to implement pre_req and post_req in + * order to support double buffering of requests (prepare one + * request while another request is active). + */ + void (*post_req)(struct mmc_host *host, struct mmc_request *req, + int err); + void (*pre_req)(struct mmc_host *host, struct mmc_request *req, + bool is_first_req); void (*request)(struct mmc_host *host, struct mmc_request *req); /* * Avoid calling these three functions too often or in a "fast path", @@ -144,6 +153,16 @@ struct mmc_host_ops { struct mmc_card; struct device;

+struct mmc_async_req { + /* active mmc request */ + struct mmc_request *mrq; + /* + * Check error status of completed mmc request. + * Returns 0 if success otherwise non zero. + */ + int (*err_check) (struct mmc_card *, struct mmc_async_req *); +}; + struct mmc_host { struct device *parent; struct device class_dev; @@ -280,6 +299,8 @@ struct mmc_host {

struct dentry *debugfs_root;

+ struct mmc_async_req *areq; /* active async req */ + unsigned long private[0] ____cacheline_aligned; };

pre_req() runs dma_map_sg() and prepares the dma descriptor for the next mmc data transfer. post_req() runs dma_unmap_sg. If not calling pre_req() before mmci_request(), mmci_request() will prepare the cache and dma just like it did it before. It is optional to use pre_req() and post_req() for mmci.

Signed-off-by: Per Forlin per.forlin@linaro.org --- drivers/mmc/host/mmci.c | 146 ++++++++++++++++++++++++++++++++++++++++++---- drivers/mmc/host/mmci.h | 8 +++ 2 files changed, 141 insertions(+), 13 deletions(-)

diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index b4a7e4f..985c77d 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -320,7 +320,8 @@ static void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data) dir = DMA_FROM_DEVICE; }

- dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir); + if (!data->host_cookie) + dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir);

/* * Use of DMA with scatter-gather is impossible. @@ -338,7 +339,8 @@ 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 = { @@ -349,13 +351,20 @@ 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;

- host->dma_current = NULL; + /* 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; @@ -370,7 +379,7 @@ 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; @@ -384,14 +393,38 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl) if (!desc) goto unmap_exit;

- /* Okay, go for it. */ - host->dma_current = chan; + 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;

@@ -406,14 +439,90 @@ 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; +}

-unmap_exit: - dmaengine_terminate_all(chan); - dma_unmap_sg(device->dev, data->sg, data->sg_len, conf.direction); - return -ENOMEM; +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; + + 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); + 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) { } @@ -434,6 +543,10 @@ 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) @@ -852,6 +965,9 @@ 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);

@@ -966,6 +1082,8 @@ 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, @@ -1003,6 +1121,8 @@ static int __devinit mmci_probe(struct amba_device *dev, host->gpio_cd = -ENOSYS; host->gpio_cd_irq = -1;

+ host->next_data.cookie = 1; + host->hw_designer = amba_manf(dev); host->hw_revision = amba_rev(dev); dev_dbg(mmc_dev(mmc), "designer ID = 0x%02x\n", host->hw_designer); diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h index ec9a7bc6..e21d850 100644 --- a/drivers/mmc/host/mmci.h +++ b/drivers/mmc/host/mmci.h @@ -150,6 +150,12 @@ 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; @@ -187,6 +193,8 @@ 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

Add four tests for read and write performance per different transfer size, 4k to 4M. * Read using blocking mmc request * Read using non-blocking mmc request * Write using blocking mmc request * Write using non-blocking mmc request

The host dirver must support pre_req() and post_req() in order to run the non-blocking test cases.

Signed-off-by: Per Forlin per.forlin@linaro.org --- drivers/mmc/card/mmc_test.c | 322 +++++++++++++++++++++++++++++++++++++++++-- 1 files changed, 313 insertions(+), 9 deletions(-)

diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c index e8508e9..5325049 100644 --- a/drivers/mmc/card/mmc_test.c +++ b/drivers/mmc/card/mmc_test.c @@ -22,6 +22,7 @@ #include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/seq_file.h> +#include <linux/random.h>

#define RESULT_OK 0 #define RESULT_FAIL 1 @@ -51,10 +52,12 @@ struct mmc_test_pages { * struct mmc_test_mem - allocated memory. * @arr: array of allocations * @cnt: number of allocations + * @size_min_cmn: lowest common size in array of allocations */ struct mmc_test_mem { struct mmc_test_pages *arr; unsigned int cnt; + unsigned int size_min_cmn; };

/** @@ -148,6 +151,26 @@ struct mmc_test_card { struct mmc_test_general_result *gr; };

+enum mmc_test_prep_media { + MMC_TEST_PREP_NONE = 0, + MMC_TEST_PREP_WRITE_FULL = 1 << 0, + MMC_TEST_PREP_ERASE = 1 << 1, +}; + +struct mmc_test_multiple_rw { + unsigned int *bs; + unsigned int len; + unsigned int size; + bool do_write; + bool do_nonblock_req; + enum mmc_test_prep_media prepare; +}; + +struct mmc_test_async_req { + struct mmc_async_req areq; + struct mmc_test_card *test; +}; + /*******************************************************************/ /* General helper functions */ /*******************************************************************/ @@ -302,6 +325,7 @@ static struct mmc_test_mem *mmc_test_alloc_mem(unsigned long min_sz, unsigned long max_seg_page_cnt = DIV_ROUND_UP(max_seg_sz, PAGE_SIZE); unsigned long page_cnt = 0; unsigned long limit = nr_free_buffer_pages() >> 4; + unsigned int min_cmn = 0; struct mmc_test_mem *mem;

if (max_page_cnt > limit) @@ -345,6 +369,12 @@ static struct mmc_test_mem *mmc_test_alloc_mem(unsigned long min_sz, mem->arr[mem->cnt].page = page; mem->arr[mem->cnt].order = order; mem->cnt += 1; + if (!min_cmn) + min_cmn = PAGE_SIZE << order; + else + min_cmn = min(min_cmn, + (unsigned int) (PAGE_SIZE << order)); + if (max_page_cnt <= (1UL << order)) break; max_page_cnt -= 1UL << order; @@ -355,6 +385,7 @@ static struct mmc_test_mem *mmc_test_alloc_mem(unsigned long min_sz, break; } } + mem->size_min_cmn = min_cmn;

return mem;

@@ -381,7 +412,6 @@ static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long sz, do { for (i = 0; i < mem->cnt; i++) { unsigned long len = PAGE_SIZE << mem->arr[i].order; - if (len > sz) len = sz; if (len > max_seg_sz) @@ -661,7 +691,7 @@ static void mmc_test_prepare_broken_mrq(struct mmc_test_card *test, * Checks that a normal transfer didn't have any errors */ static int mmc_test_check_result(struct mmc_test_card *test, - struct mmc_request *mrq) + struct mmc_request *mrq) { int ret;

@@ -685,6 +715,16 @@ static int mmc_test_check_result(struct mmc_test_card *test, return ret; }

+ +static int mmc_test_check_result_async(struct mmc_card *card, + struct mmc_async_req *areq) +{ + struct mmc_test_async_req *test_async = + container_of(areq, struct mmc_test_async_req, areq); + + return mmc_test_check_result(test_async->test, areq->mrq); +} + /* * Checks that a "short transfer" behaved as expected */ @@ -720,6 +760,89 @@ static int mmc_test_check_broken_result(struct mmc_test_card *test, }

/* + * Tests nonblock transfer with certain parameters + */ +static void mmc_test_nonblock_reset(struct mmc_request *mrq, + struct mmc_command *cmd, + struct mmc_command *stop, + struct mmc_data *data) +{ + memset(mrq, 0, sizeof(struct mmc_request)); + memset(cmd, 0, sizeof(struct mmc_command)); + memset(data, 0, sizeof(struct mmc_data)); + memset(stop, 0, sizeof(struct mmc_command)); + + mrq->cmd = cmd; + mrq->data = data; + mrq->stop = stop; +} +static int mmc_test_nonblock_transfer(struct mmc_test_card *test, + struct scatterlist *sg, unsigned sg_len, + unsigned dev_addr, unsigned blocks, + unsigned blksz, int write, int count) +{ + struct mmc_request mrq1; + struct mmc_command cmd1; + struct mmc_command stop1; + struct mmc_data data1; + + struct mmc_request mrq2; + struct mmc_command cmd2; + struct mmc_command stop2; + struct mmc_data data2; + + struct mmc_test_async_req test_areq[2]; + struct mmc_async_req *done_areq; + struct mmc_async_req *cur_areq = &test_areq[0].areq; + struct mmc_async_req *other_areq = &test_areq[1].areq; + int i; + int ret; + + test_areq[0].test = test; + test_areq[1].test = test; + + if (!test->card->host->ops->pre_req || + !test->card->host->ops->post_req) + return -RESULT_UNSUP_HOST; + + mmc_test_nonblock_reset(&mrq1, &cmd1, &stop1, &data1); + mmc_test_nonblock_reset(&mrq2, &cmd2, &stop2, &data2); + + cur_areq->mrq = &mrq1; + cur_areq->err_check = mmc_test_check_result_async; + other_areq->mrq = &mrq2; + other_areq->err_check = mmc_test_check_result_async; + + for (i = 0; i < count; i++) { + mmc_test_prepare_mrq(test, cur_areq->mrq, sg, sg_len, dev_addr, + blocks, blksz, write); + done_areq = mmc_start_req(test->card->host, cur_areq, &ret); + + if (ret || (!done_areq && i > 0)) + goto err; + + if (done_areq) { + if (done_areq->mrq == &mrq2) + mmc_test_nonblock_reset(&mrq2, &cmd2, + &stop2, &data2); + else + mmc_test_nonblock_reset(&mrq1, &cmd1, + &stop1, &data1); + } + done_areq = cur_areq; + cur_areq = other_areq; + other_areq = done_areq; + dev_addr += blocks; + } + + done_areq = mmc_start_req(test->card->host, NULL, &ret); + + return ret; +err: + return ret; +} + +/* * Tests a basic transfer with certain parameters */ static int mmc_test_simple_transfer(struct mmc_test_card *test, @@ -1336,14 +1459,17 @@ static int mmc_test_area_transfer(struct mmc_test_card *test, }

/* - * Map and transfer bytes. + * Map and transfer bytes for multiple transfers. */ -static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz, - unsigned int dev_addr, int write, int max_scatter, - int timed) +static int mmc_test_area_io_seq(struct mmc_test_card *test, unsigned long sz, + unsigned int dev_addr, int write, + int max_scatter, int timed, int count, + bool nonblock) { struct timespec ts1, ts2; - int ret; + int ret = 0; + int i; + struct mmc_test_area *t = &test->area;

/* * In the case of a maximally scattered transfer, the maximum transfer @@ -1367,8 +1493,15 @@ static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz,

if (timed) getnstimeofday(&ts1); + if (nonblock) + ret = mmc_test_nonblock_transfer(test, t->sg, t->sg_len, + dev_addr, t->blocks, 512, write, count); + else + for (i = 0; i < count && ret == 0; i++) { + ret = mmc_test_area_transfer(test, dev_addr, write); + dev_addr += sz >> 9; + }

- ret = mmc_test_area_transfer(test, dev_addr, write); if (ret) return ret;

@@ -1376,11 +1509,19 @@ static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz, getnstimeofday(&ts2);

if (timed) - mmc_test_print_rate(test, sz, &ts1, &ts2); + mmc_test_print_avg_rate(test, sz, count, &ts1, &ts2);

return 0; }

+static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz, + unsigned int dev_addr, int write, int max_scatter, + int timed) +{ + return mmc_test_area_io_seq(test, sz, dev_addr, write, max_scatter, + timed, 1, false); +} + /* * Write the test area entirely. */ @@ -1954,6 +2095,142 @@ static int mmc_test_large_seq_write_perf(struct mmc_test_card *test) return mmc_test_large_seq_perf(test, 1); }

+static int mmc_test_rw_multiple(struct mmc_test_card *test, + struct mmc_test_multiple_rw *tdata, + unsigned int reqsize, unsigned int size) +{ + unsigned int dev_addr; + struct mmc_test_area *t = &test->area; + int ret = 0; + + /* Set up test area */ + if (size > mmc_test_capacity(test->card) / 2 * 512) + size = mmc_test_capacity(test->card) / 2 * 512; + if (reqsize > t->max_tfr) + reqsize = t->max_tfr; + dev_addr = mmc_test_capacity(test->card) / 4; + if ((dev_addr & 0xffff0000)) + dev_addr &= 0xffff0000; /* Round to 64MiB boundary */ + else + dev_addr &= 0xfffff800; /* Round to 1MiB boundary */ + if (!dev_addr) + goto err; + + /* prepare test area */ + if (mmc_can_erase(test->card) && + tdata->prepare & MMC_TEST_PREP_ERASE) { + ret = mmc_erase(test->card, dev_addr, + size / 512, MMC_SECURE_ERASE_ARG); + if (ret) + ret = mmc_erase(test->card, dev_addr, + size / 512, MMC_ERASE_ARG); + if (ret) + goto err; + } + + /* Run test */ + ret = mmc_test_area_io_seq(test, reqsize, dev_addr, + tdata->do_write, 0, 1, size / reqsize, + tdata->do_nonblock_req); + if (ret) + goto err; + + return ret; + err: + printk(KERN_INFO "[%s] error\n", __func__); + return ret; +} + +static int mmc_test_rw_multiple_size(struct mmc_test_card *test, + struct mmc_test_multiple_rw *rw) +{ + int ret = 0; + int i; + + for (i = 0 ; i < rw->len && ret == 0; i++) { + ret = mmc_test_rw_multiple(test, rw, rw->bs[i], rw->size); + if (ret) + break; + } + return ret; +} + +/* + * Multiple blocking write 4k to 4 MB chunks + */ +static int mmc_test_profile_mult_write_blocking_perf(struct mmc_test_card *test) +{ + unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, + 1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22}; + struct mmc_test_multiple_rw test_data = { + .bs = bs, + .size = 128*1024*1024, + .len = ARRAY_SIZE(bs), + .do_write = true, + .do_nonblock_req = false, + .prepare = MMC_TEST_PREP_ERASE, + }; + + return mmc_test_rw_multiple_size(test, &test_data); +}; + +/* + * Multiple non-blocking write 4k to 4 MB chunks + */ +static int mmc_test_profile_mult_write_nonblock_perf(struct mmc_test_card *test) +{ + unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, + 1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22}; + struct mmc_test_multiple_rw test_data = { + .bs = bs, + .size = 128*1024*1024, + .len = ARRAY_SIZE(bs), + .do_write = true, + .do_nonblock_req = true, + .prepare = MMC_TEST_PREP_ERASE, + }; + + return mmc_test_rw_multiple_size(test, &test_data); +} + +/* + * Multiple blocking read 4k to 4 MB chunks + */ +static int mmc_test_profile_mult_read_blocking_perf(struct mmc_test_card *test) +{ + unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, + 1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22}; + struct mmc_test_multiple_rw test_data = { + .bs = bs, + .size = 128*1024*1024, + .len = ARRAY_SIZE(bs), + .do_write = false, + .do_nonblock_req = false, + .prepare = MMC_TEST_PREP_NONE, + }; + + return mmc_test_rw_multiple_size(test, &test_data); +} + +/* + * Multiple non-blocking read 4k to 4 MB chunks + */ +static int mmc_test_profile_mult_read_nonblock_perf(struct mmc_test_card *test) +{ + unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, + 1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22}; + struct mmc_test_multiple_rw test_data = { + .bs = bs, + .size = 128*1024*1024, + .len = ARRAY_SIZE(bs), + .do_write = false, + .do_nonblock_req = true, + .prepare = MMC_TEST_PREP_NONE, + }; + + return mmc_test_rw_multiple_size(test, &test_data); +} + static const struct mmc_test_case mmc_test_cases[] = { { .name = "Basic write (no data verification)", @@ -2221,6 +2498,33 @@ static const struct mmc_test_case mmc_test_cases[] = { .cleanup = mmc_test_area_cleanup, },

+ { + .name = "Write performance with blocking req 4k to 4MB", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_mult_write_blocking_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Write performance with non-blocking req 4k to 4MB", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_mult_write_nonblock_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Read performance with blocking req 4k to 4MB", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_mult_read_blocking_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Read performance with non-blocking req 4k to 4MB", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_mult_read_nonblock_perf, + .cleanup = mmc_test_area_cleanup, + }, };

static DEFINE_MUTEX(mmc_test_lock);

Break out code from mmc_blk_issue_rw_rq to create a block request prepare function. This doesn't change any functionallity. This helps when handling more than one active block request.

Signed-off-by: Per Forlin per.forlin@linaro.org --- drivers/mmc/card/block.c | 224 ++++++++++++++++++++++++--------------------- 1 files changed, 119 insertions(+), 105 deletions(-)

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 3d11690..144d435 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -661,12 +661,15 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq, } }

-static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) +static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, + struct mmc_card *card, + int disable_multi, + struct mmc_queue *mq) { + u32 readcmd, writecmd; + struct mmc_blk_request *brq = &mqrq->brq; + struct request *req = mqrq->req; struct mmc_blk_data *md = mq->data; - struct mmc_card *card = md->queue.card; - struct mmc_blk_request *brq = &mq->mqrq_cur->brq; - int ret = 1, disable_multi = 0;

/* * Reliable writes are used to implement Forced Unit Access and @@ -677,120 +680,131 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) (rq_data_dir(req) == WRITE) && (md->flags & MMC_BLK_REL_WR);

- do { - struct mmc_command cmd = {0}; - u32 readcmd, writecmd, status = 0; - - memset(brq, 0, sizeof(struct mmc_blk_request)); - brq->mrq.cmd = &brq->cmd; - brq->mrq.data = &brq->data; - - brq->cmd.arg = blk_rq_pos(req); - if (!mmc_card_blockaddr(card)) - brq->cmd.arg <<= 9; - brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC; - brq->data.blksz = 512; - brq->stop.opcode = MMC_STOP_TRANSMISSION; - brq->stop.arg = 0; - brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC; - brq->data.blocks = blk_rq_sectors(req); - - /* - * The block layer doesn't support all sector count - * restrictions, so we need to be prepared for too big - * requests. - */ - if (brq->data.blocks > card->host->max_blk_count) - brq->data.blocks = card->host->max_blk_count; + memset(brq, 0, sizeof(struct mmc_blk_request)); + brq->mrq.cmd = &brq->cmd; + brq->mrq.data = &brq->data;

- /* - * After a read error, we redo the request one sector at a time - * in order to accurately determine which sectors can be read - * successfully. - */ - if (disable_multi && brq->data.blocks > 1) - brq->data.blocks = 1; + brq->cmd.arg = blk_rq_pos(req); + if (!mmc_card_blockaddr(card)) + brq->cmd.arg <<= 9; + brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC; + brq->data.blksz = 512; + brq->stop.opcode = MMC_STOP_TRANSMISSION; + brq->stop.arg = 0; + brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC; + brq->data.blocks = blk_rq_sectors(req);

- if (brq->data.blocks > 1 || do_rel_wr) { - /* SPI multiblock writes terminate using a special - * token, not a STOP_TRANSMISSION request. - */ - if (!mmc_host_is_spi(card->host) || - rq_data_dir(req) == READ) - brq->mrq.stop = &brq->stop; - readcmd = MMC_READ_MULTIPLE_BLOCK; - writecmd = MMC_WRITE_MULTIPLE_BLOCK; - } else { - brq->mrq.stop = NULL; - readcmd = MMC_READ_SINGLE_BLOCK; - writecmd = MMC_WRITE_BLOCK; - } - if (rq_data_dir(req) == READ) { - brq->cmd.opcode = readcmd; - brq->data.flags |= MMC_DATA_READ; - } else { - brq->cmd.opcode = writecmd; - brq->data.flags |= MMC_DATA_WRITE; - } + /* + * The block layer doesn't support all sector count + * restrictions, so we need to be prepared for too big + * requests. + */ + if (brq->data.blocks > card->host->max_blk_count) + brq->data.blocks = card->host->max_blk_count;

- if (do_rel_wr) - mmc_apply_rel_rw(&brq, card, req); + /* + * After a read error, we redo the request one sector at a time + * in order to accurately determine which sectors can be read + * successfully. + */ + if (disable_multi && brq->data.blocks > 1) + brq->data.blocks = 1;

- /* - * Pre-defined multi-block transfers are preferable to - * open ended-ones (and necessary for reliable writes). - * However, it is not sufficient to just send CMD23, - * and avoid the final CMD12, as on an error condition - * CMD12 (stop) needs to be sent anyway. This, coupled - * with Auto-CMD23 enhancements provided by some - * hosts, means that the complexity of dealing - * with this is best left to the host. If CMD23 is - * supported by card and host, we'll fill sbc in and let - * the host deal with handling it correctly. This means - * that for hosts that don't expose MMC_CAP_CMD23, no - * change of behavior will be observed. - * - * N.B: Some MMC cards experience perf degradation. - * We'll avoid using CMD23-bounded multiblock writes for - * these, while retaining features like reliable writes. + if (brq->data.blocks > 1 || do_rel_wr) { + /* SPI multiblock writes terminate using a special + * token, not a STOP_TRANSMISSION request. */ + if (!mmc_host_is_spi(card->host) || + rq_data_dir(req) == READ) + brq->mrq.stop = &brq->stop; + readcmd = MMC_READ_MULTIPLE_BLOCK; + writecmd = MMC_WRITE_MULTIPLE_BLOCK; + } else { + brq->mrq.stop = NULL; + readcmd = MMC_READ_SINGLE_BLOCK; + writecmd = MMC_WRITE_BLOCK; + } + if (rq_data_dir(req) == READ) { + brq->cmd.opcode = readcmd; + brq->data.flags |= MMC_DATA_READ; + } else { + brq->cmd.opcode = writecmd; + brq->data.flags |= MMC_DATA_WRITE; + }

- if ((md->flags & MMC_BLK_CMD23) && - mmc_op_multi(brq->cmd.opcode) && - (do_rel_wr || !(card->quirks & MMC_QUIRK_BLK_NO_CMD23))) { - brq->sbc.opcode = MMC_SET_BLOCK_COUNT; - brq->sbc.arg = brq->data.blocks | - (do_rel_wr ? (1 << 31) : 0); - brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; - brq->mrq.sbc = &brq->sbc; - } + if (do_rel_wr) + mmc_apply_rel_rw(brq, card, req);

- mmc_set_data_timeout(&brq->data, card); + /* + * Pre-defined multi-block transfers are preferable to + * open ended-ones (and necessary for reliable writes). + * However, it is not sufficient to just send CMD23, + * and avoid the final CMD12, as on an error condition + * CMD12 (stop) needs to be sent anyway. This, coupled + * with Auto-CMD23 enhancements provided by some + * hosts, means that the complexity of dealing + * with this is best left to the host. If CMD23 is + * supported by card and host, we'll fill sbc in and let + * the host deal with handling it correctly. This means + * that for hosts that don't expose MMC_CAP_CMD23, no + * change of behavior will be observed. + * + * N.B: Some MMC cards experience perf degradation. + * We'll avoid using CMD23-bounded multiblock writes for + * these, while retaining features like reliable writes. + */

- brq->data.sg = mq->mqrq_cur->sg; - brq->data.sg_len = mmc_queue_map_sg(mq, mq->mqrq_cur); + if ((md->flags & MMC_BLK_CMD23) && + mmc_op_multi(brq->cmd.opcode) && + (do_rel_wr || !(card->quirks & MMC_QUIRK_BLK_NO_CMD23))) { + brq->sbc.opcode = MMC_SET_BLOCK_COUNT; + brq->sbc.arg = brq->data.blocks | + (do_rel_wr ? (1 << 31) : 0); + brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; + brq->mrq.sbc = &brq->sbc; + }

- /* - * Adjust the sg list so it is the same size as the - * request. - */ - if (brq->data.blocks != blk_rq_sectors(req)) { - int i, data_size = brq->data.blocks << 9; - struct scatterlist *sg; - - for_each_sg(brq->data.sg, sg, brq->data.sg_len, i) { - data_size -= sg->length; - if (data_size <= 0) { - sg->length += data_size; - i++; - break; - } + mmc_set_data_timeout(&brq->data, card); + + brq->data.sg = mqrq->sg; + brq->data.sg_len = mmc_queue_map_sg(mq, mqrq); + + /* + * Adjust the sg list so it is the same size as the + * request. + */ + if (brq->data.blocks != blk_rq_sectors(req)) { + int i, data_size = brq->data.blocks << 9; + struct scatterlist *sg; + + for_each_sg(brq->data.sg, sg, brq->data.sg_len, i) { + data_size -= sg->length; + if (data_size <= 0) { + sg->length += data_size; + i++; + break; } - brq->data.sg_len = i; } + brq->data.sg_len = i; + }

- mmc_queue_bounce_pre(mq->mqrq_cur); + mmc_queue_bounce_pre(mqrq); +} + +static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) +{ + struct mmc_blk_data *md = mq->data; + struct mmc_card *card = md->queue.card; + struct mmc_blk_request *brq = &mq->mqrq_cur->brq; + int ret = 1, disable_multi = 0; + + mmc_claim_host(card->host); + + do { + struct mmc_command cmd; + u32 status = 0;

+ mmc_blk_rw_rq_prep(mq->mqrq_cur, card, disable_multi, mq); mmc_wait_for_req(card->host, &brq->mrq);

mmc_queue_bounce_post(mq->mqrq_cur);

Add an additional mmc queue request instance to make way for two active block requests. One request may be active while the other request is being prepared.

Signed-off-by: Per Forlin per.forlin@linaro.org --- drivers/mmc/card/queue.c | 44 ++++++++++++++++++++++++++++++++++++++++++-- drivers/mmc/card/queue.h | 3 ++- 2 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 81d0eef..0757a39 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -130,6 +130,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock 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; @@ -140,7 +141,9 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock 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;

blk_queue_prep_rq(mq->queue, mmc_prep_request); @@ -181,9 +184,17 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock "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 prev buffer\n", + mmc_card_name(card)); + kfree(mqrq_cur->bounce_buf); + mqrq_cur->bounce_buf = NULL; + } }

- if (mqrq_cur->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); @@ -198,11 +209,19 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock 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; } } #endif

- if (!mqrq_cur->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)); @@ -213,6 +232,10 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock if (ret) goto cleanup_queue;

+ + mqrq_prev->sg = mmc_alloc_sg(host->max_segs, &ret); + if (ret) + goto cleanup_queue; }

sema_init(&mq->thread_sem, 1); @@ -229,6 +252,8 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock free_bounce_sg: kfree(mqrq_cur->bounce_sg); mqrq_cur->bounce_sg = NULL; + kfree(mqrq_prev->bounce_sg); + mqrq_prev->bounce_sg = NULL;

cleanup_queue: kfree(mqrq_cur->sg); @@ -236,6 +261,11 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock 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; } @@ -245,6 +275,7 @@ 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); @@ -267,6 +298,15 @@ void mmc_cleanup_queue(struct mmc_queue *mq) kfree(mqrq_cur->bounce_buf); mqrq_cur->bounce_buf = NULL;

+ kfree(mqrq_prev->bounce_sg); + mqrq_prev->bounce_sg = NULL; + + kfree(mqrq_prev->sg); + mqrq_prev->sg = NULL; + + kfree(mqrq_prev->bounce_buf); + mqrq_prev->bounce_buf = NULL; + mq->card = NULL; } EXPORT_SYMBOL(mmc_cleanup_queue); diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index a1defed..c8fb2dc 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -29,8 +29,9 @@ struct mmc_queue { int (*issue_fn)(struct mmc_queue *, struct request *); void *data; struct request_queue *queue; - struct mmc_queue_req mqrq[1]; + 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 *);

Change mmc_blk_issue_rw_rq() to become asynchronous. The execution flow looks like this: The mmc-queue calls issue_rw_rq(), which sends the request to the host and returns back to the mmc-queue. The mmc-queue calls issue_rw_rq() again with a new request. This new request is prepared, in isuue_rw_rq(), then it waits for the active request to complete before pushing it to the host. When to mmc-queue is empty it will call isuue_rw_rq() with req=NULL to finish off the active request without starting a new request.

Signed-off-by: Per Forlin per.forlin@linaro.org --- drivers/mmc/card/block.c | 121 +++++++++++++++++++++++++++++++++------------- drivers/mmc/card/queue.c | 17 +++++-- drivers/mmc/card/queue.h | 1 + 3 files changed, 101 insertions(+), 38 deletions(-)

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 6a84a75..66db77a 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -108,6 +108,7 @@ static DEFINE_MUTEX(open_lock);

enum mmc_blk_status { MMC_BLK_SUCCESS = 0, + MMC_BLK_PARTIAL, MMC_BLK_RETRY, MMC_BLK_DATA_ERR, MMC_BLK_CMD_ERR, @@ -668,14 +669,16 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq, } }

-static enum mmc_blk_status mmc_blk_err_check(struct mmc_blk_request *brq, - struct request *req, - struct mmc_card *card, - struct mmc_blk_data *md) +static int mmc_blk_err_check(struct mmc_card *card, + struct mmc_async_req *areq) { struct mmc_command cmd; u32 status = 0; enum mmc_blk_status ret = MMC_BLK_SUCCESS; + struct mmc_queue_req *mq_mrq = container_of(areq, struct mmc_queue_req, + mmc_active); + struct mmc_blk_request *brq = &mq_mrq->brq; + struct request *req = mq_mrq->req;

/* * Check for errors here, but don't jump to cmd_err @@ -770,7 +773,11 @@ static enum mmc_blk_status mmc_blk_err_check(struct mmc_blk_request *brq, else ret = MMC_BLK_DATA_ERR; } -out: + + if (ret == MMC_BLK_SUCCESS && + blk_rq_bytes(req) != brq->data.bytes_xfered) + ret = MMC_BLK_PARTIAL; + out: return ret; }

@@ -901,27 +908,59 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, brq->data.sg_len = i; }

+ mqrq->mmc_active.mrq = &brq->mrq; + mqrq->mmc_active.err_check = mmc_blk_err_check; + mmc_queue_bounce_pre(mqrq); }

-static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) +static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) { struct mmc_blk_data *md = mq->data; struct mmc_card *card = md->queue.card; - struct mmc_blk_request *brq = &mq->mqrq_cur->brq; - int ret = 1, disable_multi = 0; + struct mmc_blk_request *brq; + int ret = 1; + int disable_multi = 0; enum mmc_blk_status status; + struct mmc_queue_req *mq_rq; + struct request *req; + struct mmc_async_req *areq; + + if (!rqc && !mq->mqrq_prev->req) + goto out;

do { - mmc_blk_rw_rq_prep(mq->mqrq_cur, card, disable_multi, mq); - mmc_wait_for_req(card->host, &brq->mrq); + if (rqc) { + mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); + areq = &mq->mqrq_cur->mmc_active; + } else + areq = NULL; + areq = mmc_start_req(card->host, areq, (int *) &status); + if (!areq) + goto out;

- mmc_queue_bounce_post(mq->mqrq_cur); - status = mmc_blk_err_check(brq, req, card, md); + mq_rq = container_of(areq, struct mmc_queue_req, mmc_active); + brq = &mq_rq->brq; + req = mq_rq->req; + mmc_queue_bounce_post(mq_rq);

switch (status) { - case MMC_BLK_CMD_ERR: - goto cmd_err; + case MMC_BLK_SUCCESS: + case MMC_BLK_PARTIAL: + /* + * A block was successfully transferred. + */ + spin_lock_irq(&md->lock); + ret = __blk_end_request(req, 0, + brq->data.bytes_xfered); + spin_unlock_irq(&md->lock); + if (status == MMC_BLK_SUCCESS && ret) { + /* If this happen it is a bug */ + printk(KERN_ERR "%s BUG rq_tot %d d_xfer %d\n", + __func__, blk_rq_bytes(req), + brq->data.bytes_xfered); + goto cmd_err; + } break; case MMC_BLK_RETRY: disable_multi = 1; @@ -934,36 +973,41 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) * read a single sector. */ spin_lock_irq(&md->lock); - ret = __blk_end_request(req, -EIO, - brq->data.blksz); + ret = __blk_end_request(req, -EIO, brq->data.blksz); spin_unlock_irq(&md->lock); - + if (!ret) + goto start_new_req; break; - case MMC_BLK_SUCCESS: + case MMC_BLK_CMD_ERR: + ret = 1; + goto cmd_err; + break; + } + + if (ret) { /* - * A block was successfully transferred. + * In case of a none complete request + * prepare it again and resend. */ - spin_lock_irq(&md->lock); - ret = __blk_end_request(req, 0, brq->data.bytes_xfered); - spin_unlock_irq(&md->lock); - break; + mmc_blk_rw_rq_prep(mq_rq, card, disable_multi, mq); + mmc_start_req(card->host, &mq_rq->mmc_active, NULL); } } while (ret);

return 1; - + out: + return 0; cmd_err: - /* - * If this is an SD card and we're writing, we can first - * mark the known good sectors as ok. - * + /* + * If this is an SD card and we're writing, we can first + * mark the known good sectors as ok. + * * If the card is not SD, we can still ok written sectors * as reported by the controller (which might be less than * the real number of written sectors, but never more). */ if (mmc_card_sd(card)) { u32 blocks; - blocks = mmc_sd_num_wr_blocks(card); if (blocks != (u32)-1) { spin_lock_irq(&md->lock); @@ -981,6 +1025,12 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) ret = __blk_end_request(req, -EIO, blk_rq_cur_bytes(req)); spin_unlock_irq(&md->lock);

+ start_new_req: + if (rqc) { + mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); + mmc_start_req(card->host, &mq->mqrq_cur->mmc_active, NULL); + } + return 0; }

@@ -990,26 +1040,31 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) struct mmc_blk_data *md = mq->data; struct mmc_card *card = md->queue.card;

- mmc_claim_host(card->host); + if (req && !mq->mqrq_prev->req) + /* claim host only for the first request */ + mmc_claim_host(card->host); + ret = mmc_blk_part_switch(card, md); if (ret) { ret = 0; goto out; }

- if (req->cmd_flags & REQ_DISCARD) { + if (req && req->cmd_flags & REQ_DISCARD) { if (req->cmd_flags & REQ_SECURE) ret = mmc_blk_issue_secdiscard_rq(mq, req); else ret = mmc_blk_issue_discard_rq(mq, req); - } else if (req->cmd_flags & REQ_FLUSH) { + } else if (req && req->cmd_flags & REQ_FLUSH) { ret = mmc_blk_issue_flush(mq, req); } else { ret = mmc_blk_issue_rw_rq(mq, req); }

out: - mmc_release_host(card->host); + if (!req) + /* release host only when there are no more requests */ + mmc_release_host(card->host); return ret; }

diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 0757a39..2d6696a 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -52,6 +52,7 @@ 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); @@ -59,7 +60,10 @@ static int mmc_queue_thread(void *d) 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);

@@ -97,7 +104,7 @@ static void mmc_request(struct request_queue *q) return; }

- if (!mq->mqrq_cur->req) + if (!mq->mqrq_cur->req && !mq->mqrq_prev->req) wake_up_process(mq->thread); }

diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index c8fb2dc..f937538 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -19,6 +19,7 @@ struct mmc_queue_req { char *bounce_buf; struct scatterlist *bounce_sg; unsigned int bounce_sg_len; + struct mmc_async_req mmc_active; };

struct mmc_queue {