How significant is the cache maintenance over head? It depends, the eMMC are much faster now compared to a few years ago and cache maintenance cost more due to multiple cache levels and speculative cache pre-fetch. In relation the cost for handling the caches have increased and is now a bottle neck dealing with fast eMMC together with DMA.
The intention for introducing non-blocking mmc requests is to minimize the time between a mmc request ends and another mmc request starts. In the current implementation the MMC controller is idle when dma_map_sg and dma_unmap_sg is processing. Introducing non-blocking mmc request makes it possible to prepare the caches for next job in parallel to an active mmc request.
This is done by making the issue_rw_rq() non-blocking. The increase in throughput is proportional to the time it takes to prepare (major part of preparations is 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. Measurements on U5500 and Panda on eMMC and SD shows significant performance gain for large reads when running DMA mode. In the PIO case the performance is unchanged.
There are two optional hooks pre_req() and post_req() that the host driver may implement in order to move work to before and after the actual mmc_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.
Details on measurements from IOZone and mmc_test: https://wiki.linaro.org/WorkingGroups/Kernel/Specs/StoragePerfMMC-async-req
Tested on platforms * Development and extensive testing is done on ux500 and Pandaboard * Additional testing is done on * Patches are tested on samsung exynos4 platform * Boot tested on Omap4430 Blaze board * U300 MMC/PL180 mmc_test and ad hoc FS test * ARM realview mmc_test and ad hoc FS test
Changes since v8: * add comment to clarify bug print in issue_rw_rq. * mmc_test: * align size for sg_len test cases, * use MAX_SIZE define for test size for all non-blocking, * allow non-blocking test even if pre/post is not implemented, * return error if only one of pre or post is implemented.
Per Forlin (12): mmc: core: add non-blocking mmc request function omap_hsmmc: add support for pre_req and post_req mmci: implement pre_req() and post_req() mmc: mmc_test: add debugfs file to list all tests mmc: mmc_test: add test for non-blocking transfers mmc: mmc_test: test to measure how sg_len affect performance mmc: block: add member in mmc queue struct to hold request data mmc: block: add a block request prepare function mmc: block: move error code in issue_rw_rq to a separate function. mmc: queue: add a second mmc queue request member mmc: core: add random fault injection mmc: block: add handling for two parallel block requests in issue_rw_rq
drivers/mmc/card/block.c | 507 ++++++++++++++++++++++++---------------- drivers/mmc/card/mmc_test.c | 498 +++++++++++++++++++++++++++++++++++++++-- drivers/mmc/card/queue.c | 184 ++++++++++------ drivers/mmc/card/queue.h | 33 ++- drivers/mmc/core/core.c | 167 +++++++++++++- drivers/mmc/core/debugfs.c | 5 + drivers/mmc/host/mmci.c | 147 +++++++++++- drivers/mmc/host/mmci.h | 8 + drivers/mmc/host/omap_hsmmc.c | 87 +++++++- include/linux/mmc/core.h | 6 +- include/linux/mmc/host.h | 24 ++ lib/Kconfig.debug | 11 + 12 files changed, 1356 insertions(+), 321 deletions(-)
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 Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/core/core.c | 113 +++++++++++++++++++++++++++++++++++++++++---- include/linux/mmc/core.h | 6 ++- include/linux/mmc/host.h | 21 +++++++++ 3 files changed, 129 insertions(+), 11 deletions(-)
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 7843efe..d2d7239 100644 --- a/drivers/mmc/core/core.c +++ b/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);
/** 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(), post_req() runs dma_unmap_sg. If not calling pre_req() before omap_hsmmc_request() dma_map_sg will be issued before starting the transfer. It is optional to use pre_req(). If issuing pre_req() post_req() must be to be called as well.
Signed-off-by: Per Forlin per.forlin@linaro.org Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com --- drivers/mmc/host/omap_hsmmc.c | 87 +++++++++++++++++++++++++++++++++++++++-- 1 files changed, 83 insertions(+), 4 deletions(-)
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index cd317af..b29ca90 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -141,6 +141,11 @@ #define OMAP_HSMMC_WRITE(base, reg, val) \ __raw_writel((val), (base) + OMAP_HSMMC_##reg)
+struct omap_hsmmc_next { + unsigned int dma_len; + s32 cookie; +}; + struct omap_hsmmc_host { struct device *dev; struct mmc_host *mmc; @@ -184,6 +189,7 @@ struct omap_hsmmc_host { int reqs_blocked; int use_reg; int req_in_progress; + struct omap_hsmmc_next next_data;
struct omap_mmc_platform_data *pdata; }; @@ -1343,8 +1349,9 @@ static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data) return; }
- dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, - omap_hsmmc_get_dma_dir(host, data)); + if (!data->host_cookie) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + omap_hsmmc_get_dma_dir(host, data));
req_in_progress = host->req_in_progress; dma_ch = host->dma_ch; @@ -1362,6 +1369,45 @@ static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data) } }
+static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host, + struct mmc_data *data, + struct omap_hsmmc_next *next) +{ + int dma_len; + + if (!next && data->host_cookie && + data->host_cookie != host->next_data.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; + } + + /* Check if next job is already prepared */ + if (next || + (!next && data->host_cookie != host->next_data.cookie)) { + dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg, + data->sg_len, + omap_hsmmc_get_dma_dir(host, data)); + + } else { + dma_len = host->next_data.dma_len; + host->next_data.dma_len = 0; + } + + + if (dma_len == 0) + return -EINVAL; + + if (next) { + next->dma_len = dma_len; + data->host_cookie = ++next->cookie < 0 ? 1 : next->cookie; + } else + host->dma_len = dma_len; + + return 0; +} + /* * Routine to configure and start DMA for the MMC card */ @@ -1395,9 +1441,10 @@ static int omap_hsmmc_start_dma_transfer(struct omap_hsmmc_host *host, mmc_hostname(host->mmc), ret); return ret; } + ret = omap_hsmmc_pre_dma_transfer(host, data, NULL); + if (ret) + return ret;
- host->dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg, - data->sg_len, omap_hsmmc_get_dma_dir(host, data)); host->dma_ch = dma_ch; host->dma_sg_idx = 0;
@@ -1477,6 +1524,35 @@ omap_hsmmc_prepare_data(struct omap_hsmmc_host *host, struct mmc_request *req) return 0; }
+static void omap_hsmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq, + int err) +{ + struct omap_hsmmc_host *host = mmc_priv(mmc); + struct mmc_data *data = mrq->data; + + if (host->use_dma) { + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + omap_hsmmc_get_dma_dir(host, data)); + data->host_cookie = 0; + } +} + +static void omap_hsmmc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq, + bool is_first_req) +{ + struct omap_hsmmc_host *host = mmc_priv(mmc); + + if (mrq->data->host_cookie) { + mrq->data->host_cookie = 0; + return ; + } + + if (host->use_dma) + if (omap_hsmmc_pre_dma_transfer(host, mrq->data, + &host->next_data)) + mrq->data->host_cookie = 0; +} + /* * Request function. for read/write operation */ @@ -1925,6 +2001,8 @@ static int omap_hsmmc_disable_fclk(struct mmc_host *mmc, int lazy) static const struct mmc_host_ops omap_hsmmc_ops = { .enable = omap_hsmmc_enable_fclk, .disable = omap_hsmmc_disable_fclk, + .post_req = omap_hsmmc_post_req, + .pre_req = omap_hsmmc_pre_req, .request = omap_hsmmc_request, .set_ios = omap_hsmmc_set_ios, .get_cd = omap_hsmmc_get_cd, @@ -2074,6 +2152,7 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev) host->mapbase = res->start; host->base = ioremap(host->mapbase, SZ_4K); host->power_mode = MMC_POWER_OFF; + host->next_data.cookie = 1;
platform_set_drvdata(pdev, host); INIT_WORK(&host->mmc_carddetect_work, omap_hsmmc_detect);
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 Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/host/mmci.c | 147 ++++++++++++++++++++++++++++++++++++++++++---- drivers/mmc/host/mmci.h | 8 +++ 2 files changed, 142 insertions(+), 13 deletions(-)
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index b4a7e4f..6ed6770 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -211,6 +211,9 @@ 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); @@ -320,7 +323,8 @@ 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 +342,8 @@ 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 +354,20 @@ 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 +382,7 @@ 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 +396,38 @@ 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 +442,90 @@ 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 +546,10 @@ 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 +968,9 @@ 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 +1085,8 @@ 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, 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 a debugfs file "testlist" to print all available tests
Signed-off-by: Per Forlin per.forlin@linaro.org Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/card/mmc_test.c | 39 ++++++++++++++++++++++++++++++++++++++- 1 files changed, 38 insertions(+), 1 deletions(-)
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c index 233cdfa..e8508e9 100644 --- a/drivers/mmc/card/mmc_test.c +++ b/drivers/mmc/card/mmc_test.c @@ -2445,6 +2445,32 @@ static const struct file_operations mmc_test_fops_test = { .release = single_release, };
+static int mtf_testlist_show(struct seq_file *sf, void *data) +{ + int i; + + mutex_lock(&mmc_test_lock); + + for (i = 0; i < ARRAY_SIZE(mmc_test_cases); i++) + seq_printf(sf, "%d:\t%s\n", i+1, mmc_test_cases[i].name); + + mutex_unlock(&mmc_test_lock); + + return 0; +} + +static int mtf_testlist_open(struct inode *inode, struct file *file) +{ + return single_open(file, mtf_testlist_show, inode->i_private); +} + +static const struct file_operations mmc_test_fops_testlist = { + .open = mtf_testlist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static void mmc_test_free_file_test(struct mmc_card *card) { struct mmc_test_dbgfs_file *df, *dfs; @@ -2476,7 +2502,18 @@ static int mmc_test_register_file_test(struct mmc_card *card)
if (IS_ERR_OR_NULL(file)) { dev_err(&card->dev, - "Can't create file. Perhaps debugfs is disabled.\n"); + "Can't create test. Perhaps debugfs is disabled.\n"); + ret = -ENODEV; + goto err; + } + + if (card->debugfs_root) + file = debugfs_create_file("testlist", S_IRUGO, + card->debugfs_root, card, &mmc_test_fops_testlist); + + if (IS_ERR_OR_NULL(file)) { + dev_err(&card->dev, + "Can't create testlist. Perhaps debugfs is disabled.\n"); ret = -ENODEV; goto err; }
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 Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/card/mmc_test.c | 318 +++++++++++++++++++++++++++++++++++++++++- 1 files changed, 310 insertions(+), 8 deletions(-)
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c index e8508e9..51031a5 100644 --- a/drivers/mmc/card/mmc_test.c +++ b/drivers/mmc/card/mmc_test.c @@ -148,6 +148,26 @@ 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 */ /*******************************************************************/ @@ -661,7 +681,7 @@ 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 +705,17 @@ 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); + + mmc_test_wait_busy(test_async->test); + + return mmc_test_check_result(test_async->test, areq->mrq); +} + /* * Checks that a "short transfer" behaved as expected */ @@ -720,6 +751,85 @@ 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; + + 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 +1446,17 @@ 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 +1480,15 @@ 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 +1496,19 @@ 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 +2082,153 @@ 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; + + if (reqsize > size) + return 0; + + /* 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; + void *pre_req = test->card->host->ops->pre_req; + void *post_req = test->card->host->ops->post_req; + + if (rw->do_nonblock_req && + ((!pre_req && post_req) || (pre_req && !post_req))) { + printk(KERN_INFO "error: only one of pre/post is defined\n"); + return -EINVAL; + } + + 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 = TEST_AREA_MAX_SIZE, + .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 = TEST_AREA_MAX_SIZE, + .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 = TEST_AREA_MAX_SIZE, + .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 = TEST_AREA_MAX_SIZE, + .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 +2496,33 @@ 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);
test that measures how the mmc bandwidth depends on the numbers of sg elements in the sg list. The transfer size if fixed and sg length goes from a few up to 512. The purpose is to measure overhead caused by multiple sg elements.
Signed-off-by: Per Forlin per.forlin@linaro.org Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/card/mmc_test.c | 151 +++++++++++++++++++++++++++++++++++++++---- 1 files changed, 139 insertions(+), 12 deletions(-)
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c index 51031a5..006a5e9 100644 --- a/drivers/mmc/card/mmc_test.c +++ b/drivers/mmc/card/mmc_test.c @@ -155,6 +155,7 @@ enum mmc_test_prep_media { };
struct mmc_test_multiple_rw { + unsigned int *sg_len; unsigned int *bs; unsigned int len; unsigned int size; @@ -387,21 +388,26 @@ out_free: * Map memory into a scatterlist. Optionally allow the same memory to be * mapped more than once. */ -static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long sz, +static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long size, struct scatterlist *sglist, int repeat, unsigned int max_segs, unsigned int max_seg_sz, - unsigned int *sg_len) + unsigned int *sg_len, int min_sg_len) { struct scatterlist *sg = NULL; unsigned int i; + unsigned long sz = size;
sg_init_table(sglist, max_segs); + if (min_sg_len > max_segs) + min_sg_len = max_segs;
*sg_len = 0; do { for (i = 0; i < mem->cnt; i++) { unsigned long len = PAGE_SIZE << mem->arr[i].order;
+ if (min_sg_len && (size / min_sg_len < len)) + len = ALIGN(size / min_sg_len, 512); if (len > sz) len = sz; if (len > max_seg_sz) @@ -574,11 +580,12 @@ static void mmc_test_print_avg_rate(struct mmc_test_card *test, uint64_t bytes,
printk(KERN_INFO "%s: Transfer of %u x %u sectors (%u x %u%s KiB) took " "%lu.%09lu seconds (%u kB/s, %u KiB/s, " - "%u.%02u IOPS)\n", + "%u.%02u IOPS, sg_len %d)\n", mmc_hostname(test->card->host), count, sectors, count, sectors >> 1, (sectors & 1 ? ".5" : ""), (unsigned long)ts.tv_sec, (unsigned long)ts.tv_nsec, - rate / 1000, rate / 1024, iops / 100, iops % 100); + rate / 1000, rate / 1024, iops / 100, iops % 100, + test->area.sg_len);
mmc_test_save_transfer_result(test, count, sectors, ts, rate, iops); } @@ -1412,7 +1419,7 @@ static int mmc_test_no_highmem(struct mmc_test_card *test) * Map sz bytes so that it can be transferred. */ static int mmc_test_area_map(struct mmc_test_card *test, unsigned long sz, - int max_scatter) + int max_scatter, int min_sg_len) { struct mmc_test_area *t = &test->area; int err; @@ -1425,7 +1432,7 @@ static int mmc_test_area_map(struct mmc_test_card *test, unsigned long sz, &t->sg_len); } else { err = mmc_test_map_sg(t->mem, sz, t->sg, 1, t->max_segs, - t->max_seg_sz, &t->sg_len); + t->max_seg_sz, &t->sg_len, min_sg_len); } if (err) printk(KERN_INFO "%s: Failed to map sg list\n", @@ -1451,7 +1458,7 @@ static int mmc_test_area_transfer(struct mmc_test_card *test, 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) + bool nonblock, int min_sg_len) { struct timespec ts1, ts2; int ret = 0; @@ -1474,7 +1481,7 @@ static int mmc_test_area_io_seq(struct mmc_test_card *test, unsigned long sz, sz = max_tfr; }
- ret = mmc_test_area_map(test, sz, max_scatter); + ret = mmc_test_area_map(test, sz, max_scatter, min_sg_len); if (ret) return ret;
@@ -1506,7 +1513,7 @@ static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz, int timed) { return mmc_test_area_io_seq(test, sz, dev_addr, write, max_scatter, - timed, 1, false); + timed, 1, false, 0); }
/* @@ -2084,7 +2091,8 @@ static int mmc_test_large_seq_write_perf(struct mmc_test_card *test)
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 reqsize, unsigned int size, + int min_sg_len) { unsigned int dev_addr; struct mmc_test_area *t = &test->area; @@ -2121,7 +2129,7 @@ static int mmc_test_rw_multiple(struct mmc_test_card *test, /* Run test */ ret = mmc_test_area_io_seq(test, reqsize, dev_addr, tdata->do_write, 0, 1, size / reqsize, - tdata->do_nonblock_req); + tdata->do_nonblock_req, min_sg_len); if (ret) goto err;
@@ -2146,7 +2154,22 @@ static int mmc_test_rw_multiple_size(struct mmc_test_card *test, }
for (i = 0 ; i < rw->len && ret == 0; i++) { - ret = mmc_test_rw_multiple(test, rw, rw->bs[i], rw->size); + ret = mmc_test_rw_multiple(test, rw, rw->bs[i], rw->size, 0); + if (ret) + break; + } + return ret; +} + +static int mmc_test_rw_multiple_sg_len(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, 512*1024, rw->size, + rw->sg_len[i]); if (ret) break; } @@ -2229,6 +2252,82 @@ static int mmc_test_profile_mult_read_nonblock_perf(struct mmc_test_card *test) return mmc_test_rw_multiple_size(test, &test_data); }
+/* + * Multiple blocking write 1 to 512 sg elements + */ +static int mmc_test_profile_sglen_wr_blocking_perf(struct mmc_test_card *test) +{ + unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6, + 1 << 7, 1 << 8, 1 << 9}; + struct mmc_test_multiple_rw test_data = { + .sg_len = sg_len, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(sg_len), + .do_write = true, + .do_nonblock_req = false, + .prepare = MMC_TEST_PREP_ERASE, + }; + + return mmc_test_rw_multiple_sg_len(test, &test_data); +}; + +/* + * Multiple non-blocking write 1 to 512 sg elements + */ +static int mmc_test_profile_sglen_wr_nonblock_perf(struct mmc_test_card *test) +{ + unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6, + 1 << 7, 1 << 8, 1 << 9}; + struct mmc_test_multiple_rw test_data = { + .sg_len = sg_len, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(sg_len), + .do_write = true, + .do_nonblock_req = true, + .prepare = MMC_TEST_PREP_ERASE, + }; + + return mmc_test_rw_multiple_sg_len(test, &test_data); +} + +/* + * Multiple blocking read 1 to 512 sg elements + */ +static int mmc_test_profile_sglen_r_blocking_perf(struct mmc_test_card *test) +{ + unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6, + 1 << 7, 1 << 8, 1 << 9}; + struct mmc_test_multiple_rw test_data = { + .sg_len = sg_len, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(sg_len), + .do_write = false, + .do_nonblock_req = false, + .prepare = MMC_TEST_PREP_NONE, + }; + + return mmc_test_rw_multiple_sg_len(test, &test_data); +} + +/* + * Multiple non-blocking read 1 to 512 sg elements + */ +static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) +{ + unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6, + 1 << 7, 1 << 8, 1 << 9}; + struct mmc_test_multiple_rw test_data = { + .sg_len = sg_len, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(sg_len), + .do_write = false, + .do_nonblock_req = true, + .prepare = MMC_TEST_PREP_NONE, + }; + + return mmc_test_rw_multiple_sg_len(test, &test_data); +} + static const struct mmc_test_case mmc_test_cases[] = { { .name = "Basic write (no data verification)", @@ -2523,6 +2622,34 @@ static const struct mmc_test_case mmc_test_cases[] = { .run = mmc_test_profile_mult_read_nonblock_perf, .cleanup = mmc_test_area_cleanup, }, + + { + .name = "Write performance blocking req 1 to 512 sg elems", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_sglen_wr_blocking_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Write performance non-blocking req 1 to 512 sg elems", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_sglen_wr_nonblock_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Read performance blocking req 1 to 512 sg elems", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_sglen_r_blocking_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Read performance non-blocking req 1 to 512 sg elems", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_sglen_r_nonblock_perf, + .cleanup = mmc_test_area_cleanup, + }, };
static DEFINE_MUTEX(mmc_test_lock);
The way the request data is organized in the mmc queue struct it only allows processing of one request at the time. This patch adds a new struct to hold mmc queue request data such as sg list, request, blk request and bounce buffers, and updates any functions depending on the mmc queue struct. This lies the ground for using multiple active request for one mmc queue.
Signed-off-by: Per Forlin per.forlin@linaro.org Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/card/block.c | 109 ++++++++++++++++++--------------------- drivers/mmc/card/queue.c | 129 ++++++++++++++++++++++++---------------------- drivers/mmc/card/queue.h | 31 ++++++++--- 3 files changed, 141 insertions(+), 128 deletions(-)
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index bee2106..88bcc4e 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -427,14 +427,6 @@ static const struct block_device_operations mmc_bdops = { #endif };
-struct mmc_blk_request { - struct mmc_request mrq; - struct mmc_command sbc; - struct mmc_command cmd; - struct mmc_command stop; - struct mmc_data data; -}; - static inline int mmc_blk_part_switch(struct mmc_card *card, struct mmc_blk_data *md) { @@ -824,7 +816,7 @@ 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; + struct mmc_blk_request *brq = &mq->mqrq_cur->brq; int ret = 1, disable_multi = 0, retry = 0;
/* @@ -839,60 +831,60 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) do { u32 readcmd, writecmd;
- memset(&brq, 0, sizeof(struct mmc_blk_request)); - brq.mrq.cmd = &brq.cmd; - brq.mrq.data = &brq.data; + 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); + 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); + 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; + if (brq->data.blocks > card->host->max_blk_count) + brq->data.blocks = card->host->max_blk_count;
/* * 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; + if (disable_multi && brq->data.blocks > 1) + brq->data.blocks = 1;
- if (brq.data.blocks > 1 || do_rel_wr) { + 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; + brq->mrq.stop = &brq->stop; readcmd = MMC_READ_MULTIPLE_BLOCK; writecmd = MMC_WRITE_MULTIPLE_BLOCK; } else { - brq.mrq.stop = NULL; + 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; + brq->cmd.opcode = readcmd; + brq->data.flags |= MMC_DATA_READ; } else { - brq.cmd.opcode = writecmd; - brq.data.flags |= MMC_DATA_WRITE; + brq->cmd.opcode = writecmd; + brq->data.flags |= MMC_DATA_WRITE; }
if (do_rel_wr) - mmc_apply_rel_rw(&brq, card, req); + mmc_apply_rel_rw(brq, card, req);
/* * Pre-defined multi-block transfers are preferable to @@ -914,29 +906,29 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) */
if ((md->flags & MMC_BLK_CMD23) && - mmc_op_multi(brq.cmd.opcode) && + 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 | + 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; + brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; + brq->mrq.sbc = &brq->sbc; }
- mmc_set_data_timeout(&brq.data, card); + mmc_set_data_timeout(&brq->data, card);
- brq.data.sg = mq->sg; - brq.data.sg_len = mmc_queue_map_sg(mq); + brq->data.sg = mq->mqrq_cur->sg; + brq->data.sg_len = mmc_queue_map_sg(mq, mq->mqrq_cur);
/* * 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; + 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) { + for_each_sg(brq->data.sg, sg, brq->data.sg_len, i) { data_size -= sg->length; if (data_size <= 0) { sg->length += data_size; @@ -944,14 +936,14 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) break; } } - brq.data.sg_len = i; + brq->data.sg_len = i; }
- mmc_queue_bounce_pre(mq); + mmc_queue_bounce_pre(mq->mqrq_cur);
- mmc_wait_for_req(card->host, &brq.mrq); + mmc_wait_for_req(card->host, &brq->mrq);
- mmc_queue_bounce_post(mq); + mmc_queue_bounce_post(mq->mqrq_cur);
/* * sbc.error indicates a problem with the set block count @@ -963,8 +955,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) * stop.error indicates a problem with the stop command. Data * may have been transferred, or may still be transferring. */ - if (brq.sbc.error || brq.cmd.error || brq.stop.error) { - switch (mmc_blk_cmd_recovery(card, req, &brq)) { + if (brq->sbc.error || brq->cmd.error || brq->stop.error) { + switch (mmc_blk_cmd_recovery(card, req, brq)) { case ERR_RETRY: if (retry++ < 5) continue; @@ -980,9 +972,9 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) * initial command - such as address errors. No data * has been transferred. */ - if (brq.cmd.resp[0] & CMD_ERRORS) { + if (brq->cmd.resp[0] & CMD_ERRORS) { pr_err("%s: r/w command failed, status = %#x\n", - req->rq_disk->disk_name, brq.cmd.resp[0]); + req->rq_disk->disk_name, brq->cmd.resp[0]); goto cmd_abort; }
@@ -1009,15 +1001,15 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) (R1_CURRENT_STATE(status) == R1_STATE_PRG)); }
- if (brq.data.error) { + if (brq->data.error) { pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n", - req->rq_disk->disk_name, brq.data.error, + req->rq_disk->disk_name, brq->data.error, (unsigned)blk_rq_pos(req), (unsigned)blk_rq_sectors(req), - brq.cmd.resp[0], brq.stop.resp[0]); + brq->cmd.resp[0], brq->stop.resp[0]);
if (rq_data_dir(req) == READ) { - if (brq.data.blocks > 1) { + if (brq->data.blocks > 1) { /* Redo read one sector at a time */ pr_warning("%s: retrying using single block read\n", req->rq_disk->disk_name); @@ -1031,7 +1023,8 @@ 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); continue; } else { @@ -1043,7 +1036,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) * A block was successfully transferred. */ spin_lock_irq(&md->lock); - ret = __blk_end_request(req, 0, brq.data.bytes_xfered); + ret = __blk_end_request(req, 0, brq->data.bytes_xfered); spin_unlock_irq(&md->lock); } while (ret);
@@ -1069,7 +1062,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) } } else { spin_lock_irq(&md->lock); - ret = __blk_end_request(req, 0, brq.data.bytes_xfered); + ret = __blk_end_request(req, 0, brq->data.bytes_xfered); spin_unlock_irq(&md->lock); }
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 6413afa..4222e1a 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -56,7 +56,7 @@ static int mmc_queue_thread(void *d) 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) { @@ -97,10 +97,25 @@ static void mmc_request(struct request_queue *q) return; }
- if (!mq->req) + if (!mq->mqrq_cur->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; +} + /** * mmc_init_queue - initialise a queue structure. * @mq: mmc queue @@ -116,6 +131,7 @@ 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];
if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) limit = *mmc_dev(host)->dma_mask; @@ -125,8 +141,9 @@ 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)); + mq->mqrq_cur = mqrq_cur; 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); @@ -155,53 +172,44 @@ 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 buffer\n", + "allocate bounce cur buffer\n", mmc_card_name(card)); } }
- if (mq->bounce_buf) { + if (mqrq_cur->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; - } - sg_init_table(mq->bounce_sg, bouncesz / 512); + } } #endif
- if (!mq->bounce_buf) { + if (!mqrq_cur->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; - } - sg_init_table(mq->sg, host->max_segs); + }
sema_init(&mq->thread_sem, 1); @@ -216,16 +224,15 @@ 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; + 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; + blk_cleanup_queue(mq->queue); return ret; } @@ -234,6 +241,7 @@ 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;
/* Make sure the queue isn't suspended, as that will deadlock */ mmc_queue_resume(mq); @@ -247,16 +255,14 @@ 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(mq->sg); - mq->sg = NULL; + kfree(mqrq_cur->sg); + mqrq_cur->sg = NULL;
- if (mq->bounce_buf) - kfree(mq->bounce_buf); - mq->bounce_buf = NULL; + kfree(mqrq_cur->bounce_buf); + mqrq_cur->bounce_buf = NULL;
mq->card = NULL; } @@ -309,27 +315,27 @@ 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 +344,30 @@ 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); } - diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index 6223ef8..c1a69ac 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -4,19 +4,33 @@ 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_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[1]; + struct mmc_queue_req *mqrq_cur; };
extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *, @@ -25,8 +39,9 @@ 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
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 Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/card/block.c | 218 ++++++++++++++++++++++++---------------------- 1 files changed, 114 insertions(+), 104 deletions(-)
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 88bcc4e..a0a76f4 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -812,12 +812,15 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq, R1_CC_ERROR | /* Card controller error */ \ R1_ERROR) /* General/unknown error */
-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, retry = 0;
/* * Reliable writes are used to implement Forced Unit Access and @@ -828,119 +831,126 @@ 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 { - u32 readcmd, writecmd; - - 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, retry = 0; + + do { + 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);
Break out code without functional changes. This simplifies the code and makes way for handle two parallel request.
Signed-off-by: Per Forlin per.forlin@linaro.org Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/card/block.c | 220 +++++++++++++++++++++++++++------------------- 1 files changed, 131 insertions(+), 89 deletions(-)
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index a0a76f4..7ed2c68 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -106,6 +106,16 @@ struct mmc_blk_data {
static DEFINE_MUTEX(open_lock);
+enum mmc_blk_status { + MMC_BLK_SUCCESS = 0, + MMC_BLK_PARTIAL, + MMC_BLK_RETRY, + MMC_BLK_RETRY_SINGLE, + MMC_BLK_DATA_ERR, + MMC_BLK_CMD_ERR, + MMC_BLK_ABORT, +}; + module_param(perdev_minors, int, 0444); MODULE_PARM_DESC(perdev_minors, "Minors numbers to allocate per device");
@@ -812,6 +822,95 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq, R1_CC_ERROR | /* Card controller error */ \ R1_ERROR) /* General/unknown error */
+int mmc_blk_err_check(struct mmc_blk_request *brq, + struct request *req, + struct mmc_card *card, + struct mmc_blk_data *md) +{ + int ret = MMC_BLK_SUCCESS; + + /* + * sbc.error indicates a problem with the set block count + * command. No data will have been transferred. + * + * cmd.error indicates a problem with the r/w command. No + * data will have been transferred. + * + * stop.error indicates a problem with the stop command. Data + * may have been transferred, or may still be transferring. + */ + if (brq->sbc.error || brq->cmd.error || brq->stop.error) { + switch (mmc_blk_cmd_recovery(card, req, brq)) { + case ERR_RETRY: + return MMC_BLK_RETRY; + case ERR_ABORT: + return MMC_BLK_ABORT; + case ERR_CONTINUE: + break; + } + } + + /* + * Check for errors relating to the execution of the + * initial command - such as address errors. No data + * has been transferred. + */ + if (brq->cmd.resp[0] & CMD_ERRORS) { + pr_err("%s: r/w command failed, status = %#x\n", + req->rq_disk->disk_name, brq->cmd.resp[0]); + return MMC_BLK_ABORT; + } + + /* + * Everything else is either success, or a data error of some + * kind. If it was a write, we may have transitioned to + * program mode, which we have to wait for it to complete. + */ + if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) { + u32 status; + do { + int err = get_card_status(card, &status, 5); + if (err) { + printk(KERN_ERR "%s: error %d requesting status\n", + req->rq_disk->disk_name, err); + return MMC_BLK_CMD_ERR; + } + /* + * Some cards mishandle the status bits, + * so make sure to check both the busy + * indication and the card state. + */ + } while (!(status & R1_READY_FOR_DATA) || + (R1_CURRENT_STATE(status) == R1_STATE_PRG)); + } + + if (brq->data.error) { + pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n", + req->rq_disk->disk_name, brq->data.error, + (unsigned)blk_rq_pos(req), + (unsigned)blk_rq_sectors(req), + brq->cmd.resp[0], brq->stop.resp[0]); + + if (rq_data_dir(req) == READ) { + if (brq->data.blocks > 1) { + /* Redo read one sector at a time */ + pr_warning("%s: retrying using single block read\n", + req->rq_disk->disk_name); + return MMC_BLK_RETRY_SINGLE; + } + return MMC_BLK_DATA_ERR; + } else { + return MMC_BLK_CMD_ERR; + } + } + + if (ret == MMC_BLK_SUCCESS && + blk_rq_bytes(req) != brq->data.bytes_xfered) + ret = MMC_BLK_PARTIAL; + + return ret; +} + static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, struct mmc_card *card, int disable_multi, @@ -948,6 +1047,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) struct mmc_card *card = md->queue.card; struct mmc_blk_request *brq = &mq->mqrq_cur->brq; int ret = 1, disable_multi = 0, retry = 0; + enum mmc_blk_status status;
do { mmc_blk_rw_rq_prep(mq->mqrq_cur, card, disable_multi, mq); @@ -955,99 +1055,41 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req)
mmc_queue_bounce_post(mq->mqrq_cur);
- /* - * sbc.error indicates a problem with the set block count - * command. No data will have been transferred. - * - * cmd.error indicates a problem with the r/w command. No - * data will have been transferred. - * - * stop.error indicates a problem with the stop command. Data - * may have been transferred, or may still be transferring. - */ - if (brq->sbc.error || brq->cmd.error || brq->stop.error) { - switch (mmc_blk_cmd_recovery(card, req, brq)) { - case ERR_RETRY: - if (retry++ < 5) - continue; - case ERR_ABORT: - goto cmd_abort; - case ERR_CONTINUE: + status = mmc_blk_err_check(brq, req, card, md); + switch (status) { + 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); + break; + case MMC_BLK_CMD_ERR: + goto cmd_err; + case MMC_BLK_RETRY_SINGLE: + disable_multi = 1; + break; + case MMC_BLK_RETRY: + if (retry++ < 5) break; - } - } - - /* - * Check for errors relating to the execution of the - * initial command - such as address errors. No data - * has been transferred. - */ - if (brq->cmd.resp[0] & CMD_ERRORS) { - pr_err("%s: r/w command failed, status = %#x\n", - req->rq_disk->disk_name, brq->cmd.resp[0]); + case MMC_BLK_ABORT: goto cmd_abort; + case MMC_BLK_DATA_ERR: + /* + * After an error, we redo I/O one sector at a + * time, so we only reach here after trying to + * read a single sector. + */ + spin_lock_irq(&md->lock); + ret = __blk_end_request(req, -EIO, + brq->data.blksz); + spin_unlock_irq(&md->lock); + break; }
- /* - * Everything else is either success, or a data error of some - * kind. If it was a write, we may have transitioned to - * program mode, which we have to wait for it to complete. - */ - if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) { - u32 status; - do { - int err = get_card_status(card, &status, 5); - if (err) { - printk(KERN_ERR "%s: error %d requesting status\n", - req->rq_disk->disk_name, err); - goto cmd_err; - } - /* - * Some cards mishandle the status bits, - * so make sure to check both the busy - * indication and the card state. - */ - } while (!(status & R1_READY_FOR_DATA) || - (R1_CURRENT_STATE(status) == R1_STATE_PRG)); - } - - if (brq->data.error) { - pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n", - req->rq_disk->disk_name, brq->data.error, - (unsigned)blk_rq_pos(req), - (unsigned)blk_rq_sectors(req), - brq->cmd.resp[0], brq->stop.resp[0]); - - if (rq_data_dir(req) == READ) { - if (brq->data.blocks > 1) { - /* Redo read one sector at a time */ - pr_warning("%s: retrying using single block read\n", - req->rq_disk->disk_name); - disable_multi = 1; - continue; - } - - /* - * After an error, we redo I/O one sector at a - * time, so we only reach here after trying to - * read a single sector. - */ - spin_lock_irq(&md->lock); - ret = __blk_end_request(req, -EIO, - brq->data.blksz); - spin_unlock_irq(&md->lock); - continue; - } else { - goto cmd_err; - } - } - - /* - * 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); } while (ret);
return 1;
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 Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@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 4222e1a..d69d954 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -132,6 +132,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, 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; @@ -142,7 +143,9 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, 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); @@ -178,9 +181,17 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, "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); @@ -195,11 +206,19 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, 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)); @@ -210,6 +229,10 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, 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); @@ -226,6 +249,8 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, 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); @@ -233,6 +258,11 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, 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; } @@ -242,6 +272,7 @@ 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); @@ -264,6 +295,15 @@ 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 c1a69ac..1a637d2 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 *,
This simple fault injection proved to be very useful to test the error handling in the block.c rw_rq(). It may still be useful to test if the host driver handle pre_req() and post_req() correctly in case of errors.
Signed-off-by: Per Forlin per.forlin@linaro.org Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/core/core.c | 54 ++++++++++++++++++++++++++++++++++++++++++++ drivers/mmc/core/debugfs.c | 5 ++++ include/linux/mmc/host.h | 3 ++ lib/Kconfig.debug | 11 +++++++++ 4 files changed, 73 insertions(+), 0 deletions(-)
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index d2d7239..62a8cc7 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -23,6 +23,8 @@ #include <linux/log2.h> #include <linux/regulator/consumer.h> #include <linux/pm_runtime.h> +#include <linux/fault-inject.h> +#include <linux/random.h>
#include <linux/mmc/card.h> #include <linux/mmc/host.h> @@ -82,6 +84,56 @@ static void mmc_flush_scheduled_work(void) flush_workqueue(workqueue); }
+#ifdef CONFIG_FAIL_MMC_REQUEST + +static DECLARE_FAULT_ATTR(fail_mmc_request); + +static int __init setup_fail_mmc_request(char *str) +{ + return setup_fault_attr(&fail_mmc_request, str); +} +__setup("fail_mmc_request=", setup_fail_mmc_request); + +static void mmc_should_fail_request(struct mmc_host *host, + struct mmc_request *mrq) +{ + struct mmc_command *cmd = mrq->cmd; + struct mmc_data *data = mrq->data; + static const int data_errors[] = { + -ETIMEDOUT, + -EILSEQ, + -EIO, + }; + + if (!data) + return; + + if (cmd->error || data->error || !host->make_it_fail || + !should_fail(&fail_mmc_request, data->blksz * data->blocks)) + return; + + data->error = data_errors[random32() % ARRAY_SIZE(data_errors)]; + data->bytes_xfered = (random32() % (data->bytes_xfered >> 9)) << 9; +} + +static int __init fail_mmc_request_debugfs(void) +{ + return init_fault_attr_dentries(&fail_mmc_request, + "fail_mmc_request"); +} + +late_initcall(fail_mmc_request_debugfs); + +#else /* CONFIG_FAIL_MMC_REQUEST */ + +static void mmc_should_fail_request(struct mmc_host *host, + struct mmc_request *mrq) +{ +} + +#endif /* CONFIG_FAIL_MMC_REQUEST */ + + /** * mmc_request_done - finish processing an MMC request * @host: MMC host which completed request @@ -108,6 +160,8 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq) cmd->error = 0; host->ops->request(host, mrq); } else { + mmc_should_fail_request(host, mrq); + led_trigger_event(host->led, LED_OFF);
pr_debug("%s: req done (CMD%u): %d: %08x %08x %08x %08x\n", diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c index 998797e..588e76f 100644 --- a/drivers/mmc/core/debugfs.c +++ b/drivers/mmc/core/debugfs.c @@ -188,6 +188,11 @@ void mmc_add_host_debugfs(struct mmc_host *host) root, &host->clk_delay)) goto err_node; #endif +#ifdef CONFIG_FAIL_MMC_REQUEST + if (!debugfs_create_u8("make-it-fail", S_IRUSR | S_IWUSR, + root, &host->make_it_fail)) + goto err_node; +#endif return;
err_node: diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 59db6f2..0d0a48f 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -301,6 +301,9 @@ struct mmc_host {
struct mmc_async_req *areq; /* active async req */
+#ifdef CONFIG_FAIL_MMC_REQUEST + u8 make_it_fail; +#endif unsigned long private[0] ____cacheline_aligned; };
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c768bcd..330fc70 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1057,6 +1057,17 @@ config FAIL_IO_TIMEOUT Only works with drivers that use the generic timeout handling, for others it wont do anything.
+config FAIL_MMC_REQUEST + bool "Fault-injection capability for MMC IO" + select DEBUG_FS + depends on FAULT_INJECTION + help + Provide fault-injection capability for MMC IO. + This will make the mmc core return data errors. This is + useful for testing the error handling in the mmc block device + and how the mmc host driver handle retries from + the block device. + config FAULT_INJECTION_DEBUG_FS bool "Debugfs entries for fault-injection capabilities" depends on FAULT_INJECTION && SYSFS && DEBUG_FS
This patch prevents mmc core to be built as a module if mmc fault injection is selected.
Changes needed to resolve this: * remove fault inject module from core.c * export should_fail() and init_fault_attr_dentries() in fault-injection.c * update documentation fault-injection.txt
On 1 July 2011 18:55, Per Forlin per.forlin@linaro.org wrote:
This simple fault injection proved to be very useful to test the error handling in the block.c rw_rq(). It may still be useful to test if the host driver handle pre_req() and post_req() correctly in case of errors.
Signed-off-by: Per Forlin per.forlin@linaro.org Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org
drivers/mmc/core/core.c | 54 ++++++++++++++++++++++++++++++++++++++++++++ drivers/mmc/core/debugfs.c | 5 ++++ include/linux/mmc/host.h | 3 ++ lib/Kconfig.debug | 11 +++++++++ 4 files changed, 73 insertions(+), 0 deletions(-)
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index d2d7239..62a8cc7 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -23,6 +23,8 @@ #include <linux/log2.h> #include <linux/regulator/consumer.h> #include <linux/pm_runtime.h> +#include <linux/fault-inject.h> +#include <linux/random.h>
#include <linux/mmc/card.h> #include <linux/mmc/host.h> @@ -82,6 +84,56 @@ static void mmc_flush_scheduled_work(void) flush_workqueue(workqueue); }
+#ifdef CONFIG_FAIL_MMC_REQUEST
+static DECLARE_FAULT_ATTR(fail_mmc_request);
+static int __init setup_fail_mmc_request(char *str) +{
- return setup_fault_attr(&fail_mmc_request, str);
+} +__setup("fail_mmc_request=", setup_fail_mmc_request);
+static void mmc_should_fail_request(struct mmc_host *host,
- struct mmc_request *mrq)
+{
- struct mmc_command *cmd = mrq->cmd;
- struct mmc_data *data = mrq->data;
- static const int data_errors[] = {
- -ETIMEDOUT,
- -EILSEQ,
- -EIO,
- };
- if (!data)
- return;
- if (cmd->error || data->error || !host->make_it_fail ||
- !should_fail(&fail_mmc_request, data->blksz * data->blocks))
- return;
- data->error = data_errors[random32() % ARRAY_SIZE(data_errors)];
- data->bytes_xfered = (random32() % (data->bytes_xfered >> 9)) << 9;
+}
+static int __init fail_mmc_request_debugfs(void) +{
- return init_fault_attr_dentries(&fail_mmc_request,
- "fail_mmc_request");
+}
+late_initcall(fail_mmc_request_debugfs);
This line prevents mmc core to be built as a module, since there will be two init_module (the mmc core one and this one) for the same module.
+#else /* CONFIG_FAIL_MMC_REQUEST */
+static void mmc_should_fail_request(struct mmc_host *host,
- struct mmc_request *mrq)
+{ +}
+static int __init fail_mmc_request_debugfs(void) +{ +} Add fail_mmc_request_debugfs here and call it from mmc_init()
+#endif /* CONFIG_FAIL_MMC_REQUEST */
/** * mmc_request_done - finish processing an MMC request * @host: MMC host which completed request @@ -108,6 +160,8 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq) cmd->error = 0; host->ops->request(host, mrq); } else {
- mmc_should_fail_request(host, mrq);
led_trigger_event(host->led, LED_OFF);
pr_debug("%s: req done (CMD%u): %d: %08x %08x %08x %08x\n", diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c index 998797e..588e76f 100644 --- a/drivers/mmc/core/debugfs.c +++ b/drivers/mmc/core/debugfs.c @@ -188,6 +188,11 @@ void mmc_add_host_debugfs(struct mmc_host *host) root, &host->clk_delay)) goto err_node; #endif +#ifdef CONFIG_FAIL_MMC_REQUEST
- if (!debugfs_create_u8("make-it-fail", S_IRUSR | S_IWUSR,
- root, &host->make_it_fail))
- goto err_node;
+#endif return;
err_node: diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 59db6f2..0d0a48f 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -301,6 +301,9 @@ struct mmc_host {
struct mmc_async_req *areq; /* active async req */
+#ifdef CONFIG_FAIL_MMC_REQUEST
- u8 make_it_fail;
+#endif unsigned long private[0] ____cacheline_aligned; };
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c768bcd..330fc70 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1057,6 +1057,17 @@ config FAIL_IO_TIMEOUT Only works with drivers that use the generic timeout handling, for others it wont do anything.
+config FAIL_MMC_REQUEST
- bool "Fault-injection capability for MMC IO"
- select DEBUG_FS
- depends on FAULT_INJECTION
depends on FAULT_INJECTION && MMC
- help
- Provide fault-injection capability for MMC IO.
- This will make the mmc core return data errors. This is
- useful for testing the error handling in the mmc block device
- and how the mmc host driver handle retries from
- the block device.
and test how the mmc host driver handle retries from
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 Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Venkatraman S svenkatr@ti.com Tested-by: Sourav Poddarsourav.poddar@ti.com Tested-by: Linus Walleij linus.walleij@linaro.org --- drivers/mmc/card/block.c | 86 ++++++++++++++++++++++++++++++++++++++-------- drivers/mmc/card/queue.c | 17 ++++++--- drivers/mmc/card/queue.h | 1 + 3 files changed, 84 insertions(+), 20 deletions(-)
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 7ed2c68..38d0149 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -822,12 +822,14 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq, R1_CC_ERROR | /* Card controller error */ \ R1_ERROR) /* General/unknown error */
-int 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) { - int ret = MMC_BLK_SUCCESS; + 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;
/* * sbc.error indicates a problem with the set block count @@ -1038,24 +1040,41 @@ 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, retry = 0; enum mmc_blk_status status; + struct mmc_queue_req *mq_rq; + struct request *req; + struct mmc_async_req *areq;
- do { - mmc_blk_rw_rq_prep(mq->mqrq_cur, card, disable_multi, mq); - mmc_wait_for_req(card->host, &brq->mrq); + if (!rqc && !mq->mqrq_prev->req) + return 0;
- mmc_queue_bounce_post(mq->mqrq_cur); + do { + 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) + return 0; + + 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);
- status = mmc_blk_err_check(brq, req, card, md); switch (status) { case MMC_BLK_SUCCESS: case MMC_BLK_PARTIAL: @@ -1066,6 +1085,19 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) ret = __blk_end_request(req, 0, brq->data.bytes_xfered); spin_unlock_irq(&md->lock); + if (status == MMC_BLK_SUCCESS && ret) { + /* + * The blk_end_request has returned non zero + * even though all data is transfered and no + * erros returned by host. + * If this happen it's a bug. + */ + printk(KERN_ERR "%s BUG rq_tot %d d_xfer %d\n", + __func__, blk_rq_bytes(req), + brq->data.bytes_xfered); + rqc = NULL; + goto cmd_abort; + } break; case MMC_BLK_CMD_ERR: goto cmd_err; @@ -1087,9 +1119,19 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) ret = __blk_end_request(req, -EIO, brq->data.blksz); spin_unlock_irq(&md->lock); + if (!ret) + goto start_new_req; break; }
+ if (ret) { + /* + * In case of a none complete request + * prepare it again and resend. + */ + 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; @@ -1124,6 +1166,12 @@ 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; }
@@ -1133,26 +1181,34 @@ 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) { + /* complete ongoing async transfer before issuing discard */ + if (card->host->areq) + mmc_blk_issue_rw_rq(mq, NULL); 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 d69d954..8c51a54 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 1a637d2..d2a1eb4 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 {
Hi Per,
On Fri, Jul 01 2011, Per Forlin wrote:
How significant is the cache maintenance over head? It depends, the eMMC are much faster now compared to a few years ago and cache maintenance cost more due to multiple cache levels and speculative cache pre-fetch. In relation the cost for handling the caches have increased and is now a bottle neck dealing with fast eMMC together with DMA.
Thanks very much, I've pushed v9 of the patchset to mmc-next for 3.1 (after fixing some merge conflicts against Adrian Hunter's recent patches and rewording some of the commit message texts).
- Chris.
I'm not sure who's responsible for this, but the nonblocking MMC stuff is broken on OMAPs HSMMC:
mmcblk0: error -84 transferring data, sector 149201, nr 64, cmd response 0x900, card status 0xb00 mmcblk0: retrying using single block read ------------[ cut here ]------------ WARNING: at /home/rmk/git/linux-2.6-rmk/lib/dma-debug.c:811 check_unmap+0x1ac/0x764() omap_hsmmc omap_hsmmc.0: DMA-API: device driver tries to free DMA memory it has not allocated [device address=0x0000000080933000] [size=20480 bytes] Modules linked in: Backtrace: [<c0017874>] (dump_backtrace+0x0/0x10c) from [<c02ce8ac>] (dump_stack+0x18/0x1c) r7:c1abfcb8 r6:c0186248 r5:c037de51 r4:0000032b [<c02ce894>] (dump_stack+0x0/0x1c) from [<c0039ed4>] (warn_slowpath_common+0x58/0x70) [<c0039e7c>] (warn_slowpath_common+0x0/0x70) from [<c0039f90>] (warn_slowpath_fmt+0x38/0x40) r8:c1abfd50 r7:00000000 r6:00005000 r5:00000000 r4:80933000 [<c0039f58>] (warn_slowpath_fmt+0x0/0x40) from [<c0186248>] (check_unmap+0x1ac/0x764) r3:c0367d55 r2:c037e24d [<c018609c>] (check_unmap+0x0/0x764) from [<c0186978>] (debug_dma_unmap_sg+0x100/0x134) [<c0186878>] (debug_dma_unmap_sg+0x0/0x134) from [<c0019770>] (dma_unmap_sg+0x24/0x7c) [<c001974c>] (dma_unmap_sg+0x0/0x7c) from [<c0207220>] (omap_hsmmc_post_req+0x48/0x54) [<c02071d8>] (omap_hsmmc_post_req+0x0/0x54) from [<c01fb644>] (mmc_start_req+0x9c/0x128) r4:c1a76000 [<c01fb5a8>] (mmc_start_req+0x0/0x128) from [<c02049fc>] (mmc_blk_issue_rw_rq+0x80/0x460) r8:c1ab5c00 r7:00000001 r6:c1ab5824 r5:c1ab5824 r4:c1ab5c00 [<c020497c>] (mmc_blk_issue_rw_rq+0x0/0x460) from [<c02050a8>] (mmc_blk_issue_rq+0x2cc/0x2fc) [<c0204ddc>] (mmc_blk_issue_rq+0x0/0x2fc) from [<c02056c4>] (mmc_queue_thread+0xa0/0x104) [<c0205624>] (mmc_queue_thread+0x0/0x104) from [<c0054f8c>] (kthread+0x88/0x90) [<c0054f04>] (kthread+0x0/0x90) from [<c003d9a4>] (do_exit+0x0/0x618) r7:00000013 r6:c003d9a4 r5:c0054f04 r4:c1a7bc7c ---[ end trace 3314ad56daf5d14f ]---
Luckily thinks continue to work, but clearly releasing DMA mappings which drivers don't own is bad news. Unfortunately, I don't have the bandwidth to be able to investigate this at present - well, I could do but then I'd have to drop working on the OMAP4 vs generic suspend/resume code and learn about something I've no current clue about.
Can someone please investigate and fix whatever is broken.
+ Balaji,
On Friday 26 August 2011 09:49 PM, Russell King - ARM Linux wrote:
I'm not sure who's responsible for this, but the nonblocking MMC stuff is broken on OMAPs HSMMC:
mmcblk0: error -84 transferring data, sector 149201, nr 64, cmd response 0x900, card status 0xb00 mmcblk0: retrying using single block read ------------[ cut here ]------------ WARNING: at /home/rmk/git/linux-2.6-rmk/lib/dma-debug.c:811 check_unmap+0x1ac/0x764() omap_hsmmc omap_hsmmc.0: DMA-API: device driver tries to free DMA memory it has not allocated [device address=0x0000000080933000] [size=20480 bytes] Modules linked in: Backtrace: [<c0017874>] (dump_backtrace+0x0/0x10c) from [<c02ce8ac>] (dump_stack+0x18/0x1c) r7:c1abfcb8 r6:c0186248 r5:c037de51 r4:0000032b [<c02ce894>] (dump_stack+0x0/0x1c) from [<c0039ed4>] (warn_slowpath_common+0x58/0x70) [<c0039e7c>] (warn_slowpath_common+0x0/0x70) from [<c0039f90>] (warn_slowpath_fmt+0x38/0x40) r8:c1abfd50 r7:00000000 r6:00005000 r5:00000000 r4:80933000 [<c0039f58>] (warn_slowpath_fmt+0x0/0x40) from [<c0186248>] (check_unmap+0x1ac/0x764) r3:c0367d55 r2:c037e24d [<c018609c>] (check_unmap+0x0/0x764) from [<c0186978>] (debug_dma_unmap_sg+0x100/0x134) [<c0186878>] (debug_dma_unmap_sg+0x0/0x134) from [<c0019770>] (dma_unmap_sg+0x24/0x7c) [<c001974c>] (dma_unmap_sg+0x0/0x7c) from [<c0207220>] (omap_hsmmc_post_req+0x48/0x54) [<c02071d8>] (omap_hsmmc_post_req+0x0/0x54) from [<c01fb644>] (mmc_start_req+0x9c/0x128) r4:c1a76000 [<c01fb5a8>] (mmc_start_req+0x0/0x128) from [<c02049fc>] (mmc_blk_issue_rw_rq+0x80/0x460) r8:c1ab5c00 r7:00000001 r6:c1ab5824 r5:c1ab5824 r4:c1ab5c00 [<c020497c>] (mmc_blk_issue_rw_rq+0x0/0x460) from [<c02050a8>] (mmc_blk_issue_rq+0x2cc/0x2fc) [<c0204ddc>] (mmc_blk_issue_rq+0x0/0x2fc) from [<c02056c4>] (mmc_queue_thread+0xa0/0x104) [<c0205624>] (mmc_queue_thread+0x0/0x104) from [<c0054f8c>] (kthread+0x88/0x90) [<c0054f04>] (kthread+0x0/0x90) from [<c003d9a4>] (do_exit+0x0/0x618) r7:00000013 r6:c003d9a4 r5:c0054f04 r4:c1a7bc7c ---[ end trace 3314ad56daf5d14f ]---
Luckily thinks continue to work, but clearly releasing DMA mappings which drivers don't own is bad news. Unfortunately, I don't have the bandwidth to be able to investigate this at present - well, I could do but then I'd have to drop working on the OMAP4 vs generic suspend/resume code and learn about something I've no current clue about.
Please continue your help on generic suspend.
Can someone please investigate and fix whatever is broken.
Will find somebody to look at this issue.
Regards Santosh
On 26 August 2011 18:28, Santosh santosh.shilimkar@ti.com wrote:
- Balaji,
On Friday 26 August 2011 09:49 PM, Russell King - ARM Linux wrote:
I'm not sure who's responsible for this, but the nonblocking MMC stuff is broken on OMAPs HSMMC:
mmcblk0: error -84 transferring data, sector 149201, nr 64, cmd response 0x900, card status 0xb00 mmcblk0: retrying using single block read ------------[ cut here ]------------ WARNING: at /home/rmk/git/linux-2.6-rmk/lib/dma-debug.c:811 check_unmap+0x1ac/0x764() omap_hsmmc omap_hsmmc.0: DMA-API: device driver tries to free DMA memory it has not allocated [device address=0x0000000080933000] [size=20480 bytes] Modules linked in: Backtrace: [<c0017874>] (dump_backtrace+0x0/0x10c) from [<c02ce8ac>] (dump_stack+0x18/0x1c) r7:c1abfcb8 r6:c0186248 r5:c037de51 r4:0000032b [<c02ce894>] (dump_stack+0x0/0x1c) from [<c0039ed4>] (warn_slowpath_common+0x58/0x70) [<c0039e7c>] (warn_slowpath_common+0x0/0x70) from [<c0039f90>] (warn_slowpath_fmt+0x38/0x40) r8:c1abfd50 r7:00000000 r6:00005000 r5:00000000 r4:80933000 [<c0039f58>] (warn_slowpath_fmt+0x0/0x40) from [<c0186248>] (check_unmap+0x1ac/0x764) r3:c0367d55 r2:c037e24d [<c018609c>] (check_unmap+0x0/0x764) from [<c0186978>] (debug_dma_unmap_sg+0x100/0x134) [<c0186878>] (debug_dma_unmap_sg+0x0/0x134) from [<c0019770>] (dma_unmap_sg+0x24/0x7c) [<c001974c>] (dma_unmap_sg+0x0/0x7c) from [<c0207220>] (omap_hsmmc_post_req+0x48/0x54) [<c02071d8>] (omap_hsmmc_post_req+0x0/0x54) from [<c01fb644>] (mmc_start_req+0x9c/0x128) r4:c1a76000 [<c01fb5a8>] (mmc_start_req+0x0/0x128) from [<c02049fc>] (mmc_blk_issue_rw_rq+0x80/0x460) r8:c1ab5c00 r7:00000001 r6:c1ab5824 r5:c1ab5824 r4:c1ab5c00 [<c020497c>] (mmc_blk_issue_rw_rq+0x0/0x460) from [<c02050a8>] (mmc_blk_issue_rq+0x2cc/0x2fc) [<c0204ddc>] (mmc_blk_issue_rq+0x0/0x2fc) from [<c02056c4>] (mmc_queue_thread+0xa0/0x104) [<c0205624>] (mmc_queue_thread+0x0/0x104) from [<c0054f8c>] (kthread+0x88/0x90) [<c0054f04>] (kthread+0x0/0x90) from [<c003d9a4>] (do_exit+0x0/0x618) r7:00000013 r6:c003d9a4 r5:c0054f04 r4:c1a7bc7c ---[ end trace 3314ad56daf5d14f ]---
Luckily thinks continue to work, but clearly releasing DMA mappings which drivers don't own is bad news. Unfortunately, I don't have the bandwidth to be able to investigate this at present - well, I could do but then I'd have to drop working on the OMAP4 vs generic suspend/resume code and learn about something I've no current clue about.
Please continue your help on generic suspend.
Can someone please investigate and fix whatever is broken.
Will find somebody to look at this issue.
I had a look at this and my guess is that the same mapped DMA memory is unmapped twice. First the memory is unmapped in omap_hsmmc_dma_cleanup() due to the mmc error, then later in omap_hsmmc_post_req(). Here is a patch to resolve that. I haven't had the chance to test it yet though.
--- drivers/mmc/host/omap_hsmmc.c | 7 +++++-- 1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 21e4a79..7f40767 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1011,6 +1011,7 @@ static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno) host->data->sg_len, omap_hsmmc_get_dma_dir(host, host->data)); omap_free_dma(dma_ch); + data->host_cookie = 0; } host->data = NULL; } @@ -1576,8 +1577,10 @@ static void omap_hsmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq, struct mmc_data *data = mrq->data;
if (host->use_dma) { - dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, - omap_hsmmc_get_dma_dir(host, data)); + if (data->host_cookie) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, + data->sg_len, + omap_hsmmc_get_dma_dir(host, data)); data->host_cookie = 0;
I also checked the mmci code for this same issue and mmci doesn't have the same bug. MMCI works fine in 3.1-rc2 even though the code is "wrong". I propose this change. @@ -529,7 +529,7 @@ static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq, if (chan) { if (err) dmaengine_terminate_all(chan); - if (err || data->host_cookie) + if (data->host_cookie)
I'll post these patches as soon as I have managed to test them or sooner if I get a tested-by.
Regards, Per
On Sun, Aug 28, 2011 at 12:50:54PM +0200, Per Forlin wrote:
On 26 August 2011 18:28, Santosh santosh.shilimkar@ti.com wrote:
- Balaji,
On Friday 26 August 2011 09:49 PM, Russell King - ARM Linux wrote:
I'm not sure who's responsible for this, but the nonblocking MMC stuff is broken on OMAPs HSMMC:
mmcblk0: error -84 transferring data, sector 149201, nr 64, cmd response 0x900, card status 0xb00 mmcblk0: retrying using single block read ------------[ cut here ]------------ WARNING: at /home/rmk/git/linux-2.6-rmk/lib/dma-debug.c:811 check_unmap+0x1ac/0x764() omap_hsmmc omap_hsmmc.0: DMA-API: device driver tries to free DMA memory it has not allocated [device address=0x0000000080933000] [size=20480 bytes] Modules linked in: Backtrace: [<c0017874>] (dump_backtrace+0x0/0x10c) from [<c02ce8ac>] (dump_stack+0x18/0x1c) r7:c1abfcb8 r6:c0186248 r5:c037de51 r4:0000032b [<c02ce894>] (dump_stack+0x0/0x1c) from [<c0039ed4>] (warn_slowpath_common+0x58/0x70) [<c0039e7c>] (warn_slowpath_common+0x0/0x70) from [<c0039f90>] (warn_slowpath_fmt+0x38/0x40) r8:c1abfd50 r7:00000000 r6:00005000 r5:00000000 r4:80933000 [<c0039f58>] (warn_slowpath_fmt+0x0/0x40) from [<c0186248>] (check_unmap+0x1ac/0x764) r3:c0367d55 r2:c037e24d [<c018609c>] (check_unmap+0x0/0x764) from [<c0186978>] (debug_dma_unmap_sg+0x100/0x134) [<c0186878>] (debug_dma_unmap_sg+0x0/0x134) from [<c0019770>] (dma_unmap_sg+0x24/0x7c) [<c001974c>] (dma_unmap_sg+0x0/0x7c) from [<c0207220>] (omap_hsmmc_post_req+0x48/0x54) [<c02071d8>] (omap_hsmmc_post_req+0x0/0x54) from [<c01fb644>] (mmc_start_req+0x9c/0x128) r4:c1a76000 [<c01fb5a8>] (mmc_start_req+0x0/0x128) from [<c02049fc>] (mmc_blk_issue_rw_rq+0x80/0x460) r8:c1ab5c00 r7:00000001 r6:c1ab5824 r5:c1ab5824 r4:c1ab5c00 [<c020497c>] (mmc_blk_issue_rw_rq+0x0/0x460) from [<c02050a8>] (mmc_blk_issue_rq+0x2cc/0x2fc) [<c0204ddc>] (mmc_blk_issue_rq+0x0/0x2fc) from [<c02056c4>] (mmc_queue_thread+0xa0/0x104) [<c0205624>] (mmc_queue_thread+0x0/0x104) from [<c0054f8c>] (kthread+0x88/0x90) [<c0054f04>] (kthread+0x0/0x90) from [<c003d9a4>] (do_exit+0x0/0x618) r7:00000013 r6:c003d9a4 r5:c0054f04 r4:c1a7bc7c ---[ end trace 3314ad56daf5d14f ]---
Luckily thinks continue to work, but clearly releasing DMA mappings which drivers don't own is bad news. Unfortunately, I don't have the bandwidth to be able to investigate this at present - well, I could do but then I'd have to drop working on the OMAP4 vs generic suspend/resume code and learn about something I've no current clue about.
Please continue your help on generic suspend.
Can someone please investigate and fix whatever is broken.
Will find somebody to look at this issue.
I had a look at this and my guess is that the same mapped DMA memory is unmapped twice. First the memory is unmapped in omap_hsmmc_dma_cleanup() due to the mmc error, then later in omap_hsmmc_post_req(). Here is a patch to resolve that. I haven't had the chance to test it yet though.
drivers/mmc/host/omap_hsmmc.c | 7 +++++-- 1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 21e4a79..7f40767 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1011,6 +1011,7 @@ static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno) host->data->sg_len, omap_hsmmc_get_dma_dir(host, host->data)); omap_free_dma(dma_ch);
data->host_cookie = 0; } host->data = NULL;
} @@ -1576,8 +1577,10 @@ static void omap_hsmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq, struct mmc_data *data = mrq->data;
if (host->use_dma) {
dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
omap_hsmmc_get_dma_dir(host, data));
if (data->host_cookie)
dma_unmap_sg(mmc_dev(host->mmc), data->sg,
data->sg_len,
omap_hsmmc_get_dma_dir(host, data)); data->host_cookie = 0;
I also checked the mmci code for this same issue and mmci doesn't have the same bug. MMCI works fine in 3.1-rc2 even though the code is "wrong". I propose this change. @@ -529,7 +529,7 @@ static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq, if (chan) { if (err) dmaengine_terminate_all(chan);
if (err || data->host_cookie)
if (data->host_cookie)
I'll post these patches as soon as I have managed to test them or sooner if I get a tested-by.
Looking at MMCI, are you sure all those DMA engine terminate calls are correct?
For example, why are we terminating all DMA engine transfers in the post request function? Surely that should've already been taken care of by the driver before it told the core that the request was completed. If the post request function is called for the previous request, meanwhile the next request is in flight, terminating the DMA engine transfer will cause invalid state in the driver.
Basically, this looks completely buggered. I think you need to review your changes with a thought to what happens logically with DMA and the MMC host drivers whenever an error occurs.
On 28 August 2011 13:11, Russell King - ARM Linux linux@arm.linux.org.uk wrote:
On Sun, Aug 28, 2011 at 12:50:54PM +0200, Per Forlin wrote:
On 26 August 2011 18:28, Santosh santosh.shilimkar@ti.com wrote:
- Balaji,
On Friday 26 August 2011 09:49 PM, Russell King - ARM Linux wrote:
I'm not sure who's responsible for this, but the nonblocking MMC stuff is broken on OMAPs HSMMC:
mmcblk0: error -84 transferring data, sector 149201, nr 64, cmd response 0x900, card status 0xb00 mmcblk0: retrying using single block read ------------[ cut here ]------------ WARNING: at /home/rmk/git/linux-2.6-rmk/lib/dma-debug.c:811 check_unmap+0x1ac/0x764() omap_hsmmc omap_hsmmc.0: DMA-API: device driver tries to free DMA memory it has not allocated [device address=0x0000000080933000] [size=20480 bytes] Modules linked in: Backtrace: [<c0017874>] (dump_backtrace+0x0/0x10c) from [<c02ce8ac>] (dump_stack+0x18/0x1c) r7:c1abfcb8 r6:c0186248 r5:c037de51 r4:0000032b [<c02ce894>] (dump_stack+0x0/0x1c) from [<c0039ed4>] (warn_slowpath_common+0x58/0x70) [<c0039e7c>] (warn_slowpath_common+0x0/0x70) from [<c0039f90>] (warn_slowpath_fmt+0x38/0x40) r8:c1abfd50 r7:00000000 r6:00005000 r5:00000000 r4:80933000 [<c0039f58>] (warn_slowpath_fmt+0x0/0x40) from [<c0186248>] (check_unmap+0x1ac/0x764) r3:c0367d55 r2:c037e24d [<c018609c>] (check_unmap+0x0/0x764) from [<c0186978>] (debug_dma_unmap_sg+0x100/0x134) [<c0186878>] (debug_dma_unmap_sg+0x0/0x134) from [<c0019770>] (dma_unmap_sg+0x24/0x7c) [<c001974c>] (dma_unmap_sg+0x0/0x7c) from [<c0207220>] (omap_hsmmc_post_req+0x48/0x54) [<c02071d8>] (omap_hsmmc_post_req+0x0/0x54) from [<c01fb644>] (mmc_start_req+0x9c/0x128) r4:c1a76000 [<c01fb5a8>] (mmc_start_req+0x0/0x128) from [<c02049fc>] (mmc_blk_issue_rw_rq+0x80/0x460) r8:c1ab5c00 r7:00000001 r6:c1ab5824 r5:c1ab5824 r4:c1ab5c00 [<c020497c>] (mmc_blk_issue_rw_rq+0x0/0x460) from [<c02050a8>] (mmc_blk_issue_rq+0x2cc/0x2fc) [<c0204ddc>] (mmc_blk_issue_rq+0x0/0x2fc) from [<c02056c4>] (mmc_queue_thread+0xa0/0x104) [<c0205624>] (mmc_queue_thread+0x0/0x104) from [<c0054f8c>] (kthread+0x88/0x90) [<c0054f04>] (kthread+0x0/0x90) from [<c003d9a4>] (do_exit+0x0/0x618) r7:00000013 r6:c003d9a4 r5:c0054f04 r4:c1a7bc7c ---[ end trace 3314ad56daf5d14f ]---
Luckily thinks continue to work, but clearly releasing DMA mappings which drivers don't own is bad news. Unfortunately, I don't have the bandwidth to be able to investigate this at present - well, I could do but then I'd have to drop working on the OMAP4 vs generic suspend/resume code and learn about something I've no current clue about.
Please continue your help on generic suspend.
Can someone please investigate and fix whatever is broken.
Will find somebody to look at this issue.
I had a look at this and my guess is that the same mapped DMA memory is unmapped twice. First the memory is unmapped in omap_hsmmc_dma_cleanup() due to the mmc error, then later in omap_hsmmc_post_req(). Here is a patch to resolve that. I haven't had the chance to test it yet though.
drivers/mmc/host/omap_hsmmc.c | 7 +++++-- 1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 21e4a79..7f40767 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1011,6 +1011,7 @@ static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno) host->data->sg_len, omap_hsmmc_get_dma_dir(host, host->data)); omap_free_dma(dma_ch);
- data->host_cookie = 0;
} host->data = NULL; } @@ -1576,8 +1577,10 @@ static void omap_hsmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq, struct mmc_data *data = mrq->data;
if (host->use_dma) {
- dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
- omap_hsmmc_get_dma_dir(host, data));
- if (data->host_cookie)
- dma_unmap_sg(mmc_dev(host->mmc), data->sg,
- data->sg_len,
- omap_hsmmc_get_dma_dir(host, data));
data->host_cookie = 0;
I also checked the mmci code for this same issue and mmci doesn't have the same bug. MMCI works fine in 3.1-rc2 even though the code is "wrong". I propose this change. @@ -529,7 +529,7 @@ static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq, if (chan) { if (err) dmaengine_terminate_all(chan);
- if (err || data->host_cookie)
- if (data->host_cookie)
I'll post these patches as soon as I have managed to test them or sooner if I get a tested-by.
Looking at MMCI, are you sure all those DMA engine terminate calls are correct?
I should probably do so together with adding better descriptions on what happens and what the intention is.
For example, why are we terminating all DMA engine transfers in the post request function?
The reason for calling DMA terminate here is to handle the case of cleaning up an MMC request that has only been prepared in mmci_pre_request(), and not been passed to mmci_request(). The if (err) is only true if that scenario has happened. The variable err may need to be better defined. I can think of three states: 1. err == no error 2. err == mmc request failed 3. err == mmc request is prepared but not started Currently "err" is only set if #3 occurs.
The parts to clean up in post_request() if #3 happens (err == true): in mmci: DMA mapped memory and prepared DMA descriptors in omap_hsmmc: DMA mapped memory
Now when I think more about I need to check the DMA drivers more closely if dma_terminate_all() will free resources for prepared but not submitted descriptors. I will have to add this support to the dma drivers if it's missing.
of by the driver before it told the core that the request was completed. If the post request function is called for the previous request, meanwhile the next request is in flight, terminating the DMA engine transfer will cause invalid state in the driver.
Basically, this looks completely buggered. I think you need to review your changes with a thought to what happens logically with DMA and the MMC host drivers whenever an error occurs.
I agree, I need to look more closely on the error handling.
Regards, Per