linux.git/drivers/mmc/core/queue.c, branch v4.16-rc2

mmc: block: Remove code no longer needed after the switch to blk-mq

2017-12-11T12:02:22+00:00

Remove code no longer needed after the switch to blk-mq.

Signed-off-by: Adrian Hunter 
Acked-by: Linus Walleij 
Tested-by: Linus Walleij 
Signed-off-by: Ulf Hansson

mmc: block: make function mmc_cqe_issue_type static

2017-12-11T11:48:05+00:00

The function mmc_cqe_issue_type is local to the source and does
not need to be in global scope, so make it static.

Cleans up sparse warning:
drivers/mmc/core/queue.c:62:21: warning: symbol 'mmc_cqe_issue_type'
was not declared. Should it be static?

Signed-off-by: Colin Ian King 
Acked-by: Adrian Hunter 
Signed-off-by: Ulf Hansson

mmc: block: blk-mq: Add support for direct completion

2017-12-11T11:44:35+00:00

For blk-mq, add support for completing requests directly in the ->done
callback. That means that error handling and urgent background operations
must be handled by recovery_work in that case.

Signed-off-by: Adrian Hunter 
Acked-by: Linus Walleij 
Signed-off-by: Ulf Hansson 
Tested-by: Linus Walleij

mmc: block: Add CQE support

2017-12-11T11:44:34+00:00

Add CQE support to the block driver, including:
    - optionally using DCMD for flush requests
    - "manually" issuing discard requests
    - issuing read / write requests to the CQE
    - supporting block-layer timeouts
    - handling recovery
    - supporting re-tuning

CQE offers 25% - 50% better random multi-threaded I/O.  There is a slight
(e.g. 2%) drop in sequential read speed but no observable change to sequential
write.

CQE automatically sends the commands to complete requests.  However it only
supports reads / writes and so-called "direct commands" (DCMD).  Furthermore
DCMD is limited to one command at a time, but discards require 3 commands.
That makes issuing discards through CQE very awkward, but some CQE's don't
support DCMD anyway.  So for discards, the existing non-CQE approach is
taken, where the mmc core code issues the 3 commands one at a time i.e.
mmc_erase(). Where DCMD is used, is for issuing flushes.

Signed-off-by: Adrian Hunter 
Acked-by: Linus Walleij 
Signed-off-by: Ulf Hansson 
Tested-by: Linus Walleij

mmc: block: Add blk-mq support

2017-12-11T11:44:33+00:00

Define and use a blk-mq queue. Discards and flushes are processed
synchronously, but reads and writes asynchronously. In order to support
slow DMA unmapping, DMA unmapping is not done until after the next request
is started. That means the request is not completed until then. If there is
no next request then the completion is done by queued work.

Signed-off-by: Adrian Hunter 
Acked-by: Linus Walleij 
Signed-off-by: Ulf Hansson 
Tested-by: Linus Walleij

mmc: block: Simplify cleaning up the queue

2017-12-11T11:44:31+00:00

Use blk_cleanup_queue() to shutdown the queue when the driver is removed,
and instead get an extra reference to the queue to prevent the queue being
freed before the final mmc_blk_put().

Signed-off-by: Adrian Hunter 
Acked-by: Linus Walleij 
Signed-off-by: Ulf Hansson 
Tested-by: Linus Walleij

mmc: block: No need to export mmc_cleanup_queue()

2017-12-11T11:44:31+00:00

mmc_cleanup_queue() is not used by a different module. Do not export it.

Signed-off-by: Adrian Hunter 
Acked-by: Linus Walleij 
Signed-off-by: Ulf Hansson 
Tested-by: Linus Walleij

mmc: block: Factor out mmc_setup_queue()

2017-10-30T10:45:52+00:00

Factor out some common code that will also be used with blk-mq.

Signed-off-by: Adrian Hunter 
Reviewed-by: Linus Walleij 
Signed-off-by: Ulf Hansson

mmc: block: Delete mmc_access_rpmb()

2017-10-30T10:40:10+00:00

This function is used by the block layer queue to bail out of
requests if the current request is towards an RPMB
"block device".

This was done to avoid boot time scanning of this "block
device" which was never really a block device, thus duct-taping
over the fact that it was badly engineered.

This problem is now gone as we removed the offending RPMB block
device in another patch and replaced it with a character
device.

Cc: Tomas Winkler 
Signed-off-by: Linus Walleij 
Signed-off-by: Ulf Hansson

mmc: Delete bounce buffer handling

2017-10-04T08:22:55+00:00

In may, Steven sent a patch deleting the bounce buffer handling
and the CONFIG_MMC_BLOCK_BOUNCE option.

I chose the less invasive path of making it a runtime config
option, and we merged that successfully for kernel v4.12.

The code is however just standing in the way and taking up
space for seemingly no gain on any systems in wide use today.

Pierre says the code was there to improve speed on TI SDHCI
controllers on certain HP laptops and possibly some Ricoh
controllers as well. Early SDHCI controllers lacked the
scatter-gather feature, which made software bounce buffers
a significant speed boost.

We are clearly talking about the list of SDHCI PCI-based
MMC/SD card readers found in the pci_ids[] list in
drivers/mmc/host/sdhci-pci-core.c.

The TI SDHCI derivative is not supported by the upstream
kernel. This leaves the Ricoh.

What we can however notice is that the x86 defconfigs in the
kernel did not enable CONFIG_MMC_BLOCK_BOUNCE option, which
means that any such laptop would have to have a custom
configured kernel to actually take advantage of this
bounce buffer speed-up. It simply seems like there was
a speed optimization for the Ricoh controllers that noone
was using. (I have not checked the distro defconfigs but
I am pretty sure the situation is the same there.)

Bounce buffers increased performance on the OMAP HSMMC
at one point, and was part of the original submission in
commit a45c6cb81647 ("[ARM] 5369/1: omap mmc: Add new
   omap hsmmc controller for 2430 and 34xx, v3")

This optimization was removed in
commit 0ccd76d4c236 ("omap_hsmmc: Implement scatter-gather
   emulation")
which found that scatter-gather emulation provided even
better performance.

The same was introduced for SDHCI in
commit 2134a922c6e7 ("sdhci: scatter-gather (ADMA) support")

I am pretty positively convinced that software
scatter-gather emulation will do for any host controller what
the bounce buffers were doing. Essentially, the bounce buffer
was a reimplementation of software scatter-gather-emulation in
the MMC subsystem, and it should be done away with.

Cc: Pierre Ossman 
Cc: Juha Yrjola 
Cc: Steven J. Hill 
Cc: Shawn Lin 
Cc: Adrian Hunter 
Suggested-by: Steven J. Hill 
Suggested-by: Shawn Lin 
Signed-off-by: Linus Walleij 
Signed-off-by: Ulf Hansson