* [PATCH] mmci: don't flush the dcache
@ 2011-01-01 10:12 Rabin Vincent
0 siblings, 0 replies; only message in thread
From: Rabin Vincent @ 2011-01-01 10:12 UTC (permalink / raw)
To: linux-arm-kernel
Since freshly created page cache pages are considered dirty and are
always flushed before they are mapped into userspace, and an
already-mapped page will never be passed to be read into by the mmci
driver, remove the flush_dcache_page() calls.
Signed-off-by: Rabin Vincent <rabin@rab.in>
---
drivers/mmc/host/mmci.c | 19 -------------------
1 files changed, 0 insertions(+), 19 deletions(-)
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 0814b88..ccbbc18 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -284,22 +284,6 @@ mmci_data_irq(struct mmci_host *host, struct
mmc_data *data,
/* Force-complete the transaction */
host->blockend =3D true;
host->dataend =3D true;
-
- /*
- * We hit an error condition. Ensure that any data
- * partially written to a page is properly coherent.
- */
- if (data->flags & MMC_DATA_READ) {
- struct sg_mapping_iter *sg_miter =3D &host->sg_miter;
- unsigned long flags;
-
- local_irq_save(flags);
- if (sg_miter_next(sg_miter)) {
- flush_dcache_page(sg_miter->page);
- sg_miter_stop(sg_miter);
- }
- local_irq_restore(flags);
- }
}
/*
@@ -530,9 +514,6 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
if (remain)
break;
- if (status & MCI_RXACTIVE)
- flush_dcache_page(sg_miter->page);
-
status =3D readl(base + MMCISTATUS);
} while (1);
--=20
1.7.2.3
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2011-01-01 10:12 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-01-01 10:12 [PATCH] mmci: don't flush the dcache Rabin Vincent
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).