From 3c58f737231e2c8cbf543a09d84d8c8e80e05e43 Mon Sep 17 00:00:00 2001 From: Bodo Stroesser Date: Thu, 18 Jun 2020 15:16:31 +0200 Subject: scsi: target: tcmu: Optimize use of flush_dcache_page (scatter|gather)_data_area() need to flush dcache after writing data to or before reading data from a page in uio data area. The two routines are able to handle data transfer to/from such a page in fragments and flush the cache after each fragment was copied by calling the wrapper tcmu_flush_dcache_range(). That means: 1) flush_dcache_page() can be called multiple times for the same page. 2) Calling flush_dcache_page() indirectly using the wrapper does not make sense, because each call of the wrapper is for one single page only and the calling routine already has the correct page pointer. Change (scatter|gather)_data_area() such that, instead of calling tcmu_flush_dcache_range() before/after each memcpy, it now calls flush_dcache_page() before unmapping a page (when writing is complete for that page) or after mapping a page (when starting to read the page). After this change only calls to tcmu_flush_dcache_range() for addresses in vmalloc'ed command ring are left over. The patch was tested on ARM with kernel 4.19.118 and 5.7.2 Link: https://lore.kernel.org/r/20200618131632.32748-2-bstroesser@ts.fujitsu.com Tested-by: JiangYu Tested-by: Daniel Meyerholt Acked-by: Mike Christie Signed-off-by: Bodo Stroesser Signed-off-by: Martin K. Petersen --- drivers/target/target_core_user.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'drivers/target') diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index b38da27e033f..9c19b94698c6 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -675,8 +675,10 @@ static void scatter_data_area(struct tcmu_dev *udev, from = kmap_atomic(sg_page(sg)) + sg->offset; while (sg_remaining > 0) { if (block_remaining == 0) { - if (to) + if (to) { + flush_dcache_page(page); kunmap_atomic(to); + } block_remaining = DATA_BLOCK_SIZE; dbi = tcmu_cmd_get_dbi(tcmu_cmd); @@ -721,7 +723,6 @@ static void scatter_data_area(struct tcmu_dev *udev, memcpy(to + offset, from + sg->length - sg_remaining, copy_bytes); - tcmu_flush_dcache_range(to, copy_bytes); } sg_remaining -= copy_bytes; @@ -730,8 +731,10 @@ static void scatter_data_area(struct tcmu_dev *udev, kunmap_atomic(from - sg->offset); } - if (to) + if (to) { + flush_dcache_page(page); kunmap_atomic(to); + } } static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd, @@ -777,13 +780,13 @@ static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd, dbi = tcmu_cmd_get_dbi(cmd); page = tcmu_get_block_page(udev, dbi); from = kmap_atomic(page); + flush_dcache_page(page); } copy_bytes = min_t(size_t, sg_remaining, block_remaining); if (read_len < copy_bytes) copy_bytes = read_len; offset = DATA_BLOCK_SIZE - block_remaining; - tcmu_flush_dcache_range(from, copy_bytes); memcpy(to + sg->length - sg_remaining, from + offset, copy_bytes); -- cgit v1.2.3