From: Bodo Stroesser <bstroesser@ts.fujitsu.com> To: martin.petersen@oracle.com, michael.christie@oracle.com, linux-scsi@vger.kernel.org, target-devel@vger.kernel.org Cc: Bodo Stroesser <bstroesser@ts.fujitsu.com> Subject: [PATCH RFC] scsi: target: tcmu: optimize use of flush_dcache_page Date: Fri, 29 May 2020 09:26:56 +0000 [thread overview] Message-ID: <20200529092656.1048-1-bstroesser@ts.fujitsu.com> (raw) (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 is 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. Therefore I changed (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). Signed-off-by: Bodo Stroesser <bstroesser@ts.fujitsu.com> --- Since I have x86 machines only, where flush_dcache_page() is empty, this patch indeed is compile tested only. Therefore it needs thorough review or ideally a test on an architecture that has a non empty flush_dcache_page(). drivers/target/target_core_user.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index cdb4848d23c6..d922a7087c31 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -676,8 +676,10 @@ 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); @@ -722,7 +724,6 @@ 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; @@ -731,8 +732,10 @@ 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, @@ -778,13 +781,13 @@ 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); -- 2.12.3
WARNING: multiple messages have this Message-ID (diff)
From: Bodo Stroesser <bstroesser@ts.fujitsu.com> To: martin.petersen@oracle.com, michael.christie@oracle.com, linux-scsi@vger.kernel.org, target-devel@vger.kernel.org Cc: Bodo Stroesser <bstroesser@ts.fujitsu.com> Subject: [PATCH RFC] scsi: target: tcmu: optimize use of flush_dcache_page Date: Fri, 29 May 2020 11:26:56 +0200 [thread overview] Message-ID: <20200529092656.1048-1-bstroesser@ts.fujitsu.com> (raw) (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 is 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. Therefore I changed (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). Signed-off-by: Bodo Stroesser <bstroesser@ts.fujitsu.com> --- Since I have x86 machines only, where flush_dcache_page() is empty, this patch indeed is compile tested only. Therefore it needs thorough review or ideally a test on an architecture that has a non empty flush_dcache_page(). drivers/target/target_core_user.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index cdb4848d23c6..d922a7087c31 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -676,8 +676,10 @@ 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); @@ -722,7 +724,6 @@ 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; @@ -731,8 +732,10 @@ 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, @@ -778,13 +781,13 @@ 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); -- 2.12.3
next reply other threads:[~2020-05-29 9:26 UTC|newest] Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-05-29 9:26 Bodo Stroesser [this message] 2020-05-29 9:26 ` [PATCH RFC] scsi: target: tcmu: optimize use of flush_dcache_page Bodo Stroesser
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20200529092656.1048-1-bstroesser@ts.fujitsu.com \ --to=bstroesser@ts.fujitsu.com \ --cc=linux-scsi@vger.kernel.org \ --cc=martin.petersen@oracle.com \ --cc=michael.christie@oracle.com \ --cc=target-devel@vger.kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.