linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: linux-kernel@vger.kernel.org
Cc: linux-raid@vger.kernel.org, netdev@vger.kernel.org,
	maciej.sosnowski@intel.com
Subject: [PATCH 19/29] ioat1: trim ioat_dma_desc_sw
Date: Thu, 03 Sep 2009 19:32:06 -0700	[thread overview]
Message-ID: <20090904023206.32667.35974.stgit@dwillia2-linux.ch.intel.com> (raw)
In-Reply-To: <20090904022733.32667.77626.stgit@dwillia2-linux.ch.intel.com>

Save 4 bytes per software descriptor by transmitting tx_cnt in an unused
portion of the hardware descriptor.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dma/ioat/dma.c |    4 ++--
 drivers/dma/ioat/dma.h |    2 --
 drivers/dma/ioat/hw.h  |    6 +++++-
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index abc96c4..f59b6f4 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -396,7 +396,7 @@ static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
 	dump_desc_dbg(ioat, chain_tail);
 	dump_desc_dbg(ioat, first);
 
-	ioat->pending += desc->tx_cnt;
+	ioat->pending += desc->hw->tx_cnt;
 	if (ioat->pending >= ioat_pending_level)
 		__ioat1_dma_memcpy_issue_pending(ioat);
 	spin_unlock_bh(&ioat->desc_lock);
@@ -655,11 +655,11 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
 	spin_unlock_bh(&ioat->desc_lock);
 
 	desc->txd.flags = flags;
-	desc->tx_cnt = tx_cnt;
 	desc->len = total_len;
 	list_splice(&chain, &desc->txd.tx_list);
 	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
 	hw->ctl_f.compl_write = 1;
+	hw->tx_cnt = tx_cnt;
 	dump_desc_dbg(ioat, desc);
 
 	return &desc->txd;
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index e47083b..ec851cf 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -165,14 +165,12 @@ ioat_is_complete(struct dma_chan *c, dma_cookie_t cookie,
  * @hw: hardware DMA descriptor
  * @node: this descriptor will either be on the free list,
  *     or attached to a transaction list (async_tx.tx_list)
- * @tx_cnt: number of descriptors required to complete the transaction
  * @txd: the generic software descriptor for all engines
  * @id: identifier for debug
  */
 struct ioat_desc_sw {
 	struct ioat_dma_descriptor *hw;
 	struct list_head node;
-	int tx_cnt;
 	size_t len;
 	struct dma_async_tx_descriptor txd;
 	#ifdef DEBUG
diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h
index e13f3ed..7481fb1 100644
--- a/drivers/dma/ioat/hw.h
+++ b/drivers/dma/ioat/hw.h
@@ -63,7 +63,11 @@ struct ioat_dma_descriptor {
 	uint64_t	next;
 	uint64_t	rsv1;
 	uint64_t	rsv2;
-	uint64_t	user1;
+	/* store some driver data in an unused portion of the descriptor */
+	union {
+		uint64_t	user1;
+		uint64_t	tx_cnt;
+	};
 	uint64_t	user2;
 };
 #endif


  parent reply	other threads:[~2009-09-04  2:32 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-09-04  2:30 [PATCH 00/29] ioatdma: towards raid support Dan Williams
2009-09-04  2:30 ` [PATCH 01/29] ioat: move to drivers/dma/ioat/ Dan Williams
2009-09-04  2:30 ` [PATCH 02/29] ioat: move definitions to dma.h Dan Williams
2009-09-04  2:30 ` [PATCH 03/29] ioat: convert ioat_probe to pcim/devm Dan Williams
2009-09-04  2:30 ` [PATCH 04/29] ioat: cleanup some long deref chains and 80 column collisions Dan Williams
2009-09-04  2:30 ` [PATCH 05/29] ioat: kill function prototype ifdef guards Dan Williams
2009-09-04  2:31 ` [PATCH 06/29] ioat: split ioat_dma_probe into core/version-specific routines Dan Williams
2009-09-04  2:31 ` [PATCH 07/29] ioat: fix type mismatch for ->dmacount Dan Williams
2009-09-04  2:31 ` [PATCH 08/29] ioat: define descriptor control bit-field Dan Williams
2009-09-04  2:31 ` [PATCH 09/29] ioat1: move descriptor allocation from submit to prep Dan Williams
2009-09-04  2:31 ` [PATCH 10/29] ioat: fix self test interrupts Dan Williams
2009-09-04  2:31 ` [PATCH 11/29] ioat: prepare the code for ioat[12]_dma_chan split Dan Williams
2009-09-04  2:31 ` [PATCH 12/29] ioat2,3: convert to a true ring buffer Dan Williams
2009-09-04  2:31 ` [PATCH 13/29] ioat1: kill unused unmap parameters Dan Williams
2009-09-04  2:31 ` [PATCH 14/29] ioat: add some dev_dbg() calls Dan Williams
2009-09-04  2:31 ` [PATCH 15/29] ioat: cleanup completion status reads Dan Williams
2009-09-04  2:31 ` [PATCH 16/29] ioat: ignore reserved bits for chancnt and xfercap Dan Williams
2009-09-04  2:31 ` [PATCH 17/29] ioat: preserve chanctrl bits when re-arming interrupts Dan Williams
2009-09-04  2:32 ` [PATCH 18/29] ioat: ___devinit annotate the initialization paths Dan Williams
2009-09-04  2:32 ` Dan Williams [this message]
2009-09-14 14:55   ` [PATCH 19/29] ioat1: trim ioat_dma_desc_sw Sosnowski, Maciej
2009-09-04  2:32 ` [PATCH 20/29] ioat: switch watchdog and reset handler from workqueue to timer Dan Williams
2009-09-14 14:59   ` Sosnowski, Maciej
2009-09-04  2:32 ` [PATCH 21/29] ioat2,3: dynamically resize descriptor ring Dan Williams
2009-09-14 15:00   ` Sosnowski, Maciej
2009-09-15 23:07     ` Dan Williams
2009-09-04  2:32 ` [PATCH 22/29] net_dma: poll for a descriptor after allocation failure Dan Williams
2009-09-14 15:00   ` Sosnowski, Maciej
2009-09-04  2:32 ` [PATCH 23/29] dw_dmac: implement a private tx_list Dan Williams
2009-09-04  2:32 ` [PATCH 24/29] fsldma: " Dan Williams
2009-09-04 19:42   ` Dan Williams
2009-09-04  2:32 ` [PATCH 25/29] iop-adma: " Dan Williams
2009-09-04  2:32 ` [PATCH 26/29] ioat: " Dan Williams
2009-09-14 15:01   ` Sosnowski, Maciej
2009-09-04  2:32 ` [PATCH 27/29] mv_xor: " Dan Williams
2009-09-04  2:32 ` [PATCH 28/29] dmaengine: kill tx_list Dan Williams
2009-09-14 15:01   ` Sosnowski, Maciej
2009-09-04  2:32 ` [PATCH 29/29] ioat2, 3: cacheline align software descriptor allocations Dan Williams
2009-09-14 15:02   ` Sosnowski, Maciej

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=20090904023206.32667.35974.stgit@dwillia2-linux.ch.intel.com \
    --to=dan.j.williams@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=maciej.sosnowski@intel.com \
    --cc=netdev@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: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).