From: Dave Jiang <dave.jiang@intel.com>
To: djbw@fb.com
Cc: vinod.koul@intel.com, linux-kernel@vger.kernel.org
Subject: [PATCH v2 1/5] ioatdma: Removing hw bug workaround for CB3.x .2 and earlier
Date: Wed, 10 Apr 2013 16:44:20 -0700 [thread overview]
Message-ID: <20130410234420.9082.7578.stgit@djiang5-linux2.ch.intel.com> (raw)
In-Reply-To: <20130410234230.9082.89305.stgit@djiang5-linux2.ch.intel.com>
CB3.2 and earlier hardware has silicon bugs that are no longer needed with
the new hardware. We don't have to use a NULL op to signal interrupt for
RAID ops any longer. This code make sure the legacy workarounds only happen on
legacy hardware.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
drivers/dma/ioat/dma_v3.c | 31 ++++++++++++++++++++-----------
1 file changed, 20 insertions(+), 11 deletions(-)
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index cf97e3f..6393115 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -837,6 +837,7 @@ __ioat3_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result,
{
struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
struct ioat_chan_common *chan = &ioat->base;
+ struct ioatdma_device *device = chan->device;
struct ioat_ring_ent *compl_desc;
struct ioat_ring_ent *desc;
struct ioat_ring_ent *ext;
@@ -847,6 +848,7 @@ __ioat3_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result,
u32 offset = 0;
u8 op = result ? IOAT_OP_PQ_VAL : IOAT_OP_PQ;
int i, s, idx, with_ext, num_descs;
+ int cb32 = (device->version < IOAT_VER_3_3) ? 1 : 0;
dev_dbg(to_dev(chan), "%s\n", __func__);
/* the engine requires at least two sources (we provide
@@ -872,7 +874,7 @@ __ioat3_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result,
* order.
*/
if (likely(num_descs) &&
- ioat2_check_space_lock(ioat, num_descs+1) == 0)
+ ioat2_check_space_lock(ioat, num_descs + cb32) == 0)
idx = ioat->head;
else
return NULL;
@@ -926,16 +928,23 @@ __ioat3_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result,
pq->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
dump_pq_desc_dbg(ioat, desc, ext);
- /* completion descriptor carries interrupt bit */
- compl_desc = ioat2_get_ring_ent(ioat, idx + i);
- compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
- hw = compl_desc->hw;
- hw->ctl = 0;
- hw->ctl_f.null = 1;
- hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
- hw->ctl_f.compl_write = 1;
- hw->size = NULL_DESC_BUFFER_SIZE;
- dump_desc_dbg(ioat, compl_desc);
+ if (!cb32) {
+ pq->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+ pq->ctl_f.compl_write = 1;
+ compl_desc = desc;
+ } else {
+ /* completion descriptor carries interrupt bit */
+ compl_desc = ioat2_get_ring_ent(ioat, idx + i);
+ compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
+ hw = compl_desc->hw;
+ hw->ctl = 0;
+ hw->ctl_f.null = 1;
+ hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+ hw->ctl_f.compl_write = 1;
+ hw->size = NULL_DESC_BUFFER_SIZE;
+ dump_desc_dbg(ioat, compl_desc);
+ }
+
/* we leave the channel locked to ensure in order submission */
return &compl_desc->txd;
next prev parent reply other threads:[~2013-04-10 23:44 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-10 23:44 [PATCH v2 0/5] ioatdma: Intel S1200 support patches Dave Jiang
2013-04-10 23:44 ` Dave Jiang [this message]
2013-04-10 23:44 ` [PATCH v2 2/5] ioatdma: Adding support for 16 src PQ ops and super extended descriptors Dave Jiang
2013-04-10 23:44 ` [PATCH v2 3/5] ioatdma: S1200 platforms ioatdma channel 2 and 3 falsely advertise RAID cap Dave Jiang
2013-04-10 23:44 ` [PATCH v2 4/5] ioatdma: Adding write back descriptor error status support for ioatdma 3.3 Dave Jiang
2013-04-10 23:44 ` [PATCH v2 5/5] async_tx: allow generic async_memcpy() not be effected by channel switch Dave Jiang
2013-04-12 1:04 ` [PATCH v2 0/5] ioatdma: Intel S1200 support patches Dan Williams
2013-04-15 17:17 ` Vinod Koul
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=20130410234420.9082.7578.stgit@djiang5-linux2.ch.intel.com \
--to=dave.jiang@intel.com \
--cc=djbw@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=vinod.koul@intel.com \
/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