From: Ben Hutchings <bhutchings@solarflare.com>
To: David Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org, linux-net-drivers@solarflare.com
Subject: [PATCH net-2.6] sfc: Siena: Disable write-combining when SR-IOV is enabled
Date: Wed, 23 Mar 2011 21:16:59 +0000 [thread overview]
Message-ID: <1300915019.2638.20.camel@bwh-desktop> (raw)
In-Reply-To: <1300914873.2638.19.camel@bwh-desktop>
From: Steve Hodgson <shodgson@solarflare.com>
If SR-IOV is enabled by firmware, even if it is not enabled in the PCI
capability, TX pushes using write-combining may be corrupted.
We want to know whether it is enabled before mapping the NIC
registers, and even if PCI extended capabilities are not accessible.
Therefore, we look for the MSI capability, which is removed if SR-IOV
is enabled.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
drivers/net/sfc/efx.c | 18 ++++++++++++++++--
drivers/net/sfc/workarounds.h | 2 ++
2 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index b8bd936..d890679 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -1054,6 +1054,7 @@ static int efx_init_io(struct efx_nic *efx)
{
struct pci_dev *pci_dev = efx->pci_dev;
dma_addr_t dma_mask = efx->type->max_dma_mask;
+ bool use_wc;
int rc;
netif_dbg(efx, probe, efx->net_dev, "initialising I/O\n");
@@ -1104,8 +1105,21 @@ static int efx_init_io(struct efx_nic *efx)
rc = -EIO;
goto fail3;
}
- efx->membase = ioremap_wc(efx->membase_phys,
- efx->type->mem_map_size);
+
+ /* bug22643: If SR-IOV is enabled then tx push over a write combined
+ * mapping is unsafe. We need to disable write combining in this case.
+ * MSI is unsupported when SR-IOV is enabled, and the firmware will
+ * have removed the MSI capability. So write combining is safe if
+ * there is an MSI capability.
+ */
+ use_wc = (!EFX_WORKAROUND_22643(efx) ||
+ pci_find_capability(pci_dev, PCI_CAP_ID_MSI));
+ if (use_wc)
+ efx->membase = ioremap_wc(efx->membase_phys,
+ efx->type->mem_map_size);
+ else
+ efx->membase = ioremap_nocache(efx->membase_phys,
+ efx->type->mem_map_size);
if (!efx->membase) {
netif_err(efx, probe, efx->net_dev,
"could not map memory BAR at %llx+%x\n",
diff --git a/drivers/net/sfc/workarounds.h b/drivers/net/sfc/workarounds.h
index e4dd3a7..99ff114 100644
--- a/drivers/net/sfc/workarounds.h
+++ b/drivers/net/sfc/workarounds.h
@@ -38,6 +38,8 @@
#define EFX_WORKAROUND_15783 EFX_WORKAROUND_ALWAYS
/* Legacy interrupt storm when interrupt fifo fills */
#define EFX_WORKAROUND_17213 EFX_WORKAROUND_SIENA
+/* Write combining and sriov=enabled are incompatible */
+#define EFX_WORKAROUND_22643 EFX_WORKAROUND_SIENA
/* Spurious parity errors in TSORT buffers */
#define EFX_WORKAROUND_5129 EFX_WORKAROUND_FALCON_A
--
1.7.4
--
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
next prev parent reply other threads:[~2011-03-23 21:17 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-03-23 21:14 pull request: sfc-2.6 2011-03-23 Ben Hutchings
2011-03-23 21:16 ` Ben Hutchings [this message]
2011-03-23 22:56 ` David Miller
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=1300915019.2638.20.camel@bwh-desktop \
--to=bhutchings@solarflare.com \
--cc=davem@davemloft.net \
--cc=linux-net-drivers@solarflare.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).