public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: "Stephen M. Cameron" <scameron@beardog.cce.hp.com>
To: axboe@kernel.dk
Cc: akpm@linux-foundation.org, mikem@beardog.cce.hp.com,
	linux-kernel@vger.kernel.org, brace@beardog.cce.hp.com
Subject: [PATCH 13/26] cciss: factor out cciss_p600_dma_prefetch_quirk()
Date: Mon, 19 Jul 2010 13:45:46 -0500	[thread overview]
Message-ID: <20100719184546.7908.30204.stgit@beardog.cce.hp.com> (raw)
In-Reply-To: <20100719184141.7908.26971.stgit@beardog.cce.hp.com>

From: Stephen M. Cameron <scameron@beardog.cce.hp.com>

cciss: factor out cciss_p600_dma_prefetch_quirk()

Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com>
---
 drivers/block/cciss.c |   37 +++++++++++++++++++------------------
 1 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index b4264bc..e1c2bf1 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -4120,6 +4120,24 @@ static inline void cciss_enable_scsi_prefetch(ctlr_info_t *h)
 #endif
 }
 
+/* Disable DMA prefetch for the P600.  Otherwise an ASIC bug may result
+ * in a prefetch beyond physical memory.
+ */
+static inline void cciss_p600_dma_prefetch_quirk(ctlr_info_t *h)
+{
+	u32 dma_prefetch;
+	__u32 dma_refetch;
+
+	if (h->board_id != 0x3225103C)
+		return;
+	dma_prefetch = readl(h->vaddr + I2O_DMA1_CFG);
+	dma_prefetch |= 0x8000;
+	writel(dma_prefetch, h->vaddr + I2O_DMA1_CFG);
+	pci_read_config_dword(h->pdev, PCI_COMMAND_PARITY, &dma_refetch);
+	dma_refetch |= 0x1;
+	pci_write_config_dword(h->pdev, PCI_COMMAND_PARITY, dma_refetch);
+}
+
 static int __devinit cciss_pci_init(ctlr_info_t *c)
 {
 	int prod_index, err;
@@ -4182,24 +4200,7 @@ static int __devinit cciss_pci_init(ctlr_info_t *c)
 		goto err_out_free_res;
 	}
 	cciss_enable_scsi_prefetch(c);
-	/* Disabling DMA prefetch and refetch for the P600.
-	 * An ASIC bug may result in accesses to invalid memory addresses.
-	 * We've disabled prefetch for some time now. Testing with XEN
-	 * kernels revealed a bug in the refetch if dom0 resides on a P600.
-	 */
-	if (c->board_id == 0x3225103C) {
-		__u32 dma_prefetch;
-		__u32 dma_refetch;
-		dma_prefetch = readl(c->vaddr + I2O_DMA1_CFG);
-		dma_prefetch |= 0x8000;
-		writel(dma_prefetch, c->vaddr + I2O_DMA1_CFG);
-		pci_read_config_dword(c->pdev, PCI_COMMAND_PARITY,
-			&dma_refetch);
-		dma_refetch |= 0x1;
-		pci_write_config_dword(c->pdev, PCI_COMMAND_PARITY,
-			dma_refetch);
-	}
-
+	cciss_p600_dma_prefetch_quirk(c);
 #ifdef CCISS_DEBUG
 	printk(KERN_WARNING "Trying to put board into Performant mode\n");
 #endif				/* CCISS_DEBUG */


  parent reply	other threads:[~2010-07-19 18:44 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-07-19 18:44 [PATCH 00/26] cciss updates July 19, 2010 Stephen M. Cameron
2010-07-19 18:44 ` [PATCH 01/26] cciss: Set the performant mode bit in the scsi half of the driver Stephen M. Cameron
2010-07-19 18:44 ` [PATCH 02/26] cciss: save pdev pointer in per hba structure early to avoid passing it around so much Stephen M. Cameron
2010-07-19 18:44 ` [PATCH 03/26] cciss: factor out cciss_lookup_board_id Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 04/26] cciss: factor out cciss_board_disabled Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 05/26] cciss: remove board_id parameter from cciss_interrupt_mode() Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 06/26] cciss: factor out cciss_find_memory_BAR() Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 07/26] cciss: factor out cciss_wait_for_board_ready() Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 08/26] cciss: factor out cciss_find_cfgtables Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 09/26] cciss: fix leak of ioremapped memory Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 10/26] cciss: factor out cciss_find_board_params Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 11/26] cciss: factor out CISS_signature_present() Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 12/26] cciss: factor out cciss_enable_scsi_prefetch() Stephen M. Cameron
2010-07-19 18:45 ` Stephen M. Cameron [this message]
2010-07-19 18:45 ` [PATCH 14/26] cciss: cleanup some debug ifdefs Stephen M. Cameron
2010-07-19 18:45 ` [PATCH 15/26] cciss: make cciss_put_controller_into_performant_mode as __devinit Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 16/26] cciss: factor out cciss_wait_for_mode_change_ack() Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 17/26] cciss: factor out cciss_enter_performant_mode Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 18/26] cciss: factor out cciss_find_cfg_addrs Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 19/26] cciss: factor out cciss_reset_devices() Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 20/26] cciss: fix hard reset code Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 21/26] cciss: sanitize max commands Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 22/26] cciss: forbid hard reset of 640x boards Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 23/26] cciss: use consistent variable names Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 24/26] cciss: separate cmd_alloc() and cmd_special_alloc() Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 25/26] cciss: change printks to dev_warn, etc Stephen M. Cameron
2010-07-19 18:46 ` [PATCH 26/26] cciss: cleanup interrupt_not_for_us Stephen M. Cameron
2010-07-21  2:05 ` [PATCH 00/26] cciss updates July 19, 2010 Jens Axboe

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=20100719184546.7908.30204.stgit@beardog.cce.hp.com \
    --to=scameron@beardog.cce.hp.com \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=brace@beardog.cce.hp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mikem@beardog.cce.hp.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