mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Muli Ben-Yehuda <mulix@mulix.org>
To: Andi Kleen <ak@suse.de>
Cc: Jon Mason <jdmason@us.ibm.com>, Muli Ben-Yehuda <MULI@il.ibm.com>,
	Linux-Kernel <linux-kernel@vger.kernel.org>,
	discuss@x86-64.org, Andrew Morton <akpm@osdl.org>
Subject: [RFC PATCH 1/3] x86-64: Calgary IOMMU - introduce iommu_detected
Date: Tue, 14 Mar 2006 10:24:32 +0200	[thread overview]
Message-ID: <20060314082432.GE23631@granada.merseine.nu> (raw)

Hi,

swiotlb relies on the gart specific iommu_aperture variable to know if
we discovered a hardware IOMMU before swiotlb
initialization. Introduce iommu_detected to do the same thing, but in
a HW IOMMU neutral manner, in preparation for adding the Calgary HW
IOMMU.

Signed-Off-By: Muli Ben-Yehuda <mulix@mulix.org>
Signed-Off-By: Jon Mason <jdmason@us.ibm.com>

diff -Naurp --exclude-from /home/muli/w/dontdiff vanilla/arch/x86_64/kernel/aperture.c iommu_detected/arch/x86_64/kernel/aperture.c
--- vanilla/arch/x86_64/kernel/aperture.c	2006-03-14 08:24:37.000000000 +0200
+++ iommu_detected/arch/x86_64/kernel/aperture.c	2006-03-14 09:05:00.000000000 +0200
@@ -212,6 +212,7 @@ void __init iommu_hole_init(void) 
 		if (read_pci_config(0, num, 3, 0x00) != NB_ID_3) 
 			continue;	
 
+		iommu_detected = 1;
 		iommu_aperture = 1; 
 
 		aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7; 
diff -Naurp --exclude-from /home/muli/w/dontdiff vanilla/arch/x86_64/kernel/pci-dma.c iommu_detected/arch/x86_64/kernel/pci-dma.c
--- vanilla/arch/x86_64/kernel/pci-dma.c	2006-03-14 08:24:37.000000000 +0200
+++ iommu_detected/arch/x86_64/kernel/pci-dma.c	2006-03-14 09:05:48.000000000 +0200
@@ -33,6 +33,9 @@ int panic_on_overflow __read_mostly = 0;
 int force_iommu __read_mostly= 0;
 #endif
 
+/* Set this to 1 if there is a HW IOMMU in the system */
+int iommu_detected __read_mostly = 0;
+
 /* Dummy device used for NULL arguments (normally ISA). Better would
    be probably a smaller DMA mask, but this is bug-to-bug compatible
    to i386. */
diff -Naurp --exclude-from /home/muli/w/dontdiff vanilla/arch/x86_64/kernel/pci-gart.c iommu_detected/arch/x86_64/kernel/pci-gart.c
--- vanilla/arch/x86_64/kernel/pci-gart.c	2006-03-14 08:24:37.000000000 +0200
+++ iommu_detected/arch/x86_64/kernel/pci-gart.c	2006-03-14 09:06:44.000000000 +0200
@@ -627,6 +627,10 @@ static int __init pci_iommu_init(void)
 	if (swiotlb)
 		return -1; 
 
+        /* Did we detect a different HW IOMMU? */
+	if (iommu_detected && !iommu_aperture)
+		return -1;
+ 
 	if (no_iommu ||
 	    (!force_iommu && end_pfn <= MAX_DMA32_PFN) ||
 	    !iommu_aperture ||
diff -Naurp --exclude-from /home/muli/w/dontdiff vanilla/arch/x86_64/kernel/pci-swiotlb.c iommu_detected/arch/x86_64/kernel/pci-swiotlb.c
--- vanilla/arch/x86_64/kernel/pci-swiotlb.c	2006-03-14 08:24:37.000000000 +0200
+++ iommu_detected/arch/x86_64/kernel/pci-swiotlb.c	2006-03-14 09:07:05.000000000 +0200
@@ -31,7 +31,7 @@ struct dma_mapping_ops swiotlb_dma_ops =
 void pci_swiotlb_init(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-	if (!iommu_aperture && !no_iommu &&
+	if (!iommu_detected && !no_iommu &&
 	    (end_pfn > MAX_DMA32_PFN || force_iommu))
 	       swiotlb = 1;
 	if (swiotlb) {
diff -Naurp --exclude-from /home/muli/w/dontdiff vanilla/include/asm-x86_64/dma-mapping.h iommu_detected/include/asm-x86_64/dma-mapping.h
--- vanilla/include/asm-x86_64/dma-mapping.h	2006-03-14 08:26:27.000000000 +0200
+++ iommu_detected/include/asm-x86_64/dma-mapping.h	2006-03-14 09:07:56.000000000 +0200
@@ -183,5 +183,6 @@ dma_cache_sync(void *vaddr, size_t size,
 
 extern struct device fallback_dev;
 extern int panic_on_overflow;
+extern int iommu_detected;
 
 #endif /* _X8664_DMA_MAPPING_H */


-- 
Muli Ben-Yehuda
http://www.mulix.org | http://mulix.livejournal.com/


             reply	other threads:[~2006-03-14  8:29 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-03-14  8:24 Muli Ben-Yehuda [this message]
2006-03-14  8:25 ` [PATCH RFC 2/3] x86-64: Calgary IOMMU - Calgary specific bits Muli Ben-Yehuda
2006-03-14  8:26   ` [RFC PATCH 3/3] x86-64: Calgary IOMMU - hook it in Muli Ben-Yehuda
2006-03-14 23:03     ` Pavel Machek
2006-03-14 23:22       ` Jon Mason
2006-03-14 23:26         ` Pavel Machek
2006-03-15  0:06           ` Jon Mason
2006-03-15  1:38             ` Muli Ben-Yehuda
2006-03-14 23:03   ` [PATCH RFC 2/3] x86-64: Calgary IOMMU - Calgary specific bits Pavel Machek
2006-03-15  0:55     ` Jon Mason
2006-03-15  0:56       ` Olof Johansson
2006-03-15  1:27         ` Jon Mason
2006-03-15  3:18           ` Olof Johansson
2006-03-15  1:52         ` Muli Ben-Yehuda
2006-03-14 15:01 ` [RFC PATCH 1/3] x86-64: Calgary IOMMU - introduce iommu_detected Andi Kleen
2006-03-14 15:07   ` Muli Ben-Yehuda

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=20060314082432.GE23631@granada.merseine.nu \
    --to=mulix@mulix.org \
    --cc=MULI@il.ibm.com \
    --cc=ak@suse.de \
    --cc=akpm@osdl.org \
    --cc=discuss@x86-64.org \
    --cc=jdmason@us.ibm.com \
    --cc=linux-kernel@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

all inboxes | Powered by JetHome®