From: Jon Mason <jdmason@us.ibm.com>
To: ak@muc.de
Cc: mulix@mulix.org, linux-kernel@vger.kernel.org
Subject: [PATCH 2/2] x86-64: no_iommu removal in pci-gart.c
Date: Thu, 2 Feb 2006 18:15:29 -0600 [thread overview]
Message-ID: <20060203001529.GC32198@us.ibm.com> (raw)
In previous versions of pci-gart.c, no_iommu was used to determine if IOMMU was
disabled in the GART DMA mapping functions. This changed in 2.6.16 and now
gart_xxx() functions are only called if gart is enabled. Therefore, uses of
no_iommu in the GART code are no longer necessary and can be removed.
Also, it removes double deceleration of no_iommu and force_iommu in pci.h and
proto.h, by removing the deceleration in pci.h.
Lastly, end_pfn off by one error.
Tested (along with patch 1/2) on dual opteron with gart enabled, iommu=soft,
and iommu=off.
Thanks,
Jon
Signed-off-by: Jon Mason <jdmason@us.ibm.com>
diff -r e961b4a72270 arch/x86_64/kernel/aperture.c
--- a/arch/x86_64/kernel/aperture.c Thu Feb 2 21:28:35 2006
+++ b/arch/x86_64/kernel/aperture.c Thu Feb 2 15:34:24 2006
@@ -248,7 +248,7 @@
/* Got the aperture from the AGP bridge */
} else if (swiotlb && !valid_agp) {
/* Do nothing */
- } else if ((!no_iommu && end_pfn >= MAX_DMA32_PFN) ||
+ } else if ((!no_iommu && end_pfn > MAX_DMA32_PFN) ||
force_iommu ||
valid_agp ||
fallback_aper_force) {
diff -r e961b4a72270 arch/x86_64/kernel/pci-gart.c
--- a/arch/x86_64/kernel/pci-gart.c Thu Feb 2 21:28:35 2006
+++ b/arch/x86_64/kernel/pci-gart.c Thu Feb 2 15:34:24 2006
@@ -228,11 +228,6 @@
int mmu = high;
if (force_iommu)
mmu = 1;
- if (no_iommu) {
- if (high)
- panic("PCI-DMA: high address but no IOMMU.\n");
- mmu = 0;
- }
return mmu;
}
@@ -241,11 +236,6 @@
u64 mask = *dev->dma_mask;
int high = addr + size >= mask;
int mmu = high;
- if (no_iommu) {
- if (high)
- panic("PCI-DMA: high address but no IOMMU.\n");
- mmu = 0;
- }
return mmu;
}
@@ -631,17 +621,13 @@
(agp_copy_info(agp_bridge, &info) < 0);
#endif
- if (swiotlb) {
- no_iommu = 1;
+ if (swiotlb)
return -1;
- }
-
+
if (no_iommu ||
(!force_iommu && end_pfn <= MAX_DMA32_PFN) ||
!iommu_aperture ||
(no_agp && init_k8_gatt(&info) < 0)) {
- no_iommu = 1;
- no_iommu_init();
printk(KERN_INFO "PCI-DMA: Disabling IOMMU.\n");
if (end_pfn > MAX_DMA32_PFN) {
printk(KERN_ERR "WARNING more than 4GB of memory "
diff -r e961b4a72270 include/asm-x86_64/pci.h
--- a/include/asm-x86_64/pci.h Thu Feb 2 21:28:35 2006
+++ b/include/asm-x86_64/pci.h Thu Feb 2 15:34:24 2006
@@ -18,8 +18,6 @@
#define pcibios_assign_all_busses() 0
#endif
#define pcibios_scan_all_fns(a, b) 0
-
-extern int no_iommu, force_iommu;
extern unsigned long pci_mem_start;
#define PCIBIOS_MIN_IO 0x1000
reply other threads:[~2006-02-03 0:15 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20060203001529.GC32198@us.ibm.com \
--to=jdmason@us.ibm.com \
--cc=ak@muc.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mulix@mulix.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