From: Andi Kleen <andi@firstfloor.org>
To: joerg.roedel@amd.com, ak@linux.intel.com,
linux-kernel@vger.kernel.org, stable@kernel.org,
tim.bird@am.sony.com
Subject: [PATCH] [42/50] iommu/amd: Don't use MSI address range for DMA addresses
Date: Thu, 28 Jul 2011 16:44:47 -0700 (PDT) [thread overview]
Message-ID: <20110728234447.0F9F02403FF@tassilo.jf.intel.com> (raw)
In-Reply-To: <20110728444.299940435@firstfloor.org>
2.6.35-longterm review patch. If anyone has any objections, please let me know.
------------------
From: Joerg Roedel <joerg.roedel@amd.com>
[ upstream commit 17f5b569e09cfa3488eaa663cbf9feada2e789f5 ]
Reserve the MSI address range in the address allocator so
that MSI addresses are not handed out as dma handles.
Cc: stable@kernel.org
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Index: linux-2.6.35.y/arch/x86/kernel/amd_iommu.c
===================================================================
--- linux-2.6.35.y.orig/arch/x86/kernel/amd_iommu.c
+++ linux-2.6.35.y/arch/x86/kernel/amd_iommu.c
@@ -25,6 +25,7 @@
#include <linux/dma-mapping.h>
#include <linux/iommu-helper.h>
#include <linux/iommu.h>
+#include <asm/msidef.h>
#include <asm/proto.h>
#include <asm/iommu.h>
#include <asm/gart.h>
@@ -1048,7 +1049,7 @@ static int alloc_new_range(struct dma_op
{
int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
struct amd_iommu *iommu;
- unsigned long i;
+ unsigned long i, old_size;
#ifdef CONFIG_IOMMU_STRESS
populate = false;
@@ -1084,8 +1085,21 @@ static int alloc_new_range(struct dma_op
}
}
+ old_size = dma_dom->aperture_size;
dma_dom->aperture_size += APERTURE_RANGE_SIZE;
+ /* Reserve address range used for MSI messages */
+ if (old_size < MSI_ADDR_BASE_LO &&
+ dma_dom->aperture_size > MSI_ADDR_BASE_LO) {
+ unsigned long spage;
+ int pages;
+
+ pages = iommu_num_pages(MSI_ADDR_BASE_LO, 0x10000, PAGE_SIZE);
+ spage = MSI_ADDR_BASE_LO >> PAGE_SHIFT;
+
+ dma_ops_reserve_addresses(dma_dom, spage, pages);
+ }
+
/* Intialize the exclusion range if necessary */
for_each_iommu(iommu) {
if (iommu->exclusion_start &&
next prev parent reply other threads:[~2011-07-28 23:47 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-28 23:44 [PATCH] [0/50] 2.6.35.14 longterm review Andi Kleen
2011-07-28 23:44 ` [PATCH] [1/50] x86: Make Dell Latitude E6420 use reboot=pci Andi Kleen
2011-07-28 23:44 ` [PATCH] [2/50] mm/futex: fix futex writes on archs with SW tracking of Andi Kleen
2011-07-28 23:44 ` [PATCH] [3/50] mm/backing-dev.c: reset bdi min_ratio in bdi_unregister() Andi Kleen
2011-07-28 23:44 ` [PATCH] [4/50] xtensa: prevent arbitrary read in ptrace Andi Kleen
2011-07-28 23:44 ` [PATCH] [5/50] ipc/sem.c: fix race with concurrent semtimedop() timeouts Andi Kleen
2011-07-28 23:44 ` [PATCH] [6/50] jme: Fix unmap error (Causing system freeze) Andi Kleen
2011-07-28 23:44 ` [PATCH] [7/50] fix crash in scsi_dispatch_cmd() Andi Kleen
2011-07-28 23:44 ` [PATCH] [8/50] mmc: Add PCI fixup quirks for Ricoh 1180:e823 reader Andi Kleen
2011-07-28 23:44 ` [PATCH] [9/50] mmc: Added quirks for Ricoh 1180:e823 lower base clock Andi Kleen
2011-07-29 0:27 ` matsumur
2011-07-29 0:37 ` Andi Kleen
2011-07-29 0:46 ` matsumur
2011-07-29 0:47 ` Chris Ball
2011-07-29 2:10 ` matsumur
2011-07-29 2:49 ` Chris Ball
2011-07-28 23:44 ` [PATCH] [10/50] Drop -Werror in perf Andi Kleen
2011-07-28 23:44 ` [PATCH] [11/50] kexec, x86: Fix incorrect jump back address if not Andi Kleen
2011-07-28 23:44 ` [PATCH] [12/50] USB: serial: add IDs for WinChipHead USB->RS232 adapter Andi Kleen
2011-07-28 23:44 ` [PATCH] [13/50] davinci: DM365 EVM: fix video input mux bits Andi Kleen
2011-07-28 23:44 ` [PATCH] [14/50] powerpc/pseries/hvconsole: Fix dropped console output Andi Kleen
2011-07-28 23:44 ` [PATCH] [15/50] hvc_console: Improve tty/console put_chars handling Andi Kleen
2011-07-28 23:44 ` [PATCH] [16/50] powerpc/kdump: Fix timeout in crash_kexec_wait_realmode Andi Kleen
2011-07-28 23:44 ` [PATCH] [17/50] si4713-i2c: avoid potential buffer overflow on si4713 Andi Kleen
2011-07-28 23:44 ` [PATCH] [18/50] hwmon: (max1111) Fix race condition causing NULL pointer Andi Kleen
2011-07-28 23:44 ` [PATCH] [19/50] hwmon: (asus_atk0110) Fix memory leak Andi Kleen
2011-07-28 23:44 ` [PATCH] [20/50] USB: OHCI: fix another regression for NVIDIA controllers Andi Kleen
2011-07-28 23:44 ` [PATCH] [21/50] firewire: cdev: prevent race between first get_info ioctl Andi Kleen
2011-07-28 23:44 ` [PATCH] [22/50] firewire: cdev: return -ENOTTY for unimplemented ioctls, not Andi Kleen
2011-07-28 23:44 ` [PATCH] [23/50] svcrpc: fix list-corrupting race on nfsd shutdown Andi Kleen
2011-07-28 23:44 ` [PATCH] [24/50] x86: Look for IA32_ENERGY_PERF_BIAS support Andi Kleen
2011-07-28 23:44 ` [PATCH] [25/50] x86, intel, power: Initialize MSR_IA32_ENERGY_PERF_BIAS Andi Kleen
2011-07-28 23:44 ` [PATCH] [26/50] SUNRPC: Fix use of static variable in rpcb_getport_async Andi Kleen
2011-07-28 23:44 ` [PATCH] [27/50] ARM: pxa/cm-x300: fix V3020 RTC functionality Andi Kleen
2011-07-28 23:44 ` [PATCH] [28/50] firewire: ohci: do not bind to Pinnacle cards, avert panic Andi Kleen
2011-07-28 23:44 ` [PATCH] [29/50] mm/nommu.c: fix remap_pfn_range() Andi Kleen
2011-07-28 23:44 ` [PATCH] [30/50] EHCI: only power off port if over-current is active Andi Kleen
2011-07-28 23:44 ` [PATCH] [31/50] mac80211: Restart STA timers only on associated state Andi Kleen
2011-07-28 23:44 ` [PATCH] [32/50] usb: musb: restore INDEX register in resume path Andi Kleen
2011-07-28 23:44 ` [PATCH] [33/50] SUNRPC: Fix a race between work-queue and rpc_killall_tasks Andi Kleen
2011-07-28 23:44 ` [PATCH] [34/50] bttv: fix s_tuner for radio Andi Kleen
2011-07-28 23:44 ` [PATCH] [35/50] pvrusb2: fix g/s_tuner support Andi Kleen
2011-07-28 23:44 ` [PATCH] [36/50] v4l2-ioctl.c: prefill tuner type for g_frequency and Andi Kleen
2011-07-28 23:44 ` [PATCH] [37/50] mac80211: fix TKIP replay vulnerability Andi Kleen
2011-07-28 23:44 ` [PATCH] [38/50] ASoC: ak4642: fixup snd_soc_update_bits mask for PW_MGMT2 Andi Kleen
2011-07-28 23:44 ` [PATCH] [39/50] tracing: Fix bug when reading system filters on module Andi Kleen
2011-07-28 23:44 ` [PATCH] [40/50] tracing: Have "enable" file use refcounts like the "filter" Andi Kleen
2011-07-28 23:44 ` [PATCH] [41/50] ARM: pxa: fix PGSR register address calculation Andi Kleen
2011-07-28 23:44 ` Andi Kleen [this message]
2011-07-28 23:44 ` [PATCH] [43/50] staging: r8192e_pci: Handle duplicate PCI ID 0x10ec:0x8192 Andi Kleen
2011-07-28 23:44 ` [PATCH] [44/50] staging: comedi: fix infoleak to userspace Andi Kleen
2011-07-28 23:44 ` [PATCH] [45/50] Staging: hv: netvsc: Fix a bug in accounting transmit slots Andi Kleen
2011-07-28 23:44 ` [PATCH] [46/50] ARM: 6989/1: perf: do not start the PMU when no events are Andi Kleen
2011-07-28 23:44 ` [PATCH] [47/50] ASoC: Ensure we delay long enough for WM8994 FLL to lock Andi Kleen
2011-07-28 23:44 ` [PATCH] [48/50] SERIAL: SC26xx: Fix link error Andi Kleen
2011-07-28 23:44 ` [PATCH] [49/50] x86, mtrr: lock stop machine during MTRR rendezvous sequence Andi Kleen
2011-07-28 23:44 ` [PATCH] [50/50] ipv6: add special mode forwarding=2 to send RS while Andi Kleen
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=20110728234447.0F9F02403FF@tassilo.jf.intel.com \
--to=andi@firstfloor.org \
--cc=ak@linux.intel.com \
--cc=joerg.roedel@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@kernel.org \
--cc=tim.bird@am.sony.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
Powered by JetHome