diff options
| author | Yinghai Lu | 2008-04-13 10:41:58 +0200 |
|---|---|---|
| committer | Ingo Molnar | 2008-04-26 23:41:04 +0200 |
| commit | e8ee6f0ae5cd860e8e6c02807edfa3c1fa01bcb5 (patch) | |
| tree | 800e742a999207617506a9475dc40e3c6234d11a /usr/initramfs_data.S | |
| parent | acpi: get boot_cpu_id as early for k8_scan_nodes (diff) | |
| download | kernel-qcow2-linux-e8ee6f0ae5cd860e8e6c02807edfa3c1fa01bcb5.tar.gz kernel-qcow2-linux-e8ee6f0ae5cd860e8e6c02807edfa3c1fa01bcb5.tar.xz kernel-qcow2-linux-e8ee6f0ae5cd860e8e6c02807edfa3c1fa01bcb5.zip | |
x86: work around io allocation overlap of HT links
normally BIOSes assign io/mmio range to different HT links without
overlapping, even same node same link should get non overlapping
entries.
but Rafael L. Wysocki's buggy BIOS creates a link with overlapping
entries for mmio and io:
node 0 link 0: io port [1000, ffffff]
node 0 link 0: mmio [e0000000, efffffff]
node 0 link 0: mmio [a0000, bffff]
node 0 link 0: mmio [80000000, ffffffff]
try to merge them and we will get:
bus: [00, ff] on node 0 link 0
bus: 00 index 0 io port: [0, ffff]
bus: 00 index 1 mmio: [80000000, fcffffffff]
bus: 00 index 2 mmio: [a0000, bffff]
so later we will reduce the chance to assign used resource to
unassigned device.
Reported-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Tested-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'usr/initramfs_data.S')
0 files changed, 0 insertions, 0 deletions