Parse the Root Port ATS Capability Reporting Structure in the DMA
Remapping Reporting Structure ACPI table.
Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
The SR-IOV spec requires that the Smallest Translation Unit and
the Invalidate Queue Depth fields in the Virtual Function ATS
capability are hardwired to 0. If a function is a Virtual Function,
then and set its Physical Function's STU before enabling the ATS.
Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
The PCIe ATS capability makes the Endpoint be able to request the
DMA address translation from the IOMMU and cache the translation
in the device side, thus alleviate IOMMU pressure and improve the
hardware performance in the I/O virtualization environment.
Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
according to Ingo, io_apic irq-setup related functions have too many
parameters with a repetitive signature.
So reduce related funcs to get less params by passing a pointer
to a newly defined io_apic_irq_attr structure.
v2: io_apic_irq ==> irq_attr
triggering ==> trigger
v3: add set_io_apic_irq_attr
[ Impact: cleanup ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Len Brown <lenb@kernel.org>
LKML-Reference: <4A08ACD3.2070401@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The NIU device refuses to allow accesses to MSI-X registers before MSI-X
is enabled. This patch fixes the problem by moving the read of the mask
register to after MSI-X is enabled.
Reported-by: David S. Miller <davem@davemloft.net>
Tested-by: David S. Miller <davem@davemloft.net>
Reviewed-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
PAGE_MASK is 0xFFFFF000 on i386 -- even with PAE.
So it's not sufficient to ensure that you use phys_addr_t or uint64_t
everywhere you handle physical addresses -- you also have to avoid using
the construct 'addr & PAGE_MASK', because that will strip the high 32
bits of the address.
This patch avoids that problem by using PHYSICAL_PAGE_MASK instead of
PAGE_MASK where appropriate. It leaves '& PAGE_MASK' in a few instances
that don't matter -- where it's being used on the virtual bus addresses
we're dishing out, which are 32-bit anyway.
Since PHYSICAL_PAGE_MASK is not present on other architectures, we have
to define it (to PAGE_MASK) if it's not already defined.
Maybe it would be better just to fix PAGE_MASK for i386/PAE?
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
To prepare those params for pcibios_irq_enable() to call setup_io_apic_routing().
[ Impact: extend function call API to prepare for new functionality ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Len Brown <lenb@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <4A01C406.2040303@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In iommu_flush_write_buffer() we read iommu->gcmd before taking the
register_lock, and then we mask in the WBF bit and write it to the
register.
There is a tiny chance that something else could have _changed_
iommu->gcmd before we take the lock, but after we read it. So we could
be undoing that change.
Never actually going to have happened in practice, since nothing else
changes that register at runtime -- aside from the write-buffer flush
it's only ever touched at startup for enabling translation, etc.
But worth fixing anyway.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
As we just did for context cache flushing, clean up the logic around
whether we need to flush the iotlb or just the write-buffer, depending
on caching mode.
Fix the same bug in qi_flush_iotlb() that qi_flush_context() had -- it
isn't supposed to be returning an error; it's supposed to be returning a
flag which triggers a write-buffer flush.
Remove some superfluous conditional write-buffer flushes which could
never have happened because they weren't for non-present-to-present
mapping changes anyway.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
It really doesn't make a lot of sense to have some of the logic to
handle caching vs. non-caching mode duplicated in qi_flush_context() and
__iommu_flush_context(), while the return value indicates whether the
caller should take other action which depends on the same thing.
Especially since qi_flush_context() thought it was returning something
entirely different anyway.
This patch makes qi_flush_context() and __iommu_flush_context() both
return void, removes the 'non_present_entry_flush' argument and makes
the only call site which _set_ that argument to 1 do the right thing.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
The domain->id is a sequence number associated with the KVM guest
and should not be used for the context flush. This patch replaces
the domain->id with a proper id value for both bare metal and KVM.
Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Acked-by: Weidong Han <weidong.han@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
The current quirk doesn't include all 82576 device IDs. This update
resolves that.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When an upstream port reports an AER error to root port, kernel
starts error recovery procedures. The default return value of
function pcie_portdrv_slot_reset is PCI_ERS_RESULT_NONE. If all
port service drivers of the downstream port under the upstream
port have no slot_reset method in pci_error_handlers, AER recovery
would stop without resume. Below patch against 2.6.30-rc3 fixes it.
Signed-off-by: Zhang Yanmin <yanmin.zhang@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This updated patch should fix the compiling errors and remove the extern
iommu_pass_through from drivers/pci/intel-iommu.c file.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
The patch adds kernel parameter intel_iommu=pt to set up pass through
mode in context mapping entry. This disables DMAR in linux kernel; but
KVM still runs on VT-d and interrupt remapping still works.
In this mode, kernel uses swiotlb for DMA API functions but other VT-d
functionalities are enabled for KVM. KVM always uses multi level
translation page table in VT-d. By default, pass though mode is disabled
in kernel.
This is useful when people don't want to enable VT-d DMAR in kernel but
still want to use KVM and interrupt remapping for reasons like DMAR
performance concern or debug purpose.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Acked-by: Weidong Han <weidong@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Try to get irq_desc on the same node as create_irq_nr().
[ Impact: optimization, make HT IRQs more NUMA-aware ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
LKML-Reference: <49F655B6.8020109@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This simplifies the node awareness of the code. All our allocators
only deal with a NUMA node ID locality not with CPU ids anyway - so
there's no need to maintain (and transform) a CPU id all across the
IRq layer.
v2: keep move_irq_desc related
[ Impact: cleanup, prepare IRQ code to be NUMA-aware ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
LKML-Reference: <49F65536.2020300@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
PCIe 1.1 base neither requires the endpoint to implement the entire
PCIe capability structure nor specifies default values of registers
that are not implemented by the device. So we only save and restore
registers that must be implemented by different device types if the
device PCIe capability version is 1.
PCIe 1.1 Capability Structure Expansion ECN and PCIe 2.0 requires
all registers in the PCIe capability to be either implemented or
hardwired to 0. Their PCIe capability version is 2.
Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Add drivers/pci/*.c source files to DocBook/kernel-api.tmpl
and update those pci/*.c source files that need kernel-doc fixes.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Commit 30a18d6c3f introduced a new
function to set the PCI bus resources. Unfortunately, neither the
author, nor the committers seemed to know that we already have somewhere
to do that -- pcibios_fixup_bus(). This patch moves the hook (used only
by the K8 code) into x86-specific code where it should have been in the
first place.
Cc: Yinghai Lu <yinghai.lu@sun.com>
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Without this patch, Broadcom BCM5906 Ethernet controllers set up via MSI
cause the machine to hang. Tejun agreed that the best is to blacklist
the whole chipset and after adding it, seeing the other VIA quirks
disabling MSI, this very much looks like the right way.
Cc: <stable@kernel.org>
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Currently, when x2apic is not enabled, interrupt remapping
will be enabled in init_dmars(), where it is too late to remap
ioapic interrupts, that is, ioapic interrupts are really in
compatibility mode, not remappable mode.
This patch always enables interrupt remapping before ioapic
setup, it guarantees all interrupts will be remapped when
interrupt remapping is enabled. Thus it doesn't need to set
the compatibility interrupt bit.
[ Impact: refactor intr-remap init sequence, enable fuller remap mode ]
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Weidong Han <weidong.han@intel.com>
Acked-by: David Woodhouse <David.Woodhouse@intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: allen.m.kay@intel.com
Cc: fenghua.yu@intel.com
LKML-Reference: <1239957736-6161-4-git-send-email-weidong.han@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If the BIOS does something obviously stupid, like claiming that the
registers for the IOMMU are at physical address zero, then print a nasty
message and abort, rather than trying to set up the IOMMU and then later
panicking.
It's becoming more and more obvious that trusting this stuff to the BIOS
was a mistake.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Replace all DMA_32BIT_MASK macro with DMA_BIT_MASK(32)
Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace all DMA_64BIT_MASK macro with DMA_BIT_MASK(64)
Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This issue was pointed out by Linus.
In dma_pte_clear_range() in intel-iommu.c
start = PAGE_ALIGN(start);
end &= PAGE_MASK;
npages = (end - start) / VTD_PAGE_SIZE;
In partial page case, start could be bigger than end and npages will be
negative.
Currently the issue doesn't show up as a real bug in because start and
end have been aligned to page boundary already by all callers. So the
issue has been hidden. But it is dangerous programming practice.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Fix this build error:
drivers/pci/intr_remapping.c: In function 'ir_parse_ioapic_scope':
drivers/pci/intr_remapping.c:617: error: invalid use of undefined type
'struct acpi_dmar_hardware_unit'
Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
It's possible for a device in the drhd->devices[] array to be NULL if
it wasn't found at boot time, which means we have to check for that
case.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
If a logical hot unplug (remove) is performed on a bridge claimed
by acpiphp and then acpiphp is unloaded, we will encounter an oops.
This is because acpiphp will access the bridge's subordinate bus,
which was released by the user's prior hot unplug.
The solution is to grab a reference on the subordinate PCI bus.
This will prevent the bus from release until acpiphp is unloaded.
Reviewed-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Tested-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Reported-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
There is no reason to prevent removal of root bus devices. A subsequent
rescan will find them just fine.
Reviewed-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This patch fixes breakage of of enable_cnt in quirk_resource_alignment.
Currently, quirk_resource_alignment calls pci_disable_device.
pci_disable_device decrements enable_cnt, so that enable_cnt becomes -1.
The patch disables memory decoding, writing command register directly.
So enable_cnt is not broken.
Signed-off-by: Yuji Shimada <shimada-yxb@necst.nec.co.jp>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
pci_rescan_bus was annotated as __devinit, which is wrong,
because it will never be part of device initialization.
Howevever, we can't simply drop the annotation, because then we
get section warnings about calling pci_scan_child_bus (which is
correctly marked as __devinit).
pci_rescan_bus will only get built when CONFIG_HOTPLUG is set,
meaning that __devinit is a nop, so we know that pci_scan_child_bus
has not been freed.
Annotate as __ref to silence modpost.
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Fix PCI iov kernel-doc warning:
Warning(drivers/pci/iov.c:638): No description found for parameter 'nr_virtfn'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This patch sets up disabled bridges even if buses have already been
added.
pci_assign_unassigned_resources is called after buses are added.
pci_assign_unassigned_resources calls pci_bus_assign_resources.
pci_bus_assign_resources calls pci_setup_bridge to configure BARs of
bridges.
Currently pci_setup_bridge returns immediately if the bus have already
been added. So pci_assign_unassigned_resources can't configure BARs of
bridges that were added in a disabled state; this patch fixes the issue.
On logical hot-add, we need to prevent the kernel from re-initializing
bridges that have already been initialized. To achieve this,
pci_setup_bridge returns immediately if the bridge have already been
enabled.
We don't need to check whether the specified bus is a root bus or not.
pci_setup_bridge is not called on a root bus, because a root bus does
not have a bridge.
The patch adds a new helper function, pci_is_enabled. I made the
function name similar to pci_is_managed. The codes which use
enable_cnt directly are changed to use pci_is_enabled.
Acked-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Yuji Shimada <shimada-yxb@necst.nec.co.jp>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
If BIOS doesn't allocate resources for the SR-IOV BARs, zero the Flash
BAR and program the SR-IOV BARs to use the old Flash Memory Space.
Please refer to Intel 82576 Gigabit Ethernet Controller Datasheet
section 7.9.2.14.2 for details.
http://download.intel.com/design/network/datashts/82576_Datasheet.pdf
Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
We were comparing {bus,devfn} and assuming that a match meant it was the
same device. It doesn't -- the same {bus,devfn} can exist in
multiple PCI domains. Include domain number in device identification
(and call it 'segment' in most places, because there's already a lot of
references to 'domain' which means something else, and this code is
infected with ACPI thinking already).
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
When the DMAR table identifies that a PCI-PCI bridge belongs to a given
IOMMU, that means that the bridge and all devices behind it should be
associated with the IOMMU. Not just the bridge itself.
This fixes the device_to_iommu() function accordingly.
(It's broken if you have the same PCI bus numbers in multiple domains,
but this function was always broken in that way; I'll be dealing with
that later).
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
interrupt remapping must be enabled before enabling x2apic, but
interrupt remapping doesn't depend on x2apic, it can be used
separately. Enable interrupt remapping in init_dmars even x2apic
is not supported.
[dwmw2: Update Kconfig accordingly, fix build with INTR_REMAP && !X2APIC]
Signed-off-by: Weidong Han <weidong.han@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
If queue invalidation is disabled after it's already initialized,
dmar_enable_qi won't re-enable it due to iommu->qi is allocated.
It may result in system hang when use queue invalidation. Add this
check to avoid this case.
Signed-off-by: Weidong Han <weidong.han@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
When extended interrupt mode (x2apic mode) is not supported in a
system, it must set compatibility format interrupt to bypass
interrupt remapping, otherwise compatibility format interrupts
will be blocked.
This will be used when interrupt remapping is enabled while x2apic
is not supported.
Signed-off-by: Weidong Han <weidong.han@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
This patch enables suspend/resume for interrupt remapping. During suspend,
interrupt remapping is disabled. When resume, interrupt remapping is enabled
again.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
This patch implements the suspend and resume feature for Intel IOMMU
DMAR. It hooks to kernel suspend and resume interface. When suspend happens, it
saves necessary hardware registers. When resume happens, it restores the
registers and restarts IOMMU by enabling translation, setting up root entry, and
re-enabling queued invalidation.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Yu Zhao