In the restore path, we previously read PCI_SRIOV_VF_OFFSET and
PCI_SRIOV_VF_STRIDE before restoring PCI_SRIOV_CTRL_ARI:
pci_restore_state
pci_restore_iov_state
sriov_restore_state
pci_iov_set_numvfs
pci_read_config_word(... PCI_SRIOV_VF_OFFSET, &iov->offset)
pci_read_config_word(... PCI_SRIOV_VF_STRIDE, &iov->stride)
pci_write_config_word(... PCI_SRIOV_CTRL, iov->ctrl)
But per SR-IOV r1.1, sec 3.3.3.5, the device can use PCI_SRIOV_CTRL_ARI to
determine PCI_SRIOV_VF_OFFSET and PCI_SRIOV_VF_STRIDE. Therefore, this
path, which is used for suspend/resume and AER recovery, can corrupt
iov->offset and iov->stride.
Since the iov state is associated with the device, not the driver, if we
reload the driver, it will use the the corrupted data, which may cause
crashes like this:
kernel BUG at drivers/pci/iov.c:157!
RIP: 0010:pci_iov_add_virtfn+0x2eb/0x350
Call Trace:
pci_enable_sriov+0x353/0x440
ixgbe_pci_sriov_configure+0xd5/0x1f0 [ixgbe]
sriov_numvfs_store+0xf7/0x170
dev_attr_store+0x18/0x30
sysfs_kf_write+0x37/0x40
kernfs_fop_write+0x120/0x1b0
vfs_write+0xb5/0x1a0
SyS_write+0x55/0xc0
Restore PCI_SRIOV_CTRL_ARI before calling pci_iov_set_numvfs(), then
restore the rest of PCI_SRIOV_CTRL (which may set PCI_SRIOV_CTRL_VFE)
afterwards.
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
[bhelgaas: changelog, add comment, also clear ARI if necessary]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
CC: Emil Tantilov <emil.s.tantilov@intel.com>
When creating virtual functions, create the "virtfn%u" and "physfn" links
in sysfs *before* attaching the driver instead of after. When we attach
the driver to the new virtual network interface first, there is a race when
the driver attaches to the new sends out an "add" udev event, and the
network interface naming software (biosdevname or systemd, for example)
tries to look at these links.
Signed-off-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cache the VF device ID in the SR-IOV structure and use it instead of
reading it over and over from the PF config space capability.
Signed-off-by: Filippo Sironi <sironi@amazon.de>
[bhelgaas: rename to "vf_device" to match pci_dev->device]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
The "reset" argument passed to pci_iov_add_virtfn() and
pci_iov_remove_virtfn() is always zero since 46cb7b1bd8 ("PCI: Remove
unused SR-IOV VF Migration support")
Remove the argument together with the associated code.
Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Russell Currey <ruscur@russell.cc>
A struct resource represents the address space consumed by a device. We
should not modify that resource while the device is actively using the
address space. For VFs, pci_iov_update_resource() enforces this by
printing a warning and doing nothing if the VFE (VF Enable) and MSE (VF
Memory Space Enable) bits are set.
Previously, both sriov_enable() and sriov_disable() called the
pcibios_sriov_disable() arch hook, which may update the struct resource,
while VFE and MSE were enabled. This effectively dropped the resource
update pcibios_sriov_disable() intended to do.
Disable VF memory decoding before calling pcibios_sriov_disable().
Reported-by: Carol L Soto <clsoto@us.ibm.com>
Tested-by: Carol L Soto <clsoto@us.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
[bhelgaas: changelog]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: shan.gavin@gmail.com
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Every method in struct device_driver or structures derived from it like
struct pci_driver MUST provide exclusion vs the driver's ->remove() method,
usually by using device_lock().
Protect use of pci_driver->sriov_configure() by holding the device lock
while calling it.
The PCI core sets the pci_dev->driver pointer in local_pci_probe() before
calling ->probe() and only clears it after ->remove(). This means driver's
->sriov_configure() callback will happily race with probe() and remove(),
most likely leading to BUGs, since drivers don't expect this.
Remove the iov lock completely, since we remove the last user.
[bhelgaas: changelog, thanks to Christoph for locking rule]
Link: http://lkml.kernel.org/r/20170522225023.14010-1-jakub.kicinski@netronome.com
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Sometimes it is not desirable to bind SR-IOV VFs to drivers. This can save
host side resource usage by VF instances that will be assigned to VMs.
Add a new PCI sysfs interface "sriov_drivers_autoprobe" to control that
from the PF. To modify it, echo 0/n/N (disable probe) or 1/y/Y (enable
probe) to:
/sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_drivers_autoprobe
Note that this must be done before enabling VFs. The change will not take
effect if VFs are already enabled. Simply, one can disable VFs by setting
sriov_numvfs to 0, choose whether to probe or not, and then re-enable the
VFs by restoring sriov_numvfs.
[bhelgaas: changelog, ABI doc]
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
pci_std_update_resource() only deals with standard BARs, so we don't have
to worry about the complications of VF BARs in an SR-IOV capability.
Compute the BAR address inline and remove pci_resource_bar(). That makes
pci_iov_resource_bar() unused, so remove that as well.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
If we update a VF BAR while it's enabled, there are two potential problems:
1) Any driver that's using the VF has a cached BAR value that is stale
after the update, and
2) We can't update 64-bit BARs atomically, so the intermediate state
(new lower dword with old upper dword) may conflict with another
device, and an access by a driver unrelated to the VF may cause a bus
error.
Warn about attempts to update VF BARs while they are enabled. This is a
programming error, so use dev_WARN() to get a backtrace.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Previously pci_update_resource() used the same code path for updating
standard BARs and VF BARs in SR-IOV capabilities.
Split the VF BAR update into a new pci_iov_update_resource() internal
interface, which makes it simpler to compute the BAR address (we can get
rid of pci_resource_bar() and pci_iov_resource_bar()).
This patch:
- Renames pci_update_resource() to pci_std_update_resource(),
- Adds pci_iov_update_resource(),
- Makes pci_update_resource() a wrapper that calls the appropriate one,
No functional change intended.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Previously we enabled VFs and enable their memory space before calling
pcibios_sriov_enable(). But pcibios_sriov_enable() may update the VF BARs:
for example, on PPC PowerNV we may change them to manage the association of
VFs to PEs.
Because 64-bit BARs cannot be updated atomically, it's unsafe to update
them while they're enabled. The half-updated state may conflict with other
devices in the system.
Call pcibios_sriov_enable() before enabling the VFs so any BAR updates
happen while the VF BARs are disabled.
[bhelgaas: changelog]
Tested-by: Carol Soto <clsoto@us.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
If pci_setup_device() returns failure, we must return failure from
pci_iov_add_virtfn(). If we ignore the failure and continue with an
uninitialized pci_dev for virtfn, we crash later when we try to use those
uninitialized parts.
Signed-off-by: Po Liu <po.liu@nxp.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Highlights:
- Restructure Linux PTE on Book3S/64 to Radix format from Paul Mackerras
- Book3s 64 MMU cleanup in preparation for Radix MMU from Aneesh Kumar K.V
- Add POWER9 cputable entry from Michael Neuling
- FPU/Altivec/VSX save/restore optimisations from Cyril Bur
- Add support for new ftrace ABI on ppc64le from Torsten Duwe
Various cleanups & minor fixes from:
- Adam Buchbinder, Andrew Donnellan, Balbir Singh, Christophe Leroy, Cyril
Bur, Luis Henriques, Madhavan Srinivasan, Pan Xinhui, Russell Currey,
Sukadev Bhattiprolu, Suraj Jitindar Singh.
General:
- atomics: Allow architectures to define their own __atomic_op_* helpers from
Boqun Feng
- Implement atomic{, 64}_*_return_* variants and acquire/release/relaxed
variants for (cmp)xchg from Boqun Feng
- Add powernv_defconfig from Jeremy Kerr
- Fix BUG_ON() reporting in real mode from Balbir Singh
- Add xmon command to dump OPAL msglog from Andrew Donnellan
- Add xmon command to dump process/task similar to ps(1) from Douglas Miller
- Clean up memory hotplug failure paths from David Gibson
pci/eeh:
- Redesign SR-IOV on PowerNV to give absolute isolation between VFs from Wei
Yang.
- EEH Support for SRIOV VFs from Wei Yang and Gavin Shan.
- PCI/IOV: Rename and export virtfn_{add, remove} from Wei Yang
- PCI: Add pcibios_bus_add_device() weak function from Wei Yang
- MAINTAINERS: Update EEH details and maintainership from Russell Currey
cxl:
- Support added to the CXL driver for running on both bare-metal and
hypervisor systems, from Christophe Lombard and Frederic Barrat.
- Ignore probes for virtual afu pci devices from Vaibhav Jain
perf:
- Export Power8 generic and cache events to sysfs from Sukadev Bhattiprolu
- hv-24x7: Fix usage with chip events, display change in counter values,
display domain indices in sysfs, eliminate domain suffix in event names,
from Sukadev Bhattiprolu
Freescale:
- Updates from Scott: "Highlights include 8xx optimizations, 32-bit checksum
optimizations, 86xx consolidation, e5500/e6500 cpu hotplug, more fman and
other dt bits, and minor fixes/cleanup."
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=qkAt
-----END PGP SIGNATURE-----
Merge tag 'powerpc-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"This was delayed a day or two by some build-breakage on old toolchains
which we've now fixed.
There's two PCI commits both acked by Bjorn.
There's one commit to mm/hugepage.c which is (co)authored by Kirill.
Highlights:
- Restructure Linux PTE on Book3S/64 to Radix format from Paul
Mackerras
- Book3s 64 MMU cleanup in preparation for Radix MMU from Aneesh
Kumar K.V
- Add POWER9 cputable entry from Michael Neuling
- FPU/Altivec/VSX save/restore optimisations from Cyril Bur
- Add support for new ftrace ABI on ppc64le from Torsten Duwe
Various cleanups & minor fixes from:
- Adam Buchbinder, Andrew Donnellan, Balbir Singh, Christophe Leroy,
Cyril Bur, Luis Henriques, Madhavan Srinivasan, Pan Xinhui, Russell
Currey, Sukadev Bhattiprolu, Suraj Jitindar Singh.
General:
- atomics: Allow architectures to define their own __atomic_op_*
helpers from Boqun Feng
- Implement atomic{, 64}_*_return_* variants and acquire/release/
relaxed variants for (cmp)xchg from Boqun Feng
- Add powernv_defconfig from Jeremy Kerr
- Fix BUG_ON() reporting in real mode from Balbir Singh
- Add xmon command to dump OPAL msglog from Andrew Donnellan
- Add xmon command to dump process/task similar to ps(1) from Douglas
Miller
- Clean up memory hotplug failure paths from David Gibson
pci/eeh:
- Redesign SR-IOV on PowerNV to give absolute isolation between VFs
from Wei Yang.
- EEH Support for SRIOV VFs from Wei Yang and Gavin Shan.
- PCI/IOV: Rename and export virtfn_{add, remove} from Wei Yang
- PCI: Add pcibios_bus_add_device() weak function from Wei Yang
- MAINTAINERS: Update EEH details and maintainership from Russell
Currey
cxl:
- Support added to the CXL driver for running on both bare-metal and
hypervisor systems, from Christophe Lombard and Frederic Barrat.
- Ignore probes for virtual afu pci devices from Vaibhav Jain
perf:
- Export Power8 generic and cache events to sysfs from Sukadev
Bhattiprolu
- hv-24x7: Fix usage with chip events, display change in counter
values, display domain indices in sysfs, eliminate domain suffix in
event names, from Sukadev Bhattiprolu
Freescale:
- Updates from Scott: "Highlights include 8xx optimizations, 32-bit
checksum optimizations, 86xx consolidation, e5500/e6500 cpu
hotplug, more fman and other dt bits, and minor fixes/cleanup"
* tag 'powerpc-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (179 commits)
powerpc: Fix unrecoverable SLB miss during restore_math()
powerpc/8xx: Fix do_mtspr_cpu6() build on older compilers
powerpc/rcpm: Fix build break when SMP=n
powerpc/book3e-64: Use hardcoded mttmr opcode
powerpc/fsl/dts: Add "jedec,spi-nor" flash compatible
powerpc/T104xRDB: add tdm riser card node to device tree
powerpc32: PAGE_EXEC required for inittext
powerpc/mpc85xx: Add pcsphy nodes to FManV3 device tree
powerpc/mpc85xx: Add MDIO bus muxing support to the board device tree(s)
powerpc/86xx: Introduce and use common dtsi
powerpc/86xx: Update device tree
powerpc/86xx: Move dts files to fsl directory
powerpc/86xx: Switch to kconfig fragments approach
powerpc/86xx: Update defconfigs
powerpc/86xx: Consolidate common platform code
powerpc32: Remove one insn in mulhdu
powerpc32: small optimisation in flush_icache_range()
powerpc: Simplify test in __dma_sync()
powerpc32: move xxxxx_dcache_range() functions inline
powerpc32: Remove clear_pages() and define clear_page() inline
...
During EEH recovery, hotplug is applied to the devices which don't
have drivers or their drivers don't support EEH. However, the hotplug,
which was implemented based on PCI bus, can't be applied to VF directly.
Instead, we unplug and plug individual PCI devices (VFs).
This renames virtn_{add,remove}() and exports them so they can be used
in PCI hotplug during EEH recovery.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Previously, we only supported SR-IOV on PCI Express Endpoints and Root
Complex Integrated Endpoints. This restriction has been present since
d1b054da8f ("PCI: initialize and release SR-IOV capability") added SR-IOV
support, but the spec does not require it. In fact, the SR-IOV spec r1.1,
sec 3.3, says the SR-IOV extended capability may be present for any Type 0
function.
Remove the function type test, so we can support SR-IOV on any function.
Some AMD GPUs have display outputs, use the VGA class code, are Legacy
Endpoints, and support SR-IOV. This change allows Linux to enable SR-IOV
on these devices.
[bhelgaas: changelog]
Link: https://bugzilla.kernel.org/show_bug.cgi?id=112221
Signed-off-by: Kelly Zytaruk <kelly.zytaruk@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
* pci/aer:
PCI/AER: Clear error status registers during enumeration and restore
* pci/hotplug:
PCI: pciehp: Queue power work requests in dedicated function
* pci/misc:
PCI: Turn off Request Attributes to avoid Chelsio T5 Completion erratum
x86/PCI: Make pci_subsys_init() static
PCI: Add builtin_pci_driver() to avoid registration boilerplate
PCI: Remove unnecessary "if" statement
* pci/msi:
x86/PCI: Don't alloc pcibios-irq when MSI is enabled
PCI/MSI: Export all remapped MSIs to sysfs attributes
PCI: Disable MSI on SiS 761
* pci/resource:
sparc/PCI: Add mem64 resource parsing for root bus
PCI: Expand Enhanced Allocation BAR output
PCI: Make Enhanced Allocation bitmasks more obvious
PCI: Handle Enhanced Allocation capability for SR-IOV devices
PCI: Add support for Enhanced Allocation devices
PCI: Add Enhanced Allocation register entries
PCI: Handle IORESOURCE_PCI_FIXED when assigning resources
PCI: Handle IORESOURCE_PCI_FIXED when sizing resources
PCI: Clear IORESOURCE_UNSET when reverting to firmware-assigned address
* pci/virtualization:
PCI: Fix sriov_enable() error path for pcibios_enable_sriov() failures
PCI: Wait 1 second between disabling VFs and clearing NumVFs
PCI: Reorder pcibios_sriov_disable()
PCI: Remove VFs in reverse order if virtfn_add() fails
PCI: Remove redundant validation of SR-IOV offset/stride registers
PCI: Set SR-IOV NumVFs to zero after enumeration
PCI: Enable SR-IOV ARI Capable Hierarchy before reading TotalVFs
PCI: Don't try to restore VF BARs
Disable VFs if pcibios_enable_sriov() fails, just like we do for other
errors in sriov_enable(). Call pcibios_sriov_disable() if virtfn_add()
fails.
[bhelgaas: changelog, split to separate patch for reviewability]
Fixes: 995df527f3 ("PCI: Add pcibios_sriov_enable() and pcibios_sriov_disable()")
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Per sec 3.3.3.1 of the SR-IOV spec, r1.1, we must allow 1.0s after clearing
VF Enable before reading any field in the SR-IOV Extended Capability.
Wait 1 second before calling pci_iov_set_numvfs(), which reads
PCI_SRIOV_VF_OFFSET and PCI_SRIOV_VF_STRIDE after it sets PCI_SRIOV_NUM_VF.
[bhelgaas: split to separate patch for reviewability, add spec reference]
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Move pcibios_sriov_disable() up so it's defined before a future use.
[bhelgaas: split to separate patch for reviewability]
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Wei Yang <weiyang@linux.vnet.ibm.com>
If virtfn_add() fails, we call virtfn_remove() for any previously added
devices. Remove the devices in reverse order (first-added is
last-removed), which is more natural and doesn't require an additional
variable.
[bhelgaas: changelog, split to separate patch for reviewability]
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Wei Yang <weiyang@linux.vnet.ibm.com>
SR-IOV BARs can be specified via EA entries. Extend the EA parser to
extract the SRIOV BAR resources, and modify sriov_init() to use resources
previously obtained via EA.
Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Sean O. Stalley <sean.stalley@intel.com>
Previously, we read, validated, and cached PCI_SRIOV_VF_OFFSET and
PCI_SRIOV_VF_STRIDE in sriov_enable(). But sriov_init() now does
that via compute_max_vf_buses(), so we don't need to do it again.
Remove the PCI_SRIOV_VF_OFFSET and PCI_SRIOV_VF_STRIDE config reads from
sriov_enable(). The pci_sriov structure already contains the offset and
stride corresponding to the current NumVFs.
[bhelgaas: split to separate patch for reviewability]
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Wei Yang <weiyang@linux.vnet.ibm.com>
The enumeration path should leave NumVFs set to zero. But after
4449f07972 ("PCI: Calculate maximum number of buses required for VFs"),
we call virtfn_max_buses() in the enumeration path, which changes NumVFs.
This NumVFs change is visible via lspci and sysfs until a driver enables
SR-IOV.
Iterate from TotalVFs down to zero so NumVFs is zero when we're finished
computing the maximum number of buses. Validate offset and stride in
the loop, so we can test it at every possible NumVFs setting. Rename
virtfn_max_buses() to compute_max_vf_buses() to hint that it does have a
side effect of updating iov->max_VF_buses.
[bhelgaas: changelog, rename, allow numVF==1 && stride==0, rework loop,
reverse sense of error path]
Fixes: 4449f07972 ("PCI: Calculate maximum number of buses required for VFs")
Based-on-patch-by: Ethan Zhao <ethan.zhao@oracle.com>
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
For some SR-IOV devices, the number of available virtual functions, i.e.,
TotalVFs, increases after setting the ARI Capable Hierarchy bit in the
SR-IOV Control register. This violates the SR-IOV spec, r1.1, sec 3.3.6,
which says TotalVFs is HwInit, but we don't need TotalVFs before setting
the ARI Capable bit anyway.
Set the ARI Capable Hierarchy bit (if ARI is enabled in the upstream
bridge) before reading TotalVFs.
[bhelgaas: changelog]
Signed-off-by: Ben Shelton <benjamin.h.shelton@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Per the SR-IOV spec r1.1, sec 3.3.14, the required alignment of a PF's IOV
BAR is the size of an individual VF BAR, and the size consumed is the
individual VF BAR size times NumVFs.
The PowerNV platform has additional alignment requirements to help support
its Partitionable Endpoint device isolation feature (see
Documentation/powerpc/pci_iov_resource_on_powernv.txt).
Add a pcibios_iov_resource_alignment() interface to allow platforms to
request additional alignment.
[bhelgaas: changelog, adapt to reworked pci_sriov_resource_alignment(),
drop "align" parameter]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
VFs are dynamically created when a driver enables them. On some platforms,
like PowerNV, special resources are necessary to enable VFs.
Add platform hooks for enabling and disabling VFs.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
On PowerNV, some resource reservation is needed for SR-IOV VFs that don't
exist at the bootup stage. To do the match between resources and VFs, the
code need to get the VF's BDF in advance.
Rename virtfn_bus() and virtfn_devfn() to pci_iov_virtfn_bus() and
pci_iov_virtfn_devfn() and export them.
[bhelgaas: changelog, make "busnr" int]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
An SR-IOV device can change its First VF Offset and VF Stride based on the
values of ARI Capable Hierarchy and NumVFs. The number of buses required
for all VFs is determined by NumVFs, First VF Offset, and VF Stride (see
SR-IOV spec r1.1, sec 2.1.2).
Previously pci_iov_bus_range() computed how many buses would be required by
TotalVFs, but this was based on a single NumVFs value and may not have been
the maximum for all NumVFs configurations.
Iterate over all valid NumVFs and calculate the maximum number of bus
numbers that could ever be required for VFs of this device.
[bhelgaas: changelog, compute busnr of NumVFs, not TotalVFs, remove
kerenl-doc comment marker]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The First VF Offset and VF Stride fields depend on the NumVFs setting, so
refresh the cached fields in struct pci_sriov when updating NumVFs. See
the SR-IOV spec r1.1, sec 3.3.9 and 3.3.10.
[bhelgaas: changelog, remove kernel-doc comment marker]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Most of PCI uses "res = &dev->resource[i]", not "res = dev->resource + i".
Use that style in iov.c also.
No functional change.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Currently we don't store the individual VF BAR size. We calculate it when
needed by dividing the PF's IOV resource size (which contains space for
*all* the VFs) by total_VFs or by reading the BAR in the SR-IOV capability
again.
Keep the individual VF BAR size in struct pci_sriov.barsz[], add
pci_iov_resource_size() to retrieve it, and use that instead of doing the
division or reading the SR-IOV capability BAR.
[bhelgaas: rename to "barsz[]", simplify barsz[] index computation, remove
SR-IOV capability BAR sizing]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
When we size VF BAR0, VF BAR1, etc., from the SR-IOV Capability of a PF, we
learn the alignment requirement and amount of space consumed by a single
VF. But when VFs are enabled, *each* of the NumVFs consumes that amount of
space, so the total size of the PF resource is "VF BAR size * NumVFs".
Add a printk of the total space consumed by the VFs corresponding to what
we already do for normal non-IOV BARs.
No functional change; new message only.
[bhelgaas: split out into its own patch]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
If we don't have space for all the bus numbers required to enable VFs,
print the largest bus number required and the range available.
No functional change; improved error message only.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
pci_iov_resource_bar() always sets its 'pci_bar_type' parameter to
'pci_bar_unknown'. Drop the parameter and just use 'pci_bar_unknown'
directly in the callers.
No functional change intended.
Signed-off-by: Myron Stowe <myron.stowe@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Chris Wright <chrisw@sous-sol.org>
CC: Yu Zhao <yuzhao@google.com>
Use PCI device flag helper functions when checking whether a device is
assigned. No functional change.
Signed-off-by: Ethan Zhao <ethan.zhao@oracle.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
pci_bus_add_device() always returns 0, so there's no point in returning
anything at all. Make it a void function and remove the tests of the
return value from the callers.
[bhelgaas: changelog, remove unused "err" from i82875p_setup_overfl_dev()]
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
This reverts commit 74bb1bcc7d ("PCI: handle SR-IOV Virtual Function
Migration"), removing this exported interface:
pci_sriov_migration()
Since pci_sriov_migration() is unused, it is impossible to schedule
sriov_migration_task() or use any of the other migration infrastructure.
This is based on Stephen Hemminger's patch (see link below), but goes a bit
further.
Link: http://lkml.kernel.org/r/20131227132710.7190647c@nehalam.linuxnetplumber.net
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
Per the SR-IOV spec rev 1.1:
3.4.1.9 Header Type (Offset 0Eh)
"... For VFs, this register must be RO Zero."
Unfortunately some devices get this wrong, ex. Emulex OneConnect 10Gb NIC.
When they do it makes us handle ACS testing and therefore IOMMU groups as
if they were actual multifunction devices and require ACS capabilities to
make sure there's no peer-to-peer between functions. VFs are never
traditional multifunction devices, so simply clear this bit before we get
any further into setup.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=68431
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
When SR-IOV is disabled (VF Enable is cleared), NumVFs is not very useful,
so this patch clears it out to prevent confusing lspci output like that
below. We already clear NumVFs in sriov_disable(), and this does the same
when we disable SR-IOV as part of parsing the SR-IOV capability.
$ lspci -vvv -s 13:00.0
13:00.0 Ethernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SFP+ Network Connection (rev 01)
Capabilities: [160 v1] Single Root I/O Virtualization (SR-IOV)
IOVCtl: Enable- Migration- Interrupt- MSE- ARIHierarchy+
Initial VFs: 64, Total VFs: 64, Number of VFs: 64, ...
[bhelgaas: changelog]
Signed-off-by: ethan.zhao <ethan.kernel@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Fix whitespace, capitalization, and spelling errors. No functional change.
I know "busses" is not an error, but "buses" was more common, so I used it
consistently.
Signed-off-by: Marta Rybczynska <rybczynska@gmail.com> (pci_reset_bridge_secondary_bus())
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Change the return value to -ENOSYS if a device is not an SR-IOV PF.
Previously we returned either -ENODEV or -EINVAL.
Also have pci_sriov_get_totalvfs() return 0 in the error case to make the
behaviour consistent whether CONFIG_PCI_IOV is enabled or not.
Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Currently, we only update NumVFs register during sriov_enable().
This register should also be updated during sriov_disable() and when
sriov_enable() fails. Otherwise, we will get the stale "Number of VFs"
info from lspci.
[bhelgaas: changelog]
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Trivial changes to IOV:
1) use new PCI interfaces to simplify IOV implementation
2) fix some reference count related race windows
[bhelgaas: fix virtfn_add() add bus/alloc dev error paths]
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Donald Dutile <ddutile@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Ram Pai <linuxram@us.ibm.com>
The flag pci_bus->is_added is used to guard invocation of
pcibios_fixup_bus(pci_bus). When virtfn_add_bus() is called, the
pci_bus->is_added flag has already been set, so remove the redundant
bus->is_added = 1;
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Donald Dutile <ddutile@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Ram Pai <linuxram@us.ibm.com>
Use the new pci_alloc_dev(bus) to replace the existing using of
alloc_pci_dev(void).
[bhelgaas: drop pci_bus ref later in pci_release_dev()]
Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: David Airlie <airlied@linux.ie>
Cc: Neela Syam Kolli <megaraidlinux@lsi.com>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Commit 4f535093cf "PCI: Put pci_dev in device tree as early as possible"
moves device registering from pci_bus_add_devices() to pci_device_add().
That causes problems for virtual functions because device_add(&virtfn->dev)
is called before setting the virtfn->is_virtfn flag, which then causes Xen
to report PCI virtual functions as PCI physical functions.
Fix it by setting virtfn->is_virtfn before calling pci_device_add().
[Jiang Liu]: Move the setting of virtfn->is_virtfn ahead further for better
readability and modify changelog.
Signed-off-by: Xudong Hao <xudong.hao@intel.com>
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org # v3.9+
This function is meant to add a helper function that will determine if a PF
has any VFs that are currently assigned to a guest. We currently have been
implementing this function per driver, and going forward I would like to avoid
that by making this function generic and using this helper.
v2: Removed extern from declaration of pci_vfs_assigned in pci.h and return
0 if SR-IOV is disabled with is inline with other PCI SRIOV functions.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Tony Nguyen