aboutsummaryrefslogtreecommitdiff
path: root/include/asm-sparc64
AgeCommit message (Collapse)Author
2007-08-20[SPARC64]: Need to clobber global reg vars in switch_to().David S. Miller
Otherwise the compiler can't see the things like the per-cpu area base register are changing. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-08-16[MATH-EMU]: Fix underflow exception reporting.David S. Miller
The underflow exception cases were wrong. This is one weird area of ieee1754 handling in that the underflow behavior changes based upon whether underflow is enabled in the trap enable mask of the FPU control register. As a specific case the Sparc V9 manual gives us the following description: -------------------- If UFM = 0: Underflow occurs if a nonzero result is tiny and a loss of accuracy occurs. Tininess may be detected before or after rounding. Loss of accuracy may be either a denormalization loss or an inexact result. If UFM = 1: Underflow occurs if a nonzero result is tiny. Tininess may be detected before or after rounding. -------------------- What this amounts to in the packing case is if we go subnormal, we set underflow if any of the following are true: 1) rounding sets inexact 2) we ended up rounding back up to normal (this is the case where we set the exponent to 1 and set the fraction to zero), this should set inexact too 3) underflow is set in FPU control register trap-enable mask The initially discovered example was "DBL_MIN / 16.0" which incorrectly generated an underflow. It should not, unless underflow is set in the trap-enable mask of the FPU csr. Another example, "0x0.0000000000001p-1022 / 16.0", should signal both inexact and underflow. The cpu implementations and ieee1754 literature is very clear about this. This is case #2 above. However, if underflow is set in the trap enable mask, only underflow should be set and reported as a trap. That is handled properly by the prioritization logic in arch/sparc{,64}/math-emu/math.c:record_exception(). Based upon a report and test case from Jakub Jelinek. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-08-16[SPARC64]: Create a HWCAP_SPARC_N2 and report it to userspace on Niagara-2.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-08-08[SPARC64]: Do not assume sun4v chips have load-twin/store-init support.David S. Miller
Check the cpu type in the OBP device tree before committing to using the optimized Niagara memcpy and memset implementation. If we don't recognize the cpu type, use a completely generic version. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-08-07[SPARC]: Centralize find_in_proplist() instead of duplicating N times.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-08-03[SPARC]: Fix O_CLOEXEC values.David S. Miller
The one choosen by asm-generic/fcntl.h is not appropriate for this platform. Noticed by Ulrich Drepper. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-08-03[SPARC64]: Add missing dma_sync_single_range_for_*().David S. Miller
Reported by Andrew Morton. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-31[SPARC64]: Add missing dma_get_cache_alignment().Andrew Morton
drivers/infiniband/hw/mthca/mthca_main.c: In function `mthca_init_icm': drivers/infiniband/hw/mthca/mthca_main.c:468: error: implicit declaration of function `dma_get_cache_alignment' Pinch the one from asm-generic/dma-mapping.h Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-30[SPARC]: Mark SBUS framebuffer ioctls as IGNORE in compat_ioctl.cDavid S. Miller
They are handled in a ->compat_ioctl() handler, so it's just noise when compat_ioctl.c warns which occurs when they are used on non-SBUS framebuffer devices. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-30[SPARC64]: asm-sparc64/floppy.h needs linux/pci.hDavid S. Miller
It uses pci_dev, calls pci_map_*(), etc. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-30[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling.David S. Miller
Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-20[SPARC64]: Convert parport to of_platform_driver.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-20[SPARC]: Implement fb_is_primary_device().David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-20[SPARC]: Fix serial console device detection.David S. Miller
The current scheme works on static interpretation of text names, which is wrong. The output-device setting, for example, must be resolved via an alias or similar to a full path name to the console device. Paths also contain an optional set of 'options', which starts with a colon at the end of the path. The option area is used to specify which of two serial ports ('a' or 'b') the path refers to when a device node drives multiple ports. 'a' is assumed if the option specification is missing. This was caught by the UltraSPARC-T1 simulator. The 'output-device' property was set to 'ttya' and we didn't pick upon the fact that this is an OBP alias set to '/virtual-devices/console'. Instead we saw it as the first serial console device, instead of the hypervisor console. The infrastructure is now there to take advantage of this to resolve the console correctly even in multi-head situations in fbcon too. Thanks to Greg Onufer for the bug report. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-20Merge branch 'master' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/sfr/ofcons * 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/sfr/ofcons: Create drivers/of/platform.c Create linux/of_platorm.h [SPARC/64] Rename some functions like PowerPC Begin consolidation of of_device.h Begin to consolidate of_device.c Consolidate of_find_node_by routines Consolidate of_get_next_child Consolidate of_get_parent Consolidate of_find_property Consolidate of_device_is_compatible Start split out of common open firmware code Split out common parts of prom.h
2007-07-19[SPARC64]: Fix handling of multiple vdc-port nodes.David S. Miller
The "id" property in vdc-port nodes are not unique, they are all zero. Therefore assign ID's using the parent's "cfg-handle" property which will be unique. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-19[SPARC]: Add sys_fallocate() entries.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-19[SPARC64]: Use orderly_poweroff().David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-20Create linux/of_platorm.hStephen Rothwell
Move common stuff from asm-powerpc/of_platform.h to here and move the common bits from asm-sparc*/of_device.h here as well. Create asm-sparc*/of_platform.h and move appropriate parts of of_device.h to them. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-20[SPARC/64] Rename some functions like PowerPCStephen Rothwell
This is to make the of merge easier. Also rename of_bus_type. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-20Begin consolidation of of_device.hStephen Rothwell
This just moves the common stuff from the arch of_device.h files to linux/of_device.h. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-20Consolidate of_find_node_by routinesStephen Rothwell
This consolidates the routines of_find_node_by_path, of_find_node_by_name, of_find_node_by_type and of_find_compatible_device. Again, the comparison of strings are done differently by Sparc and PowerPC and also these add read_locks around the iterations. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-20Consolidate of_get_parentStephen Rothwell
This requires creating dummy of_node_{get,put} routines for sparc and sparc64. It also adds a read_lock around the parent accesses. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-20Consolidate of_find_propertyStephen Rothwell
The only change here is that a readlock is taken while the property list is being traversed on Sparc where it was not taken previously. Also, Sparc uses strcasecmp to compare property names while PowerPC uses strcmp. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-20Consolidate of_device_is_compatibleStephen Rothwell
The only difference here is that Sparc uses strncmp to match compatibility names while PowerPC uses strncasecmp. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-20Start split out of common open firmware codeStephen Rothwell
This creates drivers/of/base.c (depending on CONFIG_OF) and puts the first trivially common bits from the prom.c files into it. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-20Split out common parts of prom.hStephen Rothwell
This creates linux/of.h and includes asm/prom.h from it. We also include linux/of.h from asm/prom.h while we transition. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net>
2007-07-19[PATCH] sched: sched_cacheflush is now unusedRalf Baechle
Since Ingo's recent scheduler rewrite which was merged as commit 0437e109e1841607f2988891eaa36c531c6aa6ac sched_cacheflush is unused. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-07-19arch: personality independent stack topPeter Zijlstra
New arch macro STACK_TOP_MAX it gives the larges valid stack address for the architecture in question. It differs from STACK_TOP in that it will not distinguish between personalities but will always return the largest possible address. This is used to create the initial stack on execve, which we will move down to the proper location once the binfmt code has figured out where that is. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ollie Wild <aaw@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19define new percpu interface for shared dataFenghua Yu
per cpu data section contains two types of data. One set which is exclusively accessed by the local cpu and the other set which is per cpu, but also shared by remote cpus. In the current kernel, these two sets are not clearely separated out. This can potentially cause the same data cacheline shared between the two sets of data, which will result in unnecessary bouncing of the cacheline between cpus. One way to fix the problem is to cacheline align the remotely accessed per cpu data, both at the beginning and at the end. Because of the padding at both ends, this will likely cause some memory wastage and also the interface to achieve this is not clean. This patch: Moves the remotely accessed per cpu data (which is currently marked as ____cacheline_aligned_in_smp) into a different section, where all the data elements are cacheline aligned. And as such, this differentiates the local only data and remotely accessed data cleanly. Signed-off-by: Fenghua Yu <fenghua.yu@intel.com> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Christoph Lameter <clameter@sgi.com> Cc: <linux-arch@vger.kernel.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19jprobes: remove JPROBE_ENTRY()Michael Ellerman
AFAICT now that jprobe.entry is a void *, JPROBE_ENTRY doesn't do anything useful - so remove it .. I've left a do-nothing version so that out-of-tree jprobes code will still compile without modifications. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Cc: Prasanna S Panchamukhi <prasanna@in.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-18[SPARC]: Mark sparc and sparc64 as not having virt_to_busStephen Rothwell
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-18[SPARC64]: Massively simplify VIO device layer and support hot add/remove.David S. Miller
Create and destroy VIO devices in response to MD update events. These run synchronously inside of the MD update mutex so the VIO layer doesn't need to do internal locking of any sort. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-18[SPARC64]: Add basic infrastructure for MD add/remove notification.David S. Miller
And add dummy handlers for the VIO device layer. These will be filled in with real code after the vdc, vnet, and ds drivers are reworked to have simpler dependencies on the VIO device tree. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-17fbdev: detect primary display deviceAntonino A. Daplas
Add function helper, fb_is_primary_device(). Given struct fb_info, it will return a nonzero value if the device is the primary display. Currently, only the i386 is supported where the function checks for the IORESOURCE_ROM_SHADOW flag. Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17fbdev: move arch-specific bits to their respective subdirectoriesAntonino A. Daplas
Move arch-specific bits of fb_mmap() to their respective subdirectories [bob.picco@hp.com: efi_range_is_wc is referenced but not declared] [bunk@stusta.de: fix include/asm-m68k/fb.h] Signed-off-by: Antonino Daplas <adaplas@gmail.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16Merge branch 'master' of ↵Linus Torvalds
master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6 * 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6: (26 commits) [SPARC64]: Fix UP build. [SPARC64]: dr-cpu unconfigure support. [SERIAL]: Fix console write locking in sparc drivers. [SPARC64]: Give more accurate errors in dr_cpu_configure(). [SPARC64]: Clear cpu_{core,sibling}_map[] in smp_fill_in_sib_core_maps() [SPARC64]: Fix leak when DR added cpu does not bootup. [SPARC64]: Add ->set_affinity IRQ handlers. [SPARC64]: Process dr-cpu events in a kthread instead of workqueue. [SPARC64]: More sensible udelay implementation. [SPARC64]: SMP build fixes. [SPARC64]: mdesc.c needs linux/mm.h [SPARC64]: Fix build regressions added by dr-cpu changes. [SPARC64]: Unconditionally register vio_bus_type. [SPARC64]: Initial LDOM cpu hotplug support. [SPARC64]: Fix setting of variables in LDOM guest. [SPARC64]: Fix MD property lifetime bugs. [SPARC64]: Abstract out mdesc accesses for better MD update handling. [SPARC64]: Use more mearningful names for IRQ registry. [SPARC64]: Initial domain-services driver. [SPARC64]: Export powerd facilities for external entities. ...
2007-07-16Introduce compat_u64 and compat_s64 typesArnd Bergmann
One common problem with 32 bit system call and ioctl emulation is the different alignment rules between i386 and 64 bit machines. A number of drivers work around this by marking the compat structures as 'attribute((packed))', which is not the right solution because it breaks all the non-x86 architectures that want to use the same compat code. Hopefully, this patch improves the situation, it introduces two new types, compat_u64 and compat_s64. These are defined on all architectures to have the same size and alignment as the 32 bit version of u64 and s64. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: David S. Miller <davem@davemloft.net> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Andi Kleen <ak@suse.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vasily Tarasov <vtaras@openvz.org> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16page table handling cleanupJan Beulich
Kill pte_rdprotect(), pte_exprotect(), pte_mkread(), pte_mkexec(), pte_read(), pte_exec(), and pte_user() except where arch-specific code is making use of them. Signed-off-by: Jan Beulich <jbeulich@novell.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16[SPARC64]: dr-cpu unconfigure support.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: More sensible udelay implementation.David S. Miller
Take a page from the powerpc folks and just calculate the delay factor directly. Since frequency scaling chips use a system-tick register, the value is going to be the same system-wide. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Fix build regressions added by dr-cpu changes.David S. Miller
Do not select HOTPLUG_CPU from SUN_LDOMS, that causes HOTPLUG_CPU to be selected even on non-SMP which is illegal. Only build hvtramp.o when SMP, just like trampoline.o Protect dr-cpu code in ds.c with HOTPLUG_CPU. Likewise move ldom_startcpu_cpuid() to smp.c and protect it and the call site with SUN_LDOMS && HOTPLUG_CPU. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Initial LDOM cpu hotplug support.David S. Miller
Only adding cpus is supports at the moment, removal will come next. When new cpus are configured, the machine description is updated. When we get the configure request we pass in a cpu mask of to-be-added cpus to the mdesc CPU node parser so it only fetches information for those cpus. That code also proceeds to update the SMT/multi-core scheduling bitmaps. cpu_up() does all the work and we return the status back over the DS channel. CPUs via dr-cpu need to be booted straight out of the hypervisor, and this requires: 1) A new trampoline mechanism. CPUs are booted straight out of the hypervisor with MMU disabled and running in physical addresses with no mappings installed in the TLB. The new hvtramp.S code sets up the critical cpu state, installs the locked TLB mappings for the kernel, and turns the MMU on. It then proceeds to follow the logic of the existing trampoline.S SMP cpu bringup code. 2) All calls into OBP have to be disallowed when domaining is enabled. Since cpus boot straight into the kernel from the hypervisor, OBP has no state about that cpu and therefore cannot handle being invoked on that cpu. Luckily it's only a handful of interfaces which can be called after the OBP device tree is obtained. For example, rebooting, halting, powering-off, and setting options node variables. CPU removal support will require some infrastructure changes here. Namely we'll have to process the requests via a true kernel thread instead of in a workqueue. workqueues run on a per-cpu thread, but when unconfiguring we might need to force the thread to execute on another cpu if the current cpu is the one being removed. Removal of a cpu also causes the kernel to destroy that cpu's workqueue running thread. Another issue on removal is that we may have interrupts still pointing to the cpu-to-be-removed. So new code will be needed to walk the active INO list and retarget those cpus as-needed. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Fix setting of variables in LDOM guest.David S. Miller
There is a special domain services capability for setting variables in the OBP options node. Guests don't have permanent store for the OBP variables like a normal system, so they are instead maintained in the LDOM control node or in the SC. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Fix MD property lifetime bugs.David S. Miller
Property values cannot be referenced outside of mdesc_grab()/mdesc_release() pairs. The only major offender was the VIO bus layer, easily fixed. Add some commentary to mdesc.h describing these rules. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Abstract out mdesc accesses for better MD update handling.David S. Miller
Since we have to be able to handle MD updates, having an in-tree set of data structures representing the MD objects actually makes things more painful. The MD itself is easy to parse, and we can implement the existing interfaces using direct parsing of the MD binary image. The MD is now reference counted, so accesses have to now take the form: handle = mdesc_grab(); ... operations on MD ... mdesc_release(handle); The only remaining issue are cases where code holds on to references to MD property values. mdesc_get_property() returns a direct pointer to the property value, most cases just pull in the information they need and discard the pointer, but there are few that use the pointer directly over a long lifetime. Those will be fixed up in a subsequent changeset. A preliminary handler for MD update events from domain services is there, it is rudimentry but it works and handles all of the reference counting. It does not check the generation number of the MDs, and it does not generate a "add/delete" list for notification to interesting parties about MD changes but that will be forthcoming. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Use more mearningful names for IRQ registry.David S. Miller
All of the interrupts say "LDX RX" and "LDX TX" currently which is next to useless. Put a device specific prefix before "RX" and "TX" instead which makes it much more useful. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Export powerd facilities for external entities.David S. Miller
Besides the existing usage for power-button interrupts, we'll want to make use of this code for domain-services where the LDOM manager can send reboot requests to the guest node. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Assorted LDC bug cures.David S. Miller
1) LDC_MODE_RELIABLE is deprecated an unused by anything, plus it and LDC_MODE_STREAM were mis-numbered. 2) read_stream() should try to read as much as possible into the per-LDC stream buffer area, so do not trim the read_nonraw() length by the caller's size parameter. 3) Send data ACKs when necessary in read_nonraw(). 4) In read_nonraw() when we get a pure ACK, advance the RX head unconditionally past it. 5) Provide the ACKID field in the ldcdgb() packet dump in read_nonraw(). This helps debugging stream mode LDC channel problems. 6) Decrease verbosity of rx_data_wait() so that it is more useful. A debugging message each loop iteration is too much. 7) In process_data_ack() stop the loop checking when we hit lp->tx_tail not lp->tx_head. 8) Set the seqid field properly in send_data_nack(). Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-16[SPARC64]: Add LDOM virtual channel driver and VIO device layer.David S. Miller
Virtual devices on Sun Logical Domains are built on top of a virtual channel framework. This, with help of hypervisor interfaces, provides a link layer protocol with basic handshaking over which virtual device clients and servers communicate. Built on top of this is a VIO device protocol which has it's own handshaking and message types. At this layer attributes are exchanged (disk size, network device addresses, etc.) descriptor rings are registered, and data transfers are triggers and replied to. Signed-off-by: David S. Miller <davem@davemloft.net>