The .data section in the arm64 linker script currently lacks a
definition for page-aligned data. This leads to a .page_aligned
section being placed between the end of data and start of bss.
This patch corrects that by using the generic RW_DATA_SECTION
macro which includes support for page-aligned data.
Signed-off-by: Mark Salter <msalter@redhat.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Commit e8765b265a69 (arm64: read enable-method for CPU0) introduced
checks for the enable method on CPU0 (to be later used with CPU
suspend). However, if the kernel is compiled for UP and a DT file is
used with a method like 'spin-table', Linux complains about 'invalid
enable method'. This patch turns it into an 'unsupported enable method'
warning.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Once the cpu_logical_map for any logical cpu is populated with the
corresponding physical identifier(i.e. mpidr), it's device node can
be retrieved using the DT helper 'of_get_cpu_node'. Currently the
device tree parsing code to get boot cpu node is duplicated in
'cpu_read_bootcpu_ops'.
This patch replaces the code parsing the device tree for the boot
cpu with of_get_cpu_node.
Signed-off-by: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
OF/DT core library provides architecture specific hook to match the
logical cpu index with the corresponding physical identifier.
On ARM64, the MPIDR_EL1 contains specific bitfields(MPIDR_EL1.Aff{3..0})
which uniquely identify a CPU, in addition to some non-identifying
information and reserved bits. The ARM cpu binding defines the 'reg'
property to only contain the affinity bits, and any cpu nodes with other
bits set in their 'reg' entry are skipped.
This patch overrides the weak definition of arch_match_cpu_phys_id
with ARM64 specific version using MPIDR_EL1.Aff{3..0} as cpu physical
identifiers.
Signed-off-by: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Some drivers (ACPI notably) use ioremap_cache() to map an area which could
either be outside of kernel RAM or in an already mapped reserved area of
RAM. To avoid aliases with different caching attributes, ioremap() does
not allow RAM to be remapped. But for ioremap_cache(), the existing kernel
mapping may be used.
Signed-off-by: Mark Salter <msalter@redhat.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
On an (even slightly) oversubscribed system, spinlocks are quickly
becoming a bottleneck, as some vcpus are spinning, waiting for a
lock to be released, while the vcpu holding the lock may not be
running at all.
The solution is to trap blocking WFEs and tell KVM that we're
now spinning. This ensures that other vpus will get a scheduling
boost, allowing the lock to be released more quickly. Also, using
CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT slightly improves the performance
when the VM is severely overcommited.
Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
This is the ARM part of Christoph's patchset cleaning up the various
uses of __get_cpu_var across the tree.
The idea is to convert __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations
that use the offset. Thereby address calculations are avoided and fewer
registers are used when code is generated.
[will: fixed debug ref counting checks and pcpu array accesses]
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
- Transparent Huge Pages and hugetlbfs support for KVM/ARM
- Yield CPU when guest executes WFE to speed up CPU overcommit
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)
iQEcBAABAgAGBQJSZ5NVAAoJEEtpOizt6ddyEJgH+wWw6KWqHlParb+rf04cqCQV
Fj3euz+SpYr2U2u0RimgkmeahUiGUhnlBSSH+tkLmt1if6nLawBJbUcIhaZMVdv+
cvS6k+NtK7ibwPOyFeoZCS8taEbVDut2YgrtRKbne6QDLRYBEXFtpY8o6ptLoSu4
ifQCF0FZyElCGLylSxFt9GsK+LjNjQWatVrzoHap9d58u2bma6GYwr4mEzVMHms7
REtTvpwWgsDR5C/69aG8wE4cpJZALH3OeCgy6AccdzTLaQWWpK2YLWz8AFOvoYx6
EsFmBFHZYcuwN+fv2jILgA3Is1oWwqI6k5lL+N3g/oTNNALDSWnfiJkXypJsfow=
=2Ijm
-----END PGP SIGNATURE-----
Merge tag 'kvm-arm-for-3.13-2' of git://git.linaro.org/people/cdall/linux-kvm-arm into kvm-queue
Updates for KVM/ARM, take 2 including:
- Transparent Huge Pages and hugetlbfs support for KVM/ARM
- Yield CPU when guest executes WFE to speed up CPU overcommit
This patch updates the barrier semantics in the kuser helper functions
to take advantage of the ARMv8 additions to AArch32, which are
guaranteed to be available in situations where these functions will be
called.
Note that this slightly changes the cmpxchg functions in that they are
no longer necessarily full barriers if they return 1. However, the
documentation only states they include their own barriers "as needed",
not that they are obligated to act as a full barrier for the caller.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
CC: Matthew Leach <matthew.leach@arm.com>
CC: Dave Martin <dave.martin@arm.com>
CC: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch fixes ARMV8_EVTYPE_* macros since evtCount (event number)
field width is 10bits in event selection register.
Signed-off-by: Vinayak Kale <vkale@apm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch wires up CONFIG_CPU_BIG_ENDIAN for the AArch64 kernel
configuration.
Selecting this option builds a big-endian kernel which can boot into a
big-endian userspace.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The owner and next members of the arch_spinlock_t structure need to be
swapped when compiling for big endian.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Matthew Leach <matthew.leach@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Currently when CPUs are brought online via a spin-table, the address
they should jump to is written to the cpu-release-addr in the kernel's
native endianness. As the kernel may switch endianness, secondaries
might read the value byte-reversed from what was intended, and they
would jump to the wrong address.
As the only current arm64 spin-table implementations are
little-endian, stricten up the arm64 spin-table definition such that
the value written to cpu-release-addr is _always_ little-endian
regardless of the endianness of any CPU. If a spinning CPU is
operating big-endian, it must byte-reverse the value before jumping to
handle this.
Signed-off-by: Matthew Leach <matthew.leach@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The endianness of memory accesses at EL2 and EL1 are configured by
SCTLR_EL2.EE and SCTLR_EL1.EE respectively. When the kernel is booted,
the state of SCTLR_EL{2,1}.EE is unknown, and thus the kernel must
ensure that they are set before performing any memory accesses.
This patch ensures that SCTLR_EL{2,1} are configured appropriately at
boot for kernels of either endianness.
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Matthew Leach <matthew.leach@arm.com>
[catalin.marinas@arm.com: fix SCTLR_EL1.E0E bit setting in head.S]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Currently, the code for setting the __cpu_boot_mode flag is munged in
with el2_setup. This makes things difficult on a BE bringup as a
memory access has to have occurred before el2_setup which is the place
that we'd like to set the endianess on the current EL.
Create a new function for setting __cpu_boot_mode and have el2_setup
return the mode the CPU. Also define a new constant in virt.h,
BOOT_CPU_MODE_EL1, for readability.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Matthew Leach <matthew.leach@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Add CPU_LE and CPU_BE to select assembler code in little and big
endian configurations respectively.
Signed-off-by: Matthew Leach <matthew.leach@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Currently the sigreturn compat code is copied to an offset in the
vectors table. When using a BE kernel this data will be stored in the
wrong endianess so when returning from a signal on a 32-bit BE system,
arbitrary code will be executed.
Instead of declaring the code inside a struct and copying that, use
the assembler's .byte directives to store the code in the correct
endianess regardless of platform endianess.
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Matthew Leach <matthew.leach@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The arm64 port contains wrappers for arm32 syscalls that pass 64-bit
values. These wrappers concatenate the two registers to hold a 64-bit
value in a single X register. On BE, however, the lower and higher
words are swapped.
Create a new assembler macro, regs_to_64, that when on BE systems
swaps the registers in the orr instruction.
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Matthew Leach <matthew.leach@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch adds support for BE8 AArch32 tasks to the compat layer.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
uname -m reports the machine field from the current utsname, which should
reflect the endianness of the system.
This patch reports ELF_PLATFORM for the field, so that everything appears
consistent from userspace.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch adds support for the aarch64_be ELF format to the AArch64 ELF
loader.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
For big-endian processors, we must include
linux/byteorder/big_endian.h to get the relevant definitions for
swabbing between CPU order and a defined endianness.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch adds big-endian support to the AArch64 top-level Makefile.
This currently just passes the relevant flags to the toolchain and is
predicated on a Kconfig option that will be introduced later on.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This is similar to what it is done on X86: biovecs are prevented from merging
otherwise every dma requests would be forced to bounce on the swiotlb buffer.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Changes in v7:
- remove the extra autotranslate check in biomerge.c.
Introduce xen_dma_map_page, xen_dma_unmap_page,
xen_dma_sync_single_for_cpu and xen_dma_sync_single_for_device.
They have empty implementations on x86 and ia64 but they call the
corresponding platform dma_ops function on arm and arm64.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Changes in v9:
- xen_dma_map_page return void, avoid page_to_phys.
This patch adds support for using PSCI CPU_OFF calls for CPU hotplug.
With this code it is possible to hot unplug CPUs with "psci" as their
boot-method, as long as there's an appropriate cpu_off function id
specified in the psci node.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch adds the basic infrastructure necessary to support
CPU_HOTPLUG on arm64, based on the arm implementation. Actual hotplug
support will depend on an implementation's cpu_operations (e.g. PSCI).
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
With the advent of CPU_HOTPLUG, the enable-method property for CPU0 may
tells us something useful (i.e. how to hotplug it back on), so we must
read it along with all the enable-method for all the other CPUs. Even
on UP the enable-method may tell us useful information (e.g. if a core
has some mechanism that might be usable for cpuidle), so we should
always read it.
This patch factors out the reading of the enable method, and ensures
that CPU0's enable method is read regardless of whether the kernel is
built with SMP support.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The arm64 kernel has an internal holding pen, which is necessary for
some systems where we can't bring CPUs online individually and must hold
multiple CPUs in a safe area until the kernel is able to handle them.
The current SMP infrastructure for arm64 is closely coupled to this
holding pen, and alternative boot methods must launch CPUs into the pen,
where they sit before they are launched into the kernel proper.
With PSCI (and possibly other future boot methods), we can bring CPUs
online individually, and need not perform the secondary_holding_pen
dance. Instead, this patch factors the holding pen management code out
to the spin-table boot method code, as it is the only boot method
requiring the pen.
A new entry point for secondaries, secondary_entry is added for other
boot methods to use, which bypasses the holding pen and its associated
overhead when bringing CPUs online. The smp.pen.text section is also
removed, as the pen can live in head.text without problem.
The cpu_operations structure is extended with two new functions,
cpu_boot and cpu_postboot, for bringing a cpu into the kernel and
performing any post-boot cleanup required by a bootmethod (e.g.
resetting the secondary_holding_pen_release to INVALID_HWID).
Documentation is added for cpu_operations.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
For hotplug support, we're going to want a place to store operations
that do more than bring CPUs online, and it makes sense to group these
with our current smp_enable_ops. For cpuidle support, we'll want to
group additional functions, and we may want them even for UP kernels.
This patch renames smp_enable_ops to the more general cpu_operations,
and pulls the definitions out of smp code such that they can be used in
UP kernels. While we're at it, fix up instances of the cpu parameter to
be an unsigned int, drop the init markings and rename the *_cpu
functions to cpu_* to reduce future churn when cpu_operations is
extended.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The functions in psci.c are only used from smp_psci.c, and smp_psci
cannot function without psci.c. Additionally psci.c is built when !SMP,
where it's expected that cpu_suspend may be useful.
This patch unifies the two files, removing pointless duplication and
paving the way for PSCI support in UP systems.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This function may be called from loadable modules, so it needs
exporting.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Loc Ho <lho@apm.com>
This patch introduces cmpxchg64_relaxed for arm64 using the existing
cmpxchg_local macro, which performs a cmpxchg operation (up to 64 bits)
without barrier semantics.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Our spinlocks are only 32-bit (2x16-bit tickets) and our cmpxchg can
deal with 8-bytes (as one would hope!).
This patch wires up the cmpxchg-based lockless lockref implementation
for arm64.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch introduces a ticket lock implementation for arm64, along the
same lines as the implementation for arch/arm/.
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
In ftrace_syscall_enter(),
syscall_get_arguments(..., 0, n, ...)
if (i == 0) { <handle orig_x0> ...; n--;}
memcpy(..., n * sizeof(args[0]));
If 'number of arguments(n)' is zero and 'argument index(i)' is also zero in
syscall_get_arguments(), none of arguments should be copied by memcpy().
Otherwise 'n--' can be a big positive number and unexpected amount of data
will be copied. Tracing system calls which take no argument, say sync(void),
may hit this case and eventually make the system corrupted.
This patch fixes the issue both in syscall_get_arguments() and
syscall_set_arguments().
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The KVM PSCI code blindly assumes that vcpu_id and MPIDR are
the same thing. This is true when vcpus are organized as a flat
topology, but is wrong when trying to emulate any other topology
(such as A15 clusters).
Change the KVM PSCI CPU_ON code to look at the MPIDR instead
of the vcpu_id to pick a target CPU.
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Support huge pages in KVM/ARM and KVM/ARM64. The pud_huge checking on
the unmap path may feel a bit silly as the pud_huge check is always
defined to false, but the compiler should be smart about this.
Note: This deals only with VMAs marked as huge which are allocated by
users through hugetlbfs only. Transparent huge pages can only be
detected by looking at the underlying pages (or the page tables
themselves) and this patch so far simply maps these on a page-by-page
level in the Stage-2 page tables.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)
iQEcBAABAgAGBQJSXeGaAAoJEEtpOizt6ddyeyYH/AnWdKGUELjxC0lIBDkTitnD
znyzSxqXG6z1Z6d+EYI3XCL1eB3dtyOBSJsZj45adG4HXGkCmGqosgDzivGO6GcI
yhjYgXGhP8ZvIwky1ijbVQODaEE70SEYqKwyCpU4rLJw2uRkbfRaxTrpgnusL8Bg
RG37uaOS/sasLoNxCe5GEUjm8BFGbvZGVAjcL7yJTPBw5qd7GYBxndFSTILa2iRQ
ikoBD0bUVhoaBUqSNQenoNllUBwDpFJF1HiEXKMJkUIxX/FggrSvRp8A/MAWDBw0
6Ef1P8Pt/hMfMQpOOeu8QFWM2s+smh2rTkO/O9mqi/tSvEf5YcZHMAl48B8OR88=
=tJ2u
-----END PGP SIGNATURE-----
Merge tag 'kvm-arm-for-3.13-1' of git://git.linaro.org/people/cdall/linux-kvm-arm into next
Updates for KVM/ARM including cpu=host and Cortex-A7 support
Now when the main kvm code relying on these defines has been moved to
the x86 specific part of the world, we can get rid of these.
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Pull more timekeeping items for v3.13 from John Stultz:
* Small cleanup in the clocksource code.
* Fix for rtc-pl031 to let it work with alarmtimers.
* Move arm64 to using the generic sched_clock framework & resulting
cleanup in the generic sched_clock code.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Now that prom.h is optional, all the empty prom.h headers can be removed.
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Vineet Gupta <vgupta@synopsys.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Aurelien Jacquiot <a-jacquiot@ti.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Chris Zankel <chris@zankel.net>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Remove unnecessary prom.h include in preparation to make prom.h optional.
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Cc: Will Deacon <will.deacon@arm.com>
Convert arm64 to use the common of_flat_dt_get_machine_name function.
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Register with the generic sched_clock framework now that it
supports 64 bits. This fixes two problems with the current
sched_clock support for machines using the architected timers.
First off, we don't subtract the start value from subsequent
sched_clock calls so we can potentially start off with
sched_clock returning gigantic numbers. Second, there is no
support for suspend/resume handling so problems such as discussed
in 6a4dae5 (ARM: 7565/1: sched: stop sched_clock() during
suspend, 2012-10-23) can happen without this patch. Finally, it
allows us to move the sched_clock setup into drivers clocksource
out of the arch ports.
Cc: Christopher Covington <cov@codeaurora.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
xen_swiotlb_alloc_coherent needs to allocate a coherent buffer for cpu
and devices. On native x86 is sufficient to call __get_free_pages in
order to get a coherent buffer, while on ARM (and potentially ARM64) we
need to call the native dma_ops->alloc implementation.
Introduce xen_alloc_coherent_pages to abstract the arch specific buffer
allocation.
Similarly introduce xen_free_coherent_pages to free a coherent buffer:
on x86 is simply a call to free_pages while on ARM and ARM64 is
arm_dma_ops.free.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Changes in v7:
- rename __get_dma_ops to __generic_dma_ops;
- call __generic_dma_ops(hwdev)->alloc/free on arm64 too.
Changes in v6:
- call __get_dma_ops to get the native dma_ops pointer on arm.
We can't simply override arm_dma_ops with xen_dma_ops because devices
are allowed to have their own dma_ops and they take precedence over
arm_dma_ops. When running on Xen as initial domain, we always want
xen_dma_ops to be the one in use.
We introduce __generic_dma_ops to allow xen_dma_ops functions to call
back to the native implementation.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
CC: will.deacon@arm.com
Changes in v7:
- return xen_dma_ops only if we are the initial domain;
- rename __get_dma_ops to __generic_dma_ops.
Xen on arm and arm64 needs SWIOTLB_XEN: when running on Xen we need to
program the hardware with mfns rather than pfns for dma addresses.
Remove SWIOTLB_XEN dependency on X86 and PCI and make XEN select
SWIOTLB_XEN on arm and arm64.
At the moment always rely on swiotlb-xen, but when Xen starts supporting
hardware IOMMUs we'll be able to avoid it conditionally on the presence
of an IOMMU on the platform.
Implement xen_create_contiguous_region on arm and arm64: for the moment
we assume that dom0 has been mapped 1:1 (physical addresses == machine
addresses) therefore we don't need to call XENMEM_exchange. Simply
return the physical address as dma address.
Initialize the xen-swiotlb from xen_early_init (before the native
dma_ops are initialized), set xen_dma_ops to &xen_swiotlb_dma_ops.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Changes in v8:
- assume dom0 is mapped 1:1, no need to call XENMEM_exchange.
Changes in v7:
- call __set_phys_to_machine_multi from xen_create_contiguous_region and
xen_destroy_contiguous_region to update the P2M;
- don't call XENMEM_unpin, it has been removed;
- call XENMEM_exchange instead of XENMEM_exchange_and_pin;
- set nr_exchanged to 0 before calling the hypercall.
Changes in v6:
- introduce and export xen_dma_ops;
- call xen_mm_init from as arch_initcall.
Changes in v4:
- remove redefinition of DMA_ERROR_CODE;
- update the code to use XENMEM_exchange_and_pin and XENMEM_unpin;
- add a note about hardware IOMMU in the commit message.
Changes in v3:
- code style changes;
- warn on XENMEM_put_dma_buf failures.
Introduce physical to machine and machine to physical tracking
mechanisms based on rbtrees for arm/xen and arm64/xen.
We need it because any guests on ARM are an autotranslate guests,
therefore a physical address is potentially different from a machine
address. When programming a device to do DMA, we need to be
extra-careful to use machine addresses rather than physical addresses to
program the device. Therefore we need to know the physical to machine
mappings.
For the moment we assume that dom0 starts with a 1:1 physical to machine
mapping, in other words physical addresses correspond to machine
addresses. However when mapping a foreign grant reference, obviously the
1:1 model doesn't work anymore. So at the very least we need to be able
to track grant mappings.
We need locking to protect accesses to the two trees.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Changes in v8:
- move pfn_to_mfn and mfn_to_pfn to page.h as static inline functions;
- no need to walk the tree if phys_to_mach.rb_node is NULL;
- correctly handle multipage p2m entries;
- substitute the spin_lock with a rwlock.
