openwrt/staging/blogic.git
6 years agoKVM: arm/arm64: mask/unmask daif around VHE guests
James Morse [Mon, 15 Jan 2018 19:39:00 +0000 (19:39 +0000)]
KVM: arm/arm64: mask/unmask daif around VHE guests

Non-VHE systems take an exception to EL2 in order to world-switch into the
guest. When returning from the guest KVM implicitly restores the DAIF
flags when it returns to the kernel at EL1.

With VHE none of this exception-level jumping happens, so KVMs
world-switch code is exposed to the host kernel's DAIF values, and KVM
spills the guest-exit DAIF values back into the host kernel.
On entry to a guest we have Debug and SError exceptions unmasked, KVM
has switched VBAR but isn't prepared to handle these. On guest exit
Debug exceptions are left disabled once we return to the host and will
stay this way until we enter user space.

Add a helper to mask/unmask DAIF around VHE guests. The unmask can only
happen after the hosts VBAR value has been synchronised by the isb in
__vhe_hyp_call (via kvm_call_hyp()). Masking could be as late as
setting KVMs VBAR value, but is kept here for symmetry.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: kernel: Prepare for a DISR user
James Morse [Mon, 15 Jan 2018 19:38:59 +0000 (19:38 +0000)]
arm64: kernel: Prepare for a DISR user

KVM would like to consume any pending SError (or RAS error) after guest
exit. Today it has to unmask SError and use dsb+isb to synchronise the
CPU. With the RAS extensions we can use ESB to synchronise any pending
SError.

Add the necessary macros to allow DISR to be read and converted to an
ESR.

We clear the DISR register when we enable the RAS cpufeature, and the
kernel has not executed any ESB instructions. Any value we find in DISR
must have belonged to firmware. Executing an ESB instruction is the
only way to update DISR, so we can expect firmware to have handled
any deferred SError. By the same logic we clear DISR in the idle path.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Unconditionally enable IESB on exception entry/return for firmware-first
James Morse [Mon, 15 Jan 2018 19:38:58 +0000 (19:38 +0000)]
arm64: Unconditionally enable IESB on exception entry/return for firmware-first

ARM v8.2 has a feature to add implicit error synchronization barriers
whenever the CPU enters or returns from an exception level. Add this to the
features we always enable. CPUs that don't support this feature will treat
the bit as RES0.

This feature causes RAS errors that are not yet visible to software to
become pending SErrors. We expect to have firmware-first RAS support
so synchronised RAS errors will be take immediately to EL3.
Any system without firmware-first handling of errors will take the SError
either immediatly after exception return, or when we unmask SError after
entry.S's work.

Adding IESB to the ELx flags causes it to be enabled by KVM and kexec
too.

Platform level RAS support may require additional firmware support.

Cc: Christoffer Dall <christoffer.dall@linaro.org>
Suggested-by: Will Deacon <will.deacon@arm.com>
Link: https://www.spinics.net/lists/kvm-arm/msg28192.html
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: kernel: Survive corrected RAS errors notified by SError
James Morse [Mon, 15 Jan 2018 19:38:57 +0000 (19:38 +0000)]
arm64: kernel: Survive corrected RAS errors notified by SError

Prior to v8.2, SError is an uncontainable fatal exception. The v8.2 RAS
extensions use SError to notify software about RAS errors, these can be
contained by the Error Syncronization Barrier.

An ACPI system with firmware-first may use SError as its 'SEI'
notification. Future patches may add code to 'claim' this SError as a
notification.

Other systems can distinguish these RAS errors from the SError ESR and
use the AET bits and additional data from RAS-Error registers to handle
the error. Future patches may add this kernel-first handling.

Without support for either of these we will panic(), even if we received
a corrected error. Add code to decode the severity of RAS errors. We can
safely ignore contained errors where the CPU can continue to make
progress. For all other errors we continue to panic().

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: cpufeature: Detect CPU RAS Extentions
Xie XiuQi [Mon, 15 Jan 2018 19:38:56 +0000 (19:38 +0000)]
arm64: cpufeature: Detect CPU RAS Extentions

ARM's v8.2 Extentions add support for Reliability, Availability and
Serviceability (RAS). On CPUs with these extensions system software
can use additional barriers to isolate errors and determine if faults
are pending. Add cpufeature detection.

Platform level RAS support may require additional firmware support.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Xie XiuQi <xiexiuqi@huawei.com>
[Rebased added config option, reworded commit message]
Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: sysreg: Move to use definitions for all the SCTLR bits
James Morse [Mon, 15 Jan 2018 19:38:55 +0000 (19:38 +0000)]
arm64: sysreg: Move to use definitions for all the SCTLR bits

__cpu_setup() configures SCTLR_EL1 using some hard coded hex masks,
and el2_setup() duplicates some this when setting RES1 bits.

Lets make this the same as KVM's hyp_init, which uses named bits.

First, we add definitions for all the SCTLR_EL{1,2} bits, the RES{1,0}
bits, and those we want to set or clear.

Add a build_bug checks to ensures all bits are either set or clear.
This means we don't need to preserve endian-ness configuration
generated elsewhere.

Finally, move the head.S and proc.S users of these hard-coded masks
over to the macro versions.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: cpufeature: __this_cpu_has_cap() shouldn't stop early
James Morse [Mon, 15 Jan 2018 19:38:54 +0000 (19:38 +0000)]
arm64: cpufeature: __this_cpu_has_cap() shouldn't stop early

this_cpu_has_cap() tests caps->desc not caps->matches, so it stops
walking the list when it finds a 'silent' feature, instead of
walking to the end of the list.

Prior to v4.6's 644c2ae198412 ("arm64: cpufeature: Test 'matches' pointer
to find the end of the list") we always tested desc to find the end of
a capability list. This was changed for dubious things like PAN_NOT_UAO.
v4.7's e3661b128e53e ("arm64: Allow a capability to be checked on
single CPU") added this_cpu_has_cap() using the old desc style test.

CC: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: fpsimd: Fix state leakage when migrating after sigreturn
Dave Martin [Fri, 15 Dec 2017 18:34:38 +0000 (18:34 +0000)]
arm64: fpsimd: Fix state leakage when migrating after sigreturn

When refactoring the sigreturn code to handle SVE, I changed the
sigreturn implementation to store the new FPSIMD state from the
user sigframe into task_struct before reloading the state into the
CPU regs.  This makes it easier to convert the data for SVE when
needed.

However, it turns out that the fpsimd_state structure passed into
fpsimd_update_current_state is not fully initialised, so assigning
the structure as a whole corrupts current->thread.fpsimd_state.cpu
with uninitialised data.

This means that if the garbage data written to .cpu happens to be a
valid cpu number, and the task is subsequently migrated to the cpu
identified by the that number, and then tries to enter userspace,
the CPU FPSIMD regs will be assumed to be correct for the task and
not reloaded as they should be.  This can result in returning to
userspace with the FPSIMD registers containing data that is stale or
that belongs to another task or to the kernel.

Knowingly handing around a kernel structure that is incompletely
initialised with user data is a potential source of mistakes,
especially across source file boundaries.  To help avoid a repeat
of this issue, this patch adapts the relevant internal API to hand
around the user-accessible subset only: struct user_fpsimd_state.

To avoid future surprises, this patch also converts all uses of
struct fpsimd_state that really only access the user subset, to use
struct user_fpsimd_state.  A few missing consts are added to
function prototypes for good measure.

Thanks to Will for spotting the cause of the bug here.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Correct type for PUD macros
Punit Agrawal [Wed, 10 Jan 2018 19:07:26 +0000 (19:07 +0000)]
arm64: Correct type for PUD macros

The PUD macros (PUD_TABLE_BIT, PUD_TYPE_MASK, PUD_TYPE_SECT) use the
pgdval_t even when pudval_t is available. Even though the underlying
type for both (u64) is the same it is confusing and may lead to issues
in the future.

Fix this by using pudval_t to define the PUD_* macros.

Fixes: 084bd29810a56 ("ARM64: mm: HugeTLB support.")
Fixes: 206a2a73a62d3 ("arm64: mm: Create gigabyte kernel logical mappings where possible")
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Inform user if software PAN is in use
Stephen Boyd [Wed, 29 Nov 2017 23:39:49 +0000 (15:39 -0800)]
arm64: Inform user if software PAN is in use

It isn't entirely obvious if we're using software PAN because we
don't say anything about it in the boot log. But if we're using
hardware PAN we'll print a nice CPU feature message indicating
it. Add a print for software PAN too so we know if it's being
used or not.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: fix comment above tcr_compute_pa_size
Kristina Martsenko [Mon, 15 Jan 2018 15:23:50 +0000 (15:23 +0000)]
arm64: fix comment above tcr_compute_pa_size

The 'pos' argument is used to select where in TCR to write the value:
the IPS or PS bitfield.

Fixes: 787fd1d019b2 ("arm64: limit PA size to supported range")
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoKVM: arm/arm64: fix HYP ID map extension to 52 bits
Kristina Martsenko [Mon, 15 Jan 2018 15:23:49 +0000 (15:23 +0000)]
KVM: arm/arm64: fix HYP ID map extension to 52 bits

Commit fa2a8445b1d3 incorrectly masks the index of the HYP ID map pgd
entry, causing a non-VHE kernel to hang during boot. This happens when
VA_BITS=48 and the ID map text is in 52-bit physical memory. In this
case we don't need an extra table level but need more entries in the
top-level table, so we need to map into hyp_pgd and need to use
__kvm_idmap_ptrs_per_pgd to mask in the extra bits. However,
__create_hyp_mappings currently masks by PTRS_PER_PGD instead.

Fix it so that we always use __kvm_idmap_ptrs_per_pgd for the HYP ID
map. This ensures that we use the larger mask for the top-level ID map
table when it has more entries. In all other cases, PTRS_PER_PGD is used
as normal.

Fixes: fa2a8445b1d3 ("arm64: allow ID map to be extended to 52 bits")
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: fix ID map extension to 52 bits
Kristina Martsenko [Mon, 15 Jan 2018 15:23:48 +0000 (15:23 +0000)]
arm64: fix ID map extension to 52 bits

Commit fa2a8445b1d3 added support for extending the ID map to 52 bits,
but accidentally dropped a required change to __cpu_uses_extended_idmap.
As a result, the kernel fails to boot when VA_BITS = 48 and the ID map
text is in 52-bit physical memory, because we reduce TCR.T0SZ to cover
the ID map, but then never set it back to VA_BITS.

Add back the change, and also clean up some double parentheses.

Fixes: fa2a8445b1d3 ("arm64: allow ID map to be extended to 52 bits")
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Stop printing the virtual memory layout
Laura Abbott [Tue, 19 Dec 2017 19:28:10 +0000 (11:28 -0800)]
arm64: Stop printing the virtual memory layout

Printing kernel addresses should be done in limited circumstances, mostly
for debugging purposes. Printing out the virtual memory layout at every
kernel bootup doesn't really fall into this category so delete the prints.
There are other ways to get the same information.

Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agofirmware: arm_sdei: Fix return value check in sdei_present_dt()
Wei Yongjun [Mon, 15 Jan 2018 10:41:53 +0000 (10:41 +0000)]
firmware: arm_sdei: Fix return value check in sdei_present_dt()

In case of error, the function of_platform_device_create() returns
NULL pointer not ERR_PTR(). The IS_ERR() test in the return value
check should be replaced with NULL test.

Fixes: 677a60bd2003 ("firmware: arm_sdei: Discover SDEI support via ACPI")
Acked-by: James Morse <james.morse@arm.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoperf: dsu: Use signed field for dsu_pmu->num_counters
Suzuki K Poulose [Mon, 15 Jan 2018 10:51:16 +0000 (10:51 +0000)]
perf: dsu: Use signed field for dsu_pmu->num_counters

We set dsu_pmu->num_counters to -1, when the DSU is allocated
but not initialised when none of the CPUs are active in the DSU.
However, we use an unsigned field for num_counters. Switch this
to a signed field.

Fixes: 7520fa99246d ("perf: ARM DynamIQ Shared Unit PMU support")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: capabilities: Handle duplicate entries for a capability
Suzuki K Poulose [Tue, 9 Jan 2018 16:12:18 +0000 (16:12 +0000)]
arm64: capabilities: Handle duplicate entries for a capability

Sometimes a single capability could be listed multiple times with
differing matches(), e.g, CPU errata for different MIDR versions.
This breaks verify_local_cpu_feature() and this_cpu_has_cap() as
we stop checking for a capability on a CPU with the first
entry in the given table, which is not sufficient. Make sure we
run the checks for all entries of the same capability. We do
this by fixing __this_cpu_has_cap() to run through all the
entries in the given table for a match and reuse it for
verify_local_cpu_feature().

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: cpu_errata: Add Kryo to Falkor 1003 errata
Stephen Boyd [Wed, 13 Dec 2017 22:19:37 +0000 (14:19 -0800)]
arm64: cpu_errata: Add Kryo to Falkor 1003 errata

The Kryo CPUs are also affected by the Falkor 1003 errata, so
we need to do the same workaround on Kryo CPUs. The MIDR is
slightly more complicated here, where the PART number is not
always the same when looking at all the bits from 15 to 4. Drop
the lower 8 bits and just look at the top 4 to see if it's '2'
and then consider those as Kryo CPUs. This covers all the
combinations without having to list them all out.

Fixes: 38fd94b0275c ("arm64: Work around Falkor erratum 1003")
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Extend early page table code to allow for larger kernels
Steve Capper [Thu, 11 Jan 2018 10:11:59 +0000 (10:11 +0000)]
arm64: Extend early page table code to allow for larger kernels

Currently the early assembler page table code assumes that precisely
1xpgd, 1xpud, 1xpmd are sufficient to represent the early kernel text
mappings.

Unfortunately this is rarely the case when running with a 16KB granule,
and we also run into limits with 4KB granule when building much larger
kernels.

This patch re-writes the early page table logic to compute indices of
mappings for each level of page table, and if multiple indices are
required, the next-level page table is scaled up accordingly.

Also the required size of the swapper_pg_dir is computed at link time
to cover the mapping [KIMAGE_ADDR + VOFFSET, _end]. When KASLR is
enabled, an extra page is set aside for each level that may require extra
entries at runtime.

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: entry: Move the trampoline to be before PAN
Steve Capper [Thu, 11 Jan 2018 10:11:58 +0000 (10:11 +0000)]
arm64: entry: Move the trampoline to be before PAN

The trampoline page tables are positioned after the early page tables in
the kernel linker script.

As we are about to change the early page table logic to resolve the
swapper size at link time as opposed to compile time, the
SWAPPER_DIR_SIZE variable (currently used to locate the trampline)
will be rendered unsuitable for low level assembler.

This patch solves this issue by moving the trampoline before the PAN
page tables. The offset to the trampoline from ttbr1 can then be
expressed by: PAGE_SIZE + RESERVED_TTBR0_SIZE, which is available to the
entry assembler.

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Re-order reserved_ttbr0 in linker script
Steve Capper [Thu, 11 Jan 2018 10:11:57 +0000 (10:11 +0000)]
arm64: Re-order reserved_ttbr0 in linker script

Currently one resolves the location of the reserved_ttbr0 for PAN by
taking a positive offset from swapper_pg_dir. In a future patch we wish
to extend the swapper s.t. its size is determined at link time rather
than comile time, rendering SWAPPER_DIR_SIZE unsuitable for such a low
level calculation.

In this patch we re-arrange the order of the linker script s.t. instead
one computes reserved_ttbr0 by subtracting RESERVED_TTBR0_SIZE from
swapper_pg_dir.

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: sdei: Add trampoline code for remapping the kernel
James Morse [Mon, 8 Jan 2018 15:38:18 +0000 (15:38 +0000)]
arm64: sdei: Add trampoline code for remapping the kernel

When CONFIG_UNMAP_KERNEL_AT_EL0 is set the SDEI entry point and the rest
of the kernel may be unmapped when we take an event. If this may be the
case, use an entry trampoline that can switch to the kernel page tables.

We can't use the provided PSTATE to determine whether to switch page
tables as we may have interrupted the kernel's entry trampoline, (or a
normal-priority event that interrupted the kernel's entry trampoline).
Instead test for a user ASID in ttbr1_el1.

Save a value in regs->addr_limit to indicate whether we need to restore
the original ASID when returning from this event. This value is only used
by do_page_fault(), which we don't call with the SDEI regs.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: mmu: add the entry trampolines start/end section markers into sections.h
James Morse [Mon, 8 Jan 2018 15:38:17 +0000 (15:38 +0000)]
arm64: mmu: add the entry trampolines start/end section markers into sections.h

SDEI needs to calculate an offset in the trampoline page too. Move
the extern char[] to sections.h.

This patch just moves code around.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agofirmware: arm_sdei: Discover SDEI support via ACPI
James Morse [Mon, 8 Jan 2018 15:38:16 +0000 (15:38 +0000)]
firmware: arm_sdei: Discover SDEI support via ACPI

SDEI defines a new ACPI table to indicate the presence of the interface.
The conduit is discovered in the same way as PSCI.

For ACPI we need to create the platform device ourselves as SDEI doesn't
have an entry in the DSDT.

The SDEI platform device should be created after ACPI has been initialised
so that we can parse the table, but before GHES devices are created, which
may register SDE events if they use SDEI as their notification type.

Reviewed-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: acpi: Remove __init from acpi_psci_use_hvc() for use by SDEI
James Morse [Mon, 8 Jan 2018 15:38:15 +0000 (15:38 +0000)]
arm64: acpi: Remove __init from acpi_psci_use_hvc() for use by SDEI

SDEI inherits the 'use hvc' bit that is also used by PSCI. PSCI does all
its initialisation early, SDEI does its late.

Remove the __init annotation from acpi_psci_use_hvc().

Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agofirmware: arm_sdei: add support for CPU private events
James Morse [Mon, 8 Jan 2018 15:38:14 +0000 (15:38 +0000)]
firmware: arm_sdei: add support for CPU private events

Private SDE events are per-cpu, and need to be registered and enabled
on each CPU.

Hide this detail from the caller by adapting our {,un}register and
{en,dis}able calls to send an IPI to each CPU if the event is private.

CPU private events are unregistered when the CPU is powered-off, and
re-registered when the CPU is brought back online. This saves bringing
secondary cores back online to call private_reset() on shutdown, kexec
and resume from hibernate.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agofirmware: arm_sdei: Add support for CPU and system power states
James Morse [Mon, 8 Jan 2018 15:38:13 +0000 (15:38 +0000)]
firmware: arm_sdei: Add support for CPU and system power states

When a CPU enters an idle lower-power state or is powering off, we
need to mask SDE events so that no events can be delivered while we
are messing with the MMU as the registered entry points won't be valid.

If the system reboots, we want to unregister all events and mask the CPUs.
For kexec this allows us to hand a clean slate to the next kernel
instead of relying on it to call sdei_{private,system}_data_reset().

For hibernate we unregister all events and re-register them on restore,
in case we restored with the SDE code loaded at a different address.
(e.g. KASLR).

Add all the notifiers necessary to do this. We only support shared events
so all events are left registered and enabled over CPU hotplug.

Reviewed-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
[catalin.marinas@arm.com: added CPU_PM_ENTER_FAILED case]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: kernel: Add arch-specific SDEI entry code and CPU masking
James Morse [Mon, 8 Jan 2018 15:38:12 +0000 (15:38 +0000)]
arm64: kernel: Add arch-specific SDEI entry code and CPU masking

The Software Delegated Exception Interface (SDEI) is an ARM standard
for registering callbacks from the platform firmware into the OS.
This is typically used to implement RAS notifications.

Such notifications enter the kernel at the registered entry-point
with the register values of the interrupted CPU context. Because this
is not a CPU exception, it cannot reuse the existing entry code.
(crucially we don't implicitly know which exception level we interrupted),

Add the entry point to entry.S to set us up for calling into C code. If
the event interrupted code that had interrupts masked, we always return
to that location. Otherwise we pretend this was an IRQ, and use SDEI's
complete_and_resume call to return to vbar_el1 + offset.

This allows the kernel to deliver signals to user space processes. For
KVM this triggers the world switch, a quick spin round vcpu_run, then
back into the guest, unless there are pending signals.

Add sdei_mask_local_cpu() calls to the smp_send_stop() code, this covers
the panic() code-path, which doesn't invoke cpuhotplug notifiers.

Because we can interrupt entry-from/exit-to another EL, we can't trust the
value in sp_el0 or x29, even if we interrupted the kernel, in this case
the code in entry.S will save/restore sp_el0 and use the value in
__entry_task.

When we have VMAP stacks we can interrupt the stack-overflow test, which
stirs x0 into sp, meaning we have to have our own VMAP stacks. For now
these are allocated when we probe the interface. Future patches will add
refcounting hooks to allow the arch code to allocate them lazily.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: uaccess: Add PAN helper
James Morse [Mon, 8 Jan 2018 15:38:11 +0000 (15:38 +0000)]
arm64: uaccess: Add PAN helper

Add __uaccess_{en,dis}able_hw_pan() helpers to set/clear the PSTATE.PAN
bit.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Add vmap_stack header file
James Morse [Mon, 8 Jan 2018 15:38:10 +0000 (15:38 +0000)]
arm64: Add vmap_stack header file

Today the arm64 arch code allocates an extra IRQ stack per-cpu. If we
also have SDEI and VMAP stacks we need two extra per-cpu VMAP stacks.

Move the VMAP stack allocation out to a helper in a new header file.
This avoids missing THREADINFO_GFP, or getting the all-important alignment
wrong.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agofirmware: arm_sdei: Add driver for Software Delegated Exceptions
James Morse [Mon, 8 Jan 2018 15:38:09 +0000 (15:38 +0000)]
firmware: arm_sdei: Add driver for Software Delegated Exceptions

The Software Delegated Exception Interface (SDEI) is an ARM standard
for registering callbacks from the platform firmware into the OS.
This is typically used to implement firmware notifications (such as
firmware-first RAS) or promote an IRQ that has been promoted to a
firmware-assisted NMI.

Add the code for detecting the SDEI version and the framework for
registering and unregistering events. Subsequent patches will add the
arch-specific backend code and the necessary power management hooks.

Only shared events are supported, power management, private events and
discovery for ACPI systems will be added by later patches.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoDocs: dt: add devicetree binding for describing arm64 SDEI firmware
James Morse [Mon, 8 Jan 2018 15:38:08 +0000 (15:38 +0000)]
Docs: dt: add devicetree binding for describing arm64 SDEI firmware

The Software Delegated Exception Interface (SDEI) is an ARM standard
for registering callbacks from the platform firmware into the OS.
This is typically used to implement RAS notifications, or from an
IRQ that has been promoted to a firmware-assisted NMI.

Add a new devicetree binding to describe the SDE firmware interface.

Signed-off-by: James Morse <james.morse@arm.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoKVM: arm64: Stop save/restoring host tpidr_el1 on VHE
James Morse [Mon, 8 Jan 2018 15:38:07 +0000 (15:38 +0000)]
KVM: arm64: Stop save/restoring host tpidr_el1 on VHE

Now that a VHE host uses tpidr_el2 for the cpu offset we no longer
need KVM to save/restore tpidr_el1. Move this from the 'common' code
into the non-vhe code. While we're at it, on VHE we don't need to
save the ELR or SPSR as kernel_entry in entry.S will have pushed these
onto the kernel stack, and will restore them from there. Move these
to the non-vhe code as we need them to get back to the host.

Finally remove the always-copy-tpidr we hid in the stage2 setup
code, cpufeature's enable callback will do this for VHE, we only
need KVM to do it for non-vhe. Add the copy into kvm-init instead.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: alternatives: use tpidr_el2 on VHE hosts
James Morse [Mon, 8 Jan 2018 15:38:06 +0000 (15:38 +0000)]
arm64: alternatives: use tpidr_el2 on VHE hosts

Now that KVM uses tpidr_el2 in the same way as Linux's cpu_offset in
tpidr_el1, merge the two. This saves KVM from save/restoring tpidr_el1
on VHE hosts, and allows future code to blindly access per-cpu variables
without triggering world-switch.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoKVM: arm64: Change hyp_panic()s dependency on tpidr_el2
James Morse [Mon, 8 Jan 2018 15:38:05 +0000 (15:38 +0000)]
KVM: arm64: Change hyp_panic()s dependency on tpidr_el2

Make tpidr_el2 a cpu-offset for per-cpu variables in the same way the
host uses tpidr_el1. This lets tpidr_el{1,2} have the same value, and
on VHE they can be the same register.

KVM calls hyp_panic() when anything unexpected happens. This may occur
while a guest owns the EL1 registers. KVM stashes the vcpu pointer in
tpidr_el2, which it uses to find the host context in order to restore
the host EL1 registers before parachuting into the host's panic().

The host context is a struct kvm_cpu_context allocated in the per-cpu
area, and mapped to hyp. Given the per-cpu offset for this CPU, this is
easy to find. Change hyp_panic() to take a pointer to the
struct kvm_cpu_context. Wrap these calls with an asm function that
retrieves the struct kvm_cpu_context from the host's per-cpu area.

Copy the per-cpu offset from the hosts tpidr_el1 into tpidr_el2 during
kvm init. (Later patches will make this unnecessary for VHE hosts)

We print out the vcpu pointer as part of the panic message. Add a back
reference to the 'running vcpu' in the host cpu context to preserve this.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoKVM: arm/arm64: Convert kvm_host_cpu_state to a static per-cpu allocation
James Morse [Mon, 8 Jan 2018 15:38:04 +0000 (15:38 +0000)]
KVM: arm/arm64: Convert kvm_host_cpu_state to a static per-cpu allocation

kvm_host_cpu_state is a per-cpu allocation made from kvm_arch_init()
used to store the host EL1 registers when KVM switches to a guest.

Make it easier for ASM to generate pointers into this per-cpu memory
by making it a static allocation.

Signed-off-by: James Morse <james.morse@arm.com>
Acked-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoKVM: arm64: Store vcpu on the stack during __guest_enter()
James Morse [Mon, 8 Jan 2018 15:38:03 +0000 (15:38 +0000)]
KVM: arm64: Store vcpu on the stack during __guest_enter()

KVM uses tpidr_el2 as its private vcpu register, which makes sense for
non-vhe world switch as only KVM can access this register. This means
vhe Linux has to use tpidr_el1, which KVM has to save/restore as part
of the host context.

If the SDEI handler code runs behind KVMs back, it mustn't access any
per-cpu variables. To allow this on systems with vhe we need to make
the host use tpidr_el2, saving KVM from save/restoring it.

__guest_enter() stores the host_ctxt on the stack, do the same with
the vcpu.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoMerge branch 'for-next/perf' of git://git.kernel.org/pub/scm/linux/kernel/git/will...
Catalin Marinas [Fri, 12 Jan 2018 14:33:56 +0000 (14:33 +0000)]
Merge branch 'for-next/perf' of git://git./linux/kernel/git/will/linux

Support for the Cluster PMU part of the ARM DynamIQ Shared Unit (DSU).

* 'for-next/perf' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux:
  perf: ARM DynamIQ Shared Unit PMU support
  dt-bindings: Document devicetree binding for ARM DSU PMU
  arm_pmu: Use of_cpu_node_to_id helper
  arm64: Use of_cpu_node_to_id helper for CPU topology parsing
  irqchip: gic-v3: Use of_cpu_node_to_id helper
  coresight: of: Use of_cpu_node_to_id helper
  of: Add helper for mapping device node to logical CPU number
  perf: Export perf_event_update_userpage

6 years agoarm64: cputype: Add MIDR values for Cavium ThunderX2 CPUs
Jayachandran C [Mon, 8 Jan 2018 06:53:35 +0000 (22:53 -0800)]
arm64: cputype: Add MIDR values for Cavium ThunderX2 CPUs

Add the older Broadcom ID as well as the new Cavium ID for ThunderX2
CPUs.

Signed-off-by: Jayachandran C <jnair@caviumnetworks.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Implement branch predictor hardening for Falkor
Shanker Donthineni [Fri, 5 Jan 2018 20:28:59 +0000 (14:28 -0600)]
arm64: Implement branch predictor hardening for Falkor

Falkor is susceptible to branch predictor aliasing and can
theoretically be attacked by malicious code. This patch
implements a mitigation for these attacks, preventing any
malicious entries from affecting other victim contexts.

Signed-off-by: Shanker Donthineni <shankerd@codeaurora.org>
[will: fix label name when !CONFIG_KVM and remove references to MIDR_FALKOR]
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Implement branch predictor hardening for affected Cortex-A CPUs
Will Deacon [Wed, 3 Jan 2018 12:46:21 +0000 (12:46 +0000)]
arm64: Implement branch predictor hardening for affected Cortex-A CPUs

Cortex-A57, A72, A73 and A75 are susceptible to branch predictor aliasing
and can theoretically be attacked by malicious code.

This patch implements a PSCI-based mitigation for these CPUs when available.
The call into firmware will invalidate the branch predictor state, preventing
any malicious entries from affecting other victim contexts.

Co-developed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75
Will Deacon [Wed, 3 Jan 2018 11:19:34 +0000 (11:19 +0000)]
arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75

Hook up MIDR values for the Cortex-A72 and Cortex-A75 CPUs, since they
will soon need MIDR matches for hardening the branch predictor.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: KVM: Make PSCI_VERSION a fast path
Marc Zyngier [Wed, 3 Jan 2018 16:38:37 +0000 (16:38 +0000)]
arm64: KVM: Make PSCI_VERSION a fast path

For those CPUs that require PSCI to perform a BP invalidation,
going all the way to the PSCI code for not much is a waste of
precious cycles. Let's terminate that call as early as possible.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: KVM: Use per-CPU vector when BP hardening is enabled
Marc Zyngier [Wed, 3 Jan 2018 16:38:35 +0000 (16:38 +0000)]
arm64: KVM: Use per-CPU vector when BP hardening is enabled

Now that we have per-CPU vectors, let's plug then in the KVM/arm64 code.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Add skeleton to harden the branch predictor against aliasing attacks
Will Deacon [Wed, 3 Jan 2018 11:17:58 +0000 (11:17 +0000)]
arm64: Add skeleton to harden the branch predictor against aliasing attacks

Aliasing attacks against CPU branch predictors can allow an attacker to
redirect speculative control flow on some CPUs and potentially divulge
information from one context to another.

This patch adds initial skeleton code behind a new Kconfig option to
enable implementation-specific mitigations against these attacks for
CPUs that are affected.

Co-developed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Move post_ttbr_update_workaround to C code
Marc Zyngier [Tue, 2 Jan 2018 18:19:39 +0000 (18:19 +0000)]
arm64: Move post_ttbr_update_workaround to C code

We will soon need to invoke a CPU-specific function pointer after changing
page tables, so move post_ttbr_update_workaround out into C code to make
this possible.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agodrivers/firmware: Expose psci_get_version through psci_ops structure
Will Deacon [Tue, 2 Jan 2018 21:45:41 +0000 (21:45 +0000)]
drivers/firmware: Expose psci_get_version through psci_ops structure

Entry into recent versions of ARM Trusted Firmware will invalidate the CPU
branch predictor state in order to protect against aliasing attacks.

This patch exposes the PSCI "VERSION" function via psci_ops, so that it
can be invoked outside of the PSCI driver where necessary.

Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: cpufeature: Pass capability structure to ->enable callback
Will Deacon [Tue, 2 Jan 2018 21:37:25 +0000 (21:37 +0000)]
arm64: cpufeature: Pass capability structure to ->enable callback

In order to invoke the CPU capability ->matches callback from the ->enable
callback for applying local-CPU workarounds, we need a handle on the
capability structure.

This patch passes a pointer to the capability structure to the ->enable
callback.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Take into account ID_AA64PFR0_EL1.CSV3
Will Deacon [Mon, 27 Nov 2017 18:29:30 +0000 (18:29 +0000)]
arm64: Take into account ID_AA64PFR0_EL1.CSV3

For non-KASLR kernels where the KPTI behaviour has not been overridden
on the command line we can use ID_AA64PFR0_EL1.CSV3 to determine whether
or not we should unmap the kernel whilst running at EL0.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: Kconfig: Reword UNMAP_KERNEL_AT_EL0 kconfig entry
Will Deacon [Tue, 14 Nov 2017 16:19:39 +0000 (16:19 +0000)]
arm64: Kconfig: Reword UNMAP_KERNEL_AT_EL0 kconfig entry

Although CONFIG_UNMAP_KERNEL_AT_EL0 does make KASLR more robust, it's
actually more useful as a mitigation against speculation attacks that
can leak arbitrary kernel data to userspace through speculation.

Reword the Kconfig help message to reflect this, and make the option
depend on EXPERT so that it is on by default for the majority of users.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: use RET instruction for exiting the trampoline
Will Deacon [Tue, 14 Nov 2017 16:15:59 +0000 (16:15 +0000)]
arm64: use RET instruction for exiting the trampoline

Speculation attacks against the entry trampoline can potentially resteer
the speculative instruction stream through the indirect branch and into
arbitrary gadgets within the kernel.

This patch defends against these attacks by forcing a misprediction
through the return stack: a dummy BL instruction loads an entry into
the stack, so that the predicted program flow of the subsequent RET
instruction is to a branch-to-self instruction which is finally resolved
as a branch to the kernel vectors with speculation suppressed.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: v8.4: Support for new floating point multiplication instructions
Dongjiu Geng [Wed, 13 Dec 2017 10:13:56 +0000 (18:13 +0800)]
arm64: v8.4: Support for new floating point multiplication instructions

ARM v8.4 extensions add new neon instructions for performing a
multiplication of each FP16 element of one vector with the corresponding
FP16 element of a second vector, and to add or subtract this without an
intermediate rounding to the corresponding FP32 element in a third vector.

This patch detects this feature and let the userspace know about it via a
HWCAP bit and MRS emulation.

Cc: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com>
Reviewed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoarm64: asid: Do not replace active_asids if already 0
Catalin Marinas [Wed, 27 Dec 2017 15:12:56 +0000 (15:12 +0000)]
arm64: asid: Do not replace active_asids if already 0

Under some uncommon timing conditions, a generation check and
xchg(active_asids, A1) in check_and_switch_context() on P1 can race with
an ASID roll-over on P2. If P2 has not seen the update to
active_asids[P1], it can re-allocate A1 to a new task T2 on P2. P1 ends
up waiting on the spinlock since the xchg() returned 0 while P2 can go
through a second ASID roll-over with (T2,A1,G2) active on P2. This
roll-over copies active_asids[P1] == A1,G1 into reserved_asids[P1] and
active_asids[P2] == A1,G2 into reserved_asids[P2]. A subsequent
scheduling of T1 on P1 and T2 on P2 would match reserved_asids and get
their generation bumped to G3:

P1 P2
--                                      --
TTBR0.BADDR = T0
TTBR0.ASID = A0
asid_generation = G1
check_and_switch_context(T1,A1,G1)
  generation match
check_and_switch_context(T2,A0,G0)
            new_context()
    ASID roll-over
    asid_generation = G2
    flush_context()
      active_asids[P1] = 0
      asid_map[A1] = 0
      reserved_asids[P1] = A0,G0
  xchg(active_asids, A1)
    active_asids[P1] = A1,G1
    xchg returns 0
  spin_lock_irqsave()
    allocated ASID (T2,A1,G2)
    asid_map[A1] = 1
  active_asids[P2] = A1,G2
...
check_and_switch_context(T3,A0,G0)
  new_context()
    ASID roll-over
    asid_generation = G3
    flush_context()
      active_asids[P1] = 0
      asid_map[A1] = 1
      reserved_asids[P1] = A1,G1
      reserved_asids[P2] = A1,G2
    allocated ASID (T3,A2,G3)
    asid_map[A2] = 1
  active_asids[P2] = A2,G3
  new_context()
    check_update_reserved_asid(A1,G1)
      matches reserved_asid[P1]
      reserved_asid[P1] = A1,G3
  updated T1 ASID to (T1,A1,G3)
check_and_switch_context(T2,A1,G2)
  new_context()
    check_and_switch_context(A1,G2)
      matches reserved_asids[P2]
      reserved_asids[P2] = A1,G3
  updated T2 ASID to (T2,A1,G3)

At this point, we have two tasks, T1 and T2 both using ASID A1 with the
latest generation G3. Any of them is allowed to be scheduled on the
other CPU leading to two different tasks with the same ASID on the same
CPU.

This patch changes the xchg to cmpxchg so that the active_asids is only
updated if non-zero to avoid a race with an ASID roll-over on a
different CPU.

The ASID allocation algorithm has been formally verified using the TLA+
model checker (see
https://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/kernel-tla.git/tree/asidalloc.tla
for the spec).

Reviewed-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoperf: ARM DynamIQ Shared Unit PMU support
Suzuki K Poulose [Tue, 2 Jan 2018 11:25:33 +0000 (11:25 +0000)]
perf: ARM DynamIQ Shared Unit PMU support

Add support for the Cluster PMU part of the ARM DynamIQ Shared Unit (DSU).
The DSU integrates one or more cores with an L3 memory system, control
logic, and external interfaces to form a multicore cluster. The PMU
allows counting the various events related to L3, SCU etc, along with
providing a cycle counter.

The PMU can be accessed via system registers, which are common
to the cores in the same cluster. The PMU registers follow the
semantics of the ARMv8 PMU, mostly, with the exception that
the counters record the cluster wide events.

This driver is mostly based on the ARMv8 and CCI PMU drivers.
The driver only supports ARM64 at the moment. It can be extended
to support ARM32 by providing register accessors like we do in
arch/arm64/include/arm_dsu_pmu.h.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
6 years agodt-bindings: Document devicetree binding for ARM DSU PMU
Suzuki K Poulose [Tue, 2 Jan 2018 11:25:32 +0000 (11:25 +0000)]
dt-bindings: Document devicetree binding for ARM DSU PMU

This patch documents the devicetree bindings for ARM DSU PMU.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: devicetree@vger.kernel.org
Cc: frowand.list@gmail.com
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
6 years agoarm_pmu: Use of_cpu_node_to_id helper
Suzuki K Poulose [Tue, 2 Jan 2018 11:25:31 +0000 (11:25 +0000)]
arm_pmu: Use of_cpu_node_to_id helper

Use the new generic helper, of_cpu_node_to_id(), to map a
a phandle to the logical CPU number while parsing the
PMU irq affinity.

Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
6 years agoarm64: Use of_cpu_node_to_id helper for CPU topology parsing
Suzuki K Poulose [Tue, 2 Jan 2018 11:25:30 +0000 (11:25 +0000)]
arm64: Use of_cpu_node_to_id helper for CPU topology parsing

Make use of the new generic helper to convert an of_node of a CPU
to the logical CPU id in parsing the topology.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
6 years agoirqchip: gic-v3: Use of_cpu_node_to_id helper
Suzuki K Poulose [Tue, 2 Jan 2018 11:25:29 +0000 (11:25 +0000)]
irqchip: gic-v3: Use of_cpu_node_to_id helper

Use the new generic helper of_cpu_node_to_id() instead
of using our own version to map a device node to logical CPU
number.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
6 years agocoresight: of: Use of_cpu_node_to_id helper
Suzuki K Poulose [Tue, 2 Jan 2018 11:25:28 +0000 (11:25 +0000)]
coresight: of: Use of_cpu_node_to_id helper

Reuse the new generic helper, of_cpu_node_to_id() to map a
given CPU phandle to a logical CPU number.

Acked-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Tested-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
6 years agoof: Add helper for mapping device node to logical CPU number
Suzuki K Poulose [Tue, 2 Jan 2018 11:25:27 +0000 (11:25 +0000)]
of: Add helper for mapping device node to logical CPU number

Add a helper to map a device node to a logical CPU number to avoid
duplication. Currently this is open coded in different places (e.g
gic-v3, coresight). The helper tries to map device node to a "possible"
logical CPU id, which may not be online yet. It is the responsibility
of the user to make sure that the CPU is online. The helper uses
of_cpu_device_node_get() to retrieve the device node for a given CPU
(which uses per_cpu data if available else falls back to slower
of_get_cpu_node()).

Cc: devicetree@vger.kernel.org
Cc: Frank Rowand <frowand.list@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
6 years agoperf: Export perf_event_update_userpage
Suzuki K Poulose [Tue, 2 Jan 2018 11:25:26 +0000 (11:25 +0000)]
perf: Export perf_event_update_userpage

Export perf_event_update_userpage() so that PMU driver using them,
can be built as modules.

Acked-by: Peter Zilstra <peterz@infradead.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
6 years agoarm64: make label allocation style consistent in tishift
Jason A. Donenfeld [Tue, 7 Nov 2017 02:24:04 +0000 (11:24 +0900)]
arm64: make label allocation style consistent in tishift

This is entirely cosmetic, but somehow it was missed when sending
differing versions of this patch. This just makes the file a bit more
uniform.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agoARM64 / cpuidle: Use new cpuidle macro for entering retention state
Prashanth Prakash [Wed, 15 Nov 2017 17:11:50 +0000 (10:11 -0700)]
ARM64 / cpuidle: Use new cpuidle macro for entering retention state

CPU_PM_CPU_IDLE_ENTER_RETENTION skips calling cpu_pm_enter() and
cpu_pm_exit(). By not calling cpu_pm functions in idle entry/exit
paths we can reduce the latency involved in entering and exiting
the low power idle state.

On ARM64 based Qualcomm server platform we measured below overhead
for calling cpu_pm_enter and cpu_pm_exit for retention states.

workload: stress --hdd #CPUs --hdd-bytes 32M  -t 30
Average overhead of cpu_pm_enter - 1.2us
Average overhead of cpu_pm_exit  - 3.1us

Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Prashanth Prakash <pprakash@codeaurora.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
6 years agocpuidle: Add new macro to enter a retention idle state
Prashanth Prakash [Wed, 15 Nov 2017 17:11:49 +0000 (10:11 -0700)]
cpuidle: Add new macro to enter a retention idle state

If a CPU is entering a low power idle state where it doesn't lose any
context, then there is no need to call cpu_pm_enter()/cpu_pm_exit().
Add a new macro(CPU_PM_CPU_IDLE_ENTER_RETENTION) to be used by cpuidle
drivers when they are entering retention state. By not calling
cpu_pm_enter and cpu_pm_exit we reduce the latency involved in
entering and exiting the retention idle states.

CPU_PM_CPU_IDLE_ENTER_RETENTION assumes that no state is lost and
hence CPU PM notifiers will not be called. We may need a broader
change if we need to support partial retention states effeciently.

On ARM64 based Qualcomm Server Platform we measured below overhead for
for calling cpu_pm_enter and cpu_pm_exit for retention states.

workload: stress --hdd #CPUs --hdd-bytes 32M  -t 30
        Average overhead of cpu_pm_enter - 1.2us
        Average overhead of cpu_pm_exit  - 3.1us

Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Prashanth Prakash <pprakash@codeaurora.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoMerge branch 'for-next/52-bit-pa' into for-next/core
Catalin Marinas [Fri, 22 Dec 2017 17:40:58 +0000 (17:40 +0000)]
Merge branch 'for-next/52-bit-pa' into for-next/core

* for-next/52-bit-pa:
  arm64: enable 52-bit physical address support
  arm64: allow ID map to be extended to 52 bits
  arm64: handle 52-bit physical addresses in page table entries
  arm64: don't open code page table entry creation
  arm64: head.S: handle 52-bit PAs in PTEs in early page table setup
  arm64: handle 52-bit addresses in TTBR
  arm64: limit PA size to supported range
  arm64: add kconfig symbol to configure physical address size

7 years agoarm64: enable 52-bit physical address support
Kristina Martsenko [Wed, 13 Dec 2017 17:07:25 +0000 (17:07 +0000)]
arm64: enable 52-bit physical address support

Now that 52-bit physical address support is in place, add the kconfig
symbol to enable it. As described in ARMv8.2, the larger addresses are
only supported with the 64k granule. Also ensure that PAN is configured
(or TTBR0 PAN is not), as explained in an earlier patch in this series.

Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoarm64: allow ID map to be extended to 52 bits
Kristina Martsenko [Wed, 13 Dec 2017 17:07:24 +0000 (17:07 +0000)]
arm64: allow ID map to be extended to 52 bits

Currently, when using VA_BITS < 48, if the ID map text happens to be
placed in physical memory above VA_BITS, we increase the VA size (up to
48) and create a new table level, in order to map in the ID map text.
This is okay because the system always supports 48 bits of VA.

This patch extends the code such that if the system supports 52 bits of
VA, and the ID map text is placed that high up, then we increase the VA
size accordingly, up to 52.

One difference from the current implementation is that so far the
condition of VA_BITS < 48 has meant that the top level table is always
"full", with the maximum number of entries, and an extra table level is
always needed. Now, when VA_BITS = 48 (and using 64k pages), the top
level table is not full, and we simply need to increase the number of
entries in it, instead of creating a new table level.

Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[catalin.marinas@arm.com: reduce arguments to __create_hyp_mappings()]
[catalin.marinas@arm.com: reworked/renamed __cpu_uses_extended_idmap_level()]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoarm64: handle 52-bit physical addresses in page table entries
Kristina Martsenko [Wed, 13 Dec 2017 17:07:21 +0000 (17:07 +0000)]
arm64: handle 52-bit physical addresses in page table entries

The top 4 bits of a 52-bit physical address are positioned at bits
12..15 of a page table entry. Introduce macros to convert between a
physical address and its placement in a table entry, and change all
macros/functions that access PTEs to use them.

Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[catalin.marinas@arm.com: some long lines wrapped]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoarm64: don't open code page table entry creation
Kristina Martsenko [Wed, 13 Dec 2017 17:07:20 +0000 (17:07 +0000)]
arm64: don't open code page table entry creation

Instead of open coding the generation of page table entries, use the
macros/functions that exist for this - pfn_p*d and p*d_populate. Most
code in the kernel already uses these macros, this patch tries to fix
up the few places that don't. This is useful for the next patch in this
series, which needs to change the page table entry logic, and it's
better to have that logic in one place.

The KVM extended ID map is special, since we're creating a level above
CONFIG_PGTABLE_LEVELS and the required function isn't available. Leave
it as is and add a comment to explain it. (The normal kernel ID map code
doesn't need this change because its page tables are created in assembly
(__create_page_tables)).

Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoarm64: head.S: handle 52-bit PAs in PTEs in early page table setup
Kristina Martsenko [Wed, 13 Dec 2017 17:07:19 +0000 (17:07 +0000)]
arm64: head.S: handle 52-bit PAs in PTEs in early page table setup

The top 4 bits of a 52-bit physical address are positioned at bits
12..15 in page table entries. Introduce a macro to move the bits there,
and change the early ID map and swapper table setup code to use it.

Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[catalin.marinas@arm.com: additional comments for clarification]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoarm64: handle 52-bit addresses in TTBR
Kristina Martsenko [Wed, 13 Dec 2017 17:07:18 +0000 (17:07 +0000)]
arm64: handle 52-bit addresses in TTBR

The top 4 bits of a 52-bit physical address are positioned at bits 2..5
in the TTBR registers. Introduce a couple of macros to move the bits
there, and change all TTBR writers to use them.

Leave TTBR0 PAN code unchanged, to avoid complicating it. A system with
52-bit PA will have PAN anyway (because it's ARMv8.1 or later), and a
system without 52-bit PA can only use up to 48-bit PAs. A later patch in
this series will add a kconfig dependency to ensure PAN is configured.

In addition, when using 52-bit PA there is a special alignment
requirement on the top-level table. We don't currently have any VA_BITS
configuration that would violate the requirement, but one could be added
in the future, so add a compile-time BUG_ON to check for it.

Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[catalin.marinas@arm.com: added TTBR_BADD_MASK_52 comment]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoarm64: limit PA size to supported range
Kristina Martsenko [Wed, 13 Dec 2017 17:07:17 +0000 (17:07 +0000)]
arm64: limit PA size to supported range

We currently copy the physical address size from
ID_AA64MMFR0_EL1.PARange directly into TCR.(I)PS. This will not work for
4k and 16k granule kernels on systems that support 52-bit physical
addresses, since 52-bit addresses are only permitted with the 64k
granule.

To fix this, fall back to 48 bits when configuring the PA size when the
kernel does not support 52-bit PAs. When it does, fall back to 52, to
avoid similar problems in the future if the PA size is ever increased
above 52.

Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[catalin.marinas@arm.com: tcr_set_pa_size macro renamed to tcr_compute_pa_size]
[catalin.marinas@arm.com: comments added to tcr_compute_pa_size]
[catalin.marinas@arm.com: definitions added for TCR_*PS_SHIFT]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoarm64: add kconfig symbol to configure physical address size
Kristina Martsenko [Wed, 13 Dec 2017 17:07:16 +0000 (17:07 +0000)]
arm64: add kconfig symbol to configure physical address size

ARMv8.2 introduces support for 52-bit physical addresses. To prepare for
supporting this, add a new kconfig symbol to configure the physical
address space size. The symbols will be used in subsequent patches.
Currently the only choice is 48, a later patch will add the option of 52
once the required code is in place.

Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[catalin.marinas@arm.com: folded minor patches into this one]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
7 years agoMerge branch 'kpti' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Catalin Marinas [Mon, 11 Dec 2017 16:10:30 +0000 (16:10 +0000)]
Merge branch 'kpti' of git://git./linux/kernel/git/arm64/linux

Support for unmapping the kernel when running in userspace (aka
"KAISER").

* 'kpti' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: kaslr: Put kernel vectors address in separate data page
  arm64: mm: Introduce TTBR_ASID_MASK for getting at the ASID in the TTBR
  perf: arm_spe: Fail device probe when arm64_kernel_unmapped_at_el0()
  arm64: Kconfig: Add CONFIG_UNMAP_KERNEL_AT_EL0
  arm64: entry: Add fake CPU feature for unmapping the kernel at EL0
  arm64: tls: Avoid unconditional zeroing of tpidrro_el0 for native tasks
  arm64: erratum: Work around Falkor erratum #E1003 in trampoline code
  arm64: entry: Hook up entry trampoline to exception vectors
  arm64: entry: Explicitly pass exception level to kernel_ventry macro
  arm64: mm: Map entry trampoline into trampoline and kernel page tables
  arm64: entry: Add exception trampoline page for exceptions from EL0
  arm64: mm: Invalidate both kernel and user ASIDs when performing TLBI
  arm64: mm: Add arm64_kernel_unmapped_at_el0 helper
  arm64: mm: Allocate ASIDs in pairs
  arm64: mm: Fix and re-enable ARM64_SW_TTBR0_PAN
  arm64: mm: Rename post_ttbr0_update_workaround
  arm64: mm: Remove pre_ttbr0_update_workaround for Falkor erratum #E1003
  arm64: mm: Move ASID from TTBR0 to TTBR1
  arm64: mm: Temporarily disable ARM64_SW_TTBR0_PAN
  arm64: mm: Use non-global mappings for kernel space

7 years agoarm64: kaslr: Put kernel vectors address in separate data page
Will Deacon [Wed, 6 Dec 2017 11:24:02 +0000 (11:24 +0000)]
arm64: kaslr: Put kernel vectors address in separate data page

The literal pool entry for identifying the vectors base is the only piece
of information in the trampoline page that identifies the true location
of the kernel.

This patch moves it into a page-aligned region of the .rodata section
and maps this adjacent to the trampoline text via an additional fixmap
entry, which protects against any accidental leakage of the trampoline
contents.

Suggested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Introduce TTBR_ASID_MASK for getting at the ASID in the TTBR
Will Deacon [Fri, 1 Dec 2017 17:33:48 +0000 (17:33 +0000)]
arm64: mm: Introduce TTBR_ASID_MASK for getting at the ASID in the TTBR

There are now a handful of open-coded masks to extract the ASID from a
TTBR value, so introduce a TTBR_ASID_MASK and use that instead.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoperf: arm_spe: Fail device probe when arm64_kernel_unmapped_at_el0()
Will Deacon [Mon, 27 Nov 2017 15:49:53 +0000 (15:49 +0000)]
perf: arm_spe: Fail device probe when arm64_kernel_unmapped_at_el0()

When running with the kernel unmapped whilst at EL0, the virtually-addressed
SPE buffer is also unmapped, which can lead to buffer faults if userspace
profiling is enabled and potentially also when writing back kernel samples
unless an expensive drain operation is performed on exception return.

For now, fail the SPE driver probe when arm64_kernel_unmapped_at_el0().

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: Kconfig: Add CONFIG_UNMAP_KERNEL_AT_EL0
Will Deacon [Tue, 14 Nov 2017 14:41:01 +0000 (14:41 +0000)]
arm64: Kconfig: Add CONFIG_UNMAP_KERNEL_AT_EL0

Add a Kconfig entry to control use of the entry trampoline, which allows
us to unmap the kernel whilst running in userspace and improve the
robustness of KASLR.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: entry: Add fake CPU feature for unmapping the kernel at EL0
Will Deacon [Tue, 14 Nov 2017 14:38:19 +0000 (14:38 +0000)]
arm64: entry: Add fake CPU feature for unmapping the kernel at EL0

Allow explicit disabling of the entry trampoline on the kernel command
line (kpti=off) by adding a fake CPU feature (ARM64_UNMAP_KERNEL_AT_EL0)
that can be used to toggle the alternative sequences in our entry code and
avoid use of the trampoline altogether if desired. This also allows us to
make use of a static key in arm64_kernel_unmapped_at_el0().

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: tls: Avoid unconditional zeroing of tpidrro_el0 for native tasks
Will Deacon [Tue, 14 Nov 2017 14:33:28 +0000 (14:33 +0000)]
arm64: tls: Avoid unconditional zeroing of tpidrro_el0 for native tasks

When unmapping the kernel at EL0, we use tpidrro_el0 as a scratch register
during exception entry from native tasks and subsequently zero it in
the kernel_ventry macro. We can therefore avoid zeroing tpidrro_el0
in the context-switch path for native tasks using the entry trampoline.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: erratum: Work around Falkor erratum #E1003 in trampoline code
Will Deacon [Tue, 14 Nov 2017 14:29:19 +0000 (14:29 +0000)]
arm64: erratum: Work around Falkor erratum #E1003 in trampoline code

We rely on an atomic swizzling of TTBR1 when transitioning from the entry
trampoline to the kernel proper on an exception. We can't rely on this
atomicity in the face of Falkor erratum #E1003, so on affected cores we
can issue a TLB invalidation to invalidate the walk cache prior to
jumping into the kernel. There is still the possibility of a TLB conflict
here due to conflicting walk cache entries prior to the invalidation, but
this doesn't appear to be the case on these CPUs in practice.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: entry: Hook up entry trampoline to exception vectors
Will Deacon [Tue, 14 Nov 2017 14:24:29 +0000 (14:24 +0000)]
arm64: entry: Hook up entry trampoline to exception vectors

Hook up the entry trampoline to our exception vectors so that all
exceptions from and returns to EL0 go via the trampoline, which swizzles
the vector base register accordingly. Transitioning to and from the
kernel clobbers x30, so we use tpidrro_el0 and far_el1 as scratch
registers for native tasks.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: entry: Explicitly pass exception level to kernel_ventry macro
Will Deacon [Tue, 14 Nov 2017 14:20:21 +0000 (14:20 +0000)]
arm64: entry: Explicitly pass exception level to kernel_ventry macro

We will need to treat exceptions from EL0 differently in kernel_ventry,
so rework the macro to take the exception level as an argument and
construct the branch target using that.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Map entry trampoline into trampoline and kernel page tables
Will Deacon [Tue, 14 Nov 2017 14:14:17 +0000 (14:14 +0000)]
arm64: mm: Map entry trampoline into trampoline and kernel page tables

The exception entry trampoline needs to be mapped at the same virtual
address in both the trampoline page table (which maps nothing else)
and also the kernel page table, so that we can swizzle TTBR1_EL1 on
exceptions from and return to EL0.

This patch maps the trampoline at a fixed virtual address in the fixmap
area of the kernel virtual address space, which allows the kernel proper
to be randomized with respect to the trampoline when KASLR is enabled.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: entry: Add exception trampoline page for exceptions from EL0
Will Deacon [Tue, 14 Nov 2017 14:07:40 +0000 (14:07 +0000)]
arm64: entry: Add exception trampoline page for exceptions from EL0

To allow unmapping of the kernel whilst running at EL0, we need to
point the exception vectors at an entry trampoline that can map/unmap
the kernel on entry/exit respectively.

This patch adds the trampoline page, although it is not yet plugged
into the vector table and is therefore unused.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Invalidate both kernel and user ASIDs when performing TLBI
Will Deacon [Thu, 10 Aug 2017 13:13:33 +0000 (14:13 +0100)]
arm64: mm: Invalidate both kernel and user ASIDs when performing TLBI

Since an mm has both a kernel and a user ASID, we need to ensure that
broadcast TLB maintenance targets both address spaces so that things
like CoW continue to work with the uaccess primitives in the kernel.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Add arm64_kernel_unmapped_at_el0 helper
Will Deacon [Tue, 14 Nov 2017 13:58:08 +0000 (13:58 +0000)]
arm64: mm: Add arm64_kernel_unmapped_at_el0 helper

In order for code such as TLB invalidation to operate efficiently when
the decision to map the kernel at EL0 is determined at runtime, this
patch introduces a helper function, arm64_kernel_unmapped_at_el0, to
determine whether or not the kernel is mapped whilst running in userspace.

Currently, this just reports the value of CONFIG_UNMAP_KERNEL_AT_EL0,
but will later be hooked up to a fake CPU capability using a static key.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Allocate ASIDs in pairs
Will Deacon [Thu, 10 Aug 2017 13:10:28 +0000 (14:10 +0100)]
arm64: mm: Allocate ASIDs in pairs

In preparation for separate kernel/user ASIDs, allocate them in pairs
for each mm_struct. The bottom bit distinguishes the two: if it is set,
then the ASID will map only userspace.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Fix and re-enable ARM64_SW_TTBR0_PAN
Will Deacon [Thu, 10 Aug 2017 12:58:16 +0000 (13:58 +0100)]
arm64: mm: Fix and re-enable ARM64_SW_TTBR0_PAN

With the ASID now installed in TTBR1, we can re-enable ARM64_SW_TTBR0_PAN
by ensuring that we switch to a reserved ASID of zero when disabling
user access and restore the active user ASID on the uaccess enable path.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Rename post_ttbr0_update_workaround
Will Deacon [Thu, 10 Aug 2017 12:34:30 +0000 (13:34 +0100)]
arm64: mm: Rename post_ttbr0_update_workaround

The post_ttbr0_update_workaround hook applies to any change to TTBRx_EL1.
Since we're using TTBR1 for the ASID, rename the hook to make it clearer
as to what it's doing.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Remove pre_ttbr0_update_workaround for Falkor erratum #E1003
Will Deacon [Thu, 10 Aug 2017 12:29:06 +0000 (13:29 +0100)]
arm64: mm: Remove pre_ttbr0_update_workaround for Falkor erratum #E1003

The pre_ttbr0_update_workaround hook is called prior to context-switching
TTBR0 because Falkor erratum E1003 can cause TLB allocation with the wrong
ASID if both the ASID and the base address of the TTBR are updated at
the same time.

With the ASID sitting safely in TTBR1, we no longer update things
atomically, so we can remove the pre_ttbr0_update_workaround macro as
it's no longer required. The erratum infrastructure and documentation
is left around for #E1003, as it will be required by the entry
trampoline code in a future patch.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Move ASID from TTBR0 to TTBR1
Will Deacon [Thu, 10 Aug 2017 12:19:09 +0000 (13:19 +0100)]
arm64: mm: Move ASID from TTBR0 to TTBR1

In preparation for mapping kernelspace and userspace with different
ASIDs, move the ASID to TTBR1 and update switch_mm to context-switch
TTBR0 via an invalid mapping (the zero page).

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Temporarily disable ARM64_SW_TTBR0_PAN
Will Deacon [Thu, 10 Aug 2017 12:04:48 +0000 (13:04 +0100)]
arm64: mm: Temporarily disable ARM64_SW_TTBR0_PAN

We're about to rework the way ASIDs are allocated, switch_mm is
implemented and low-level kernel entry/exit is handled, so keep the
ARM64_SW_TTBR0_PAN code out of the way whilst we do the heavy lifting.

It will be re-enabled in a subsequent patch.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoarm64: mm: Use non-global mappings for kernel space
Will Deacon [Thu, 10 Aug 2017 11:56:18 +0000 (12:56 +0100)]
arm64: mm: Use non-global mappings for kernel space

In preparation for unmapping the kernel whilst running in userspace,
make the kernel mappings non-global so we can avoid expensive TLB
invalidation on kernel exit to userspace.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Tested-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
7 years agoLinux 4.15-rc3
Linus Torvalds [Mon, 11 Dec 2017 01:56:26 +0000 (17:56 -0800)]
Linux 4.15-rc3

7 years agohpfs: don't bother with the i_version counter or f_version
Jeff Layton [Thu, 23 Nov 2017 19:34:40 +0000 (20:34 +0100)]
hpfs: don't bother with the i_version counter or f_version

HPFS does not set SB_I_VERSION and does not use the i_version counter
internally.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Mikulas Patocka <mikulas@twibright.com>
Reviewed-by: Mikulas Patocka <mikulas@twibright.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
7 years agofutex: futex_wake_op, fix sign_extend32 sign bits
Jiri Slaby [Thu, 30 Nov 2017 14:35:44 +0000 (15:35 +0100)]
futex: futex_wake_op, fix sign_extend32 sign bits

sign_extend32 counts the sign bit parameter from 0, not from 1.  So we
have to use "11" for 12th bit, not "12".

This mistake means we have not allowed negative op and cmp args since
commit 30d6e0a4190d ("futex: Remove duplicated code and fix undefined
behaviour") till now.

Fixes: 30d6e0a4190d ("futex: Remove duplicated code and fix undefined behaviour")
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Darren Hart <dvhart@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
7 years agoMerge tag 'for-4.15-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave...
Linus Torvalds [Sun, 10 Dec 2017 16:30:04 +0000 (08:30 -0800)]
Merge tag 'for-4.15-rc3-tag' of git://git./linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "This contains a few fixes (error handling, quota leak, FUA vs
  nobarrier mount option).

  There's one one worth mentioning separately - an off-by-one fix that
  leads to overwriting first byte of an adjacent page with 0, out of
  bounds of the memory allocated by an ioctl. This is under a privileged
  part of the ioctl, can be triggerd in some subvolume layouts"

* tag 'for-4.15-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: Fix possible off-by-one in btrfs_search_path_in_tree
  Btrfs: disable FUA if mounted with nobarrier
  btrfs: fix missing error return in btrfs_drop_snapshot
  btrfs: handle errors while updating refcounts in update_ref_for_cow
  btrfs: Fix quota reservation leak on preallocated files

7 years agoMerge tag 'armsoc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Linus Torvalds [Sun, 10 Dec 2017 16:26:59 +0000 (08:26 -0800)]
Merge tag 'armsoc-fixes' of git://git./linux/kernel/git/arm/arm-soc

Pull ARM SoC fixes from Olof Johansson:

 - A revert of all SCPI changes from the 4.15 merge window. They had
   regressions on the Amlogic platforms, and the submaintainer isn't
   around to fix these bugs due to vacation, etc. So we agreed to revert
   and revisit in next release cycle.

 - A series fixing a number of bugs for ARM CCN interconnect, around
   module unload, smp_processor_id() in preemptable context, and fixing
   some memory allocation failure checks.

 - A handful of devicetree fixes for different platforms, fixing
   warnings and errors that were previously ignored by the compiler.

 - The usual set of mostly minor fixes for different platforms.

* tag 'armsoc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (42 commits)
  ARM64: dts: meson-gx: fix UART pclk clock name
  ARM: omap2: hide omap3_save_secure_ram on non-OMAP3 builds
  arm: dts: nspire: Add missing #phy-cells to usb-nop-xceiv
  ARM: dts: Fix dm814x missing phy-cells property
  ARM: dts: Fix elm interrupt compiler warning
  bus: arm-ccn: fix module unloading Error: Removing state 147 which has instances left.
  bus: arm-cci: Fix use of smp_processor_id() in preemptible context
  bus: arm-ccn: Fix use of smp_processor_id() in preemptible context
  bus: arm-ccn: Simplify code
  bus: arm-ccn: Check memory allocation failure
  bus: arm-ccn: constify attribute_group structures.
  firmware: arm_scpi: Revert updates made during v4.15 merge window
  arm: dts: marvell: Add missing #phy-cells to usb-nop-xceiv
  arm64: dts: sort vendor subdirectories in Makefile alphabetically
  meson-gx-socinfo: Fix package id parsing
  ARM: meson: fix spelling mistake: "Couln't" -> "Couldn't"
  ARM: dts: meson: fix the memory region of the GPIO interrupt controller
  ARM: dts: meson: correct the sort order for the the gpio_intc node
  MAINTAINERS: exclude other Socionext SoC DT files from ARM/UNIPHIER entry
  arm64: dts: uniphier: remove unnecessary interrupt-parent
  ...

7 years agoMerge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Linus Torvalds [Sun, 10 Dec 2017 16:24:16 +0000 (08:24 -0800)]
Merge tag 'for-linus' of git://git./virt/kvm/kvm

Pull KVM fixes from Radim Krčmář:
 "ARM:
   - A number of issues in the vgic discovered using SMATCH
   - A bit one-off calculation in out stage base address mask (32-bit
     and 64-bit)
   - Fixes to single-step debugging instructions that trap for other
     reasons such as MMMIO aborts
   - Printing unavailable hyp mode as error
   - Potential spinlock deadlock in the vgic
   - Avoid calling vgic vcpu free more than once
   - Broken bit calculation for big endian systems

 s390:
   - SPDX tags
   - Fence storage key accesses from problem state
   - Make sure that irq_state.flags is not used in the future

  x86:
   - Intercept port 0x80 accesses to prevent host instability (CVE)
   - Use userspace FPU context for guest FPU (mainly an optimization
     that fixes a double use of kernel FPU)
   - Do not leak one page per module load
   - Flush APIC page address cache from MMU invalidation notifiers"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  KVM: x86: fix APIC page invalidation
  KVM: s390: Fix skey emulation permission check
  KVM: s390: mark irq_state.flags as non-usable
  KVM: s390: Remove redundant license text
  KVM: s390: add SPDX identifiers to the remaining files
  KVM: VMX: fix page leak in hardware_setup()
  KVM: VMX: remove I/O port 0x80 bypass on Intel hosts
  x86,kvm: remove KVM emulator get_fpu / put_fpu
  x86,kvm: move qemu/guest FPU switching out to vcpu_run
  KVM: arm/arm64: Fix broken GICH_ELRSR big endian conversion
  KVM: arm/arm64: kvm_arch_destroy_vm cleanups
  KVM: arm/arm64: Fix spinlock acquisition in vgic_set_owner
  kvm: arm: don't treat unavailable HYP mode as an error
  KVM: arm/arm64: Avoid attempting to load timer vgic state without a vgic
  kvm: arm64: handle single-step of hyp emulated mmio instructions
  kvm: arm64: handle single-step during SError exceptions
  kvm: arm64: handle single-step of userspace mmio instructions
  kvm: arm64: handle single-stepping trapped instructions
  KVM: arm/arm64: debug: Introduce helper for single-step
  arm: KVM: Fix VTTBR_BADDR_MASK BUG_ON off-by-one
  ...