The current code is incredibly resilient to updates to the spec and
has worked quite well so far. However, recent implementations expose a
weakness in that this is rather slow. A large part of it is written in
assembly, making it opaque to the compiler for optimisations. The
future proofness requires reading registers that are effectively
`volatile`, making it even harder for the compiler, as well as adding
lots of implicit barriers, making it hard for the microarchitecutre to
optimise as well.
We can make a few assumptions, checked by a few well placed asserts, and
remove a lot of this burden. For a start, at the moment there are 4
group 0 counters with static assignments. Contexting them is a trivial
affair that doesn't need a loop. Similarly, there can only be up to 16
group 1 counters. Contexting them is a bit harder, but we can do with a
single branch with a falling through switch. If/when both of these
change, we have a pair of asserts and the feature detection mechanism to
guard us against pretending that we support something we don't.
We can drop contexting of the offset registers. They are fully
accessible by EL2 and as such are its responsibility to preserve on
powerdown.
Another small thing we can do, is pass the core_pos into the hook.
The caller already knows which core we're running on, we don't need to
call this non-trivial function again.
Finally, knowing this, we don't really need the auxiliary AMUs to be
described by the device tree. Linux doesn't care at the moment, and any
information we need for EL3 can be neatly placed in a simple array.
All of this, combined with lifting the actual saving out of assembly,
reduces the instructions to save the context from 180 to 40, including a
lot fewer branches. The code is also much shorter and easier to read.
Also propagate to aarch32 so that the two don't diverge too much.
Change-Id: Ib62e6e9ba5be7fb9fb8965c8eee148d5598a5361
Signed-off-by: Boyan Karatotev <boyan.karatotev@arm.com>
This patch disables trapping to EL3 when the FEAT_D128
specific registers are accessed by setting the SCR_EL3.D128En bit.
If FEAT_D128 is implemented, then FEAT_SYSREG128 is implemented.
With FEAT_SYSREG128 certain system registers are treated as 128-bit,
so we should be context saving and restoring 128-bits instead of 64-bit
when FEAT_D128 is enabled.
FEAT_SYSREG128 adds support for MRRS and MSRR instruction which
helps us to read write to 128-bit system register.
Refer to Arm Architecture Manual for further details.
Change the FVP platform to default to handling this as a dynamic option
so the right decision can be made by the code at runtime.
Change-Id: I1a53db5eac29e56c8fbdcd4961ede3abfcb2411a
Signed-off-by: Jayanth Dodderi Chidanand <jayanthdodderi.chidanand@arm.com>
Signed-off-by: Govindraj Raja <govindraj.raja@arm.com>
Adds driver support to preserve DSU PMU register values over a DSU
power cycle. This driver needs to be enabled by the platforms that
support DSU and also need it's PMU registers to be preserved
Change-Id: I7fc68a3d7d99ee369379aa5cd114fffc763fc0d2
Signed-off-by: Arvind Ram Prakash <arvind.ramprakash@arm.com>
Currently, the macros used to denote feature implementation
in hardware follow a random pattern with a few macros having
suffix as SUPPORTED and a few using the suffix IMPLEMENTED.
This patch aligns the macro names uniformly using the suffix
IMPLEMENTED across all the features and removes unused macros
pertaining to the Enable feat mechanism.
FEAT_SUPPORTED --> FEAT_IMPLEMENTED
FEAT_NOT_SUPPORTED --> FEAT_NOT_IMPLEMENTED
Change-Id: I61bb7d154b23f677b80756a4b6a81f74b10cd24f
Signed-off-by: Sona Mathew <sonarebecca.mathew@arm.com>
Following utility functions/bit definitions done
- Write a helper function to return the presence of following features
- FEAT_UAO
- FEAT_EBEP
- FEAT_SEBEP
- FEAT_SSBS
- FEAT_NMI
- FEAT_PAN
- Add definition of some missing bits of SPSR.
- Add GCSCR_EL1 register encoding and accessor function.
Signed-off-by: Manish Pandey <manish.pandey2@arm.com>
Change-Id: Ifcead0dd8e3b32096e4ab810dde5d582a889785a
Bit1 in the CLUSTERPWRDN register is used to indicate on CLUSTERPACTIVE
that memory retention is required or not. It can be used for
L3 cache memory retention support.
Signed-off-by: Jacky Bai <ping.bai@nxp.com>
Change-Id: I1c53c90ae3dfbed3be7e5b2b79f2c3565db81012
With the introduction of FEAT_RME MDCR_EL3 bits NSPB and NSPBE depend on
each other. The enable code relies on the register being initialised to
zero and omits to reset NSPBE. However, this is not obvious. Reset the
bit explicitly to document this.
Similarly, reset the STE bit , since it's part of the feature enablement.
Signed-off-by: Boyan Karatotev <boyan.karatotev@arm.com>
Change-Id: I3714507bae10042cdccd2b7bc713b31d4cdeb02f
The FEAT_MTPMU feature disable runs very early after reset. This means,
it needs to be written in assembly, since the C runtime has not been
initialised yet.
However, there is no need for it to be initialised so soon. The PMU
state is only relevant after TF-A has relinquished control. The code
to do this is also very verbose and difficult to read. Delaying the
initialisation allows for it to happen with the rest of the PMU. Align
with FEAT_STATE in the process.
BREAKING CHANGE: This patch explicitly breaks the EL2 entry path. It is
currently unsupported.
Signed-off-by: Boyan Karatotev <boyan.karatotev@arm.com>
Change-Id: I2aa659d026fbdb75152469f6d19812ece3488c6f
The enablement code for the PMU is scattered and difficult to track
down. Factor out the feature into its own lib/extensions folder and
consolidate the implementation. Treat it is as an architecturally
mandatory feature as it is currently.
Additionally, do some cleanup on AArch64. Setting overflow bits in
PMCR_EL0 is irrelevant for firmware so don't do it. Then delay the PMU
initialisation until the context management stage which simplifies the
early environment assembly. One side effect is that the PMU might count
before this happens so reset all counters to 0 to prevent any leakage.
Finally, add an enable to manage_extensions_realm() as realm world uses
the pmu. This introduces the HPMN fixup to realm world.
Signed-off-by: Boyan Karatotev <boyan.karatotev@arm.com>
Change-Id: Ie13a8625820ecc5fbfa467dc6ca18025bf6a9cd3
FEAT_PAN is implemented in AArch32 as well, provide the helper functions
to query the feature availability at runtime.
Change-Id: I375e3eb7b05955ea28a092ba99bb93302af48a0e
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
This patch adds the errata management firmware interface for lower ELs
to discover details about CPU erratum. Based on the CPU erratum
identifier the interface enables the OS to find the mitigation of an
erratum in EL3.
The ABI can only be present in a system that is compliant with SMCCCv1.1
or higher. This implements v1.0 of the errata ABI spec.
For details on all possible return values, refer the design
documentation below:
ABI design documentation:
https://developer.arm.com/documentation/den0100/1-0?lang=en
Signed-off-by: Sona Mathew <SonaRebecca.Mathew@arm.com>
Change-Id: I70f0e2569cf92e6e02ad82e3e77874546232b89a
For an easier debug on Aarch32, in case of abort, it is useful to access
DFSR, IFSR, DFAR and IFAR CP15 registers.
Change-Id: Ie6b5a2882cd701f76e9d455ec43bd4b0fbe3cc78
Signed-off-by: Yann Gautier <yann.gautier@st.com>
FEAT_CCIDX modifies the register fields in CCSIDR/CCSIDR2 (aarch32)
and CCSIDR_EL1 (aarch64). This patch adds a check to the do_dcsw_op
function to use the right register format rather than assuming
that FEAT_CCIDX is not implemented.
Signed-off-by: John Powell <john.powell@arm.com>
Change-Id: I12cd00cd7b5889525d4d2750281a751dd74ef5dc
This change removes the `AMU_GROUP0_COUNTERS_MASK` and
`AMU_GROUP0_MAX_COUNTERS` preprocessor definitions, instead retrieving
the number of group 0 counters dynamically through `AMCGCR_EL0.CG0NC`.
Change-Id: I70e39c30fbd5df89b214276fac79cc8758a89f72
Signed-off-by: Chris Kay <chris.kay@arm.com>
This change introduces a small set of register getters and setters to
avoid having to repeatedly mask and shift in complex code.
Change-Id: Ia372f60c5efb924cd6eeceb75112e635ad13d942
Signed-off-by: Chris Kay <chris.kay@arm.com>
Trap bits of trace filter control registers access are in
architecturally UNKNOWN state at boot hence
1. Initialized trap bits to one to prohibit trace filter control
registers accesses in lower ELs (EL2, EL1) in all security states
when FEAT_TRF is implemented.
2. These bits are RES0 when FEAT_TRF is not implemented and hence set
it to zero to aligns with the Arm ARM reference recommendation,
that mentions software must writes RES0 bits with all 0s.
Change-Id: I1b7abf2170ece84ee585c91cda32d22b25c0fc34
Signed-off-by: Manish V Badarkhe <Manish.Badarkhe@arm.com>
Trap bits of trace system registers access are in architecturally
UNKNOWN state at boot hence
1. Initialized trap bits to one to prohibit trace system registers
accesses in lower ELs (EL2, EL1) in all security states when system
trace registers are implemented.
2. These bits are RES0 in the absence of system trace register support
and hence set it to zero to aligns with the Arm ARM reference
recommendation,that mentions software must writes RES0 bits with
all 0s.
Change-Id: I4b6c15cda882325273492895d72568b29de89ca3
Signed-off-by: Manish V Badarkhe <Manish.Badarkhe@arm.com>
ARMv8.6 adds virtual offset registers to support virtualization of the
event counters in EL1 and EL0. This patch enables support for this
feature in EL3 firmware.
Signed-off-by: John Powell <john.powell@arm.com>
Change-Id: I7ee1f3d9f554930bf5ef6f3d492e932e6d95b217
If FEAT_PMUv3 is implemented and PMEVTYPER<n>(_EL0).MT bit is implemented
as well, it is possible to control whether PMU counters take into account
events happening on other threads.
If FEAT_MTPMU is implemented, EL3 (or EL2) can override the MT bit
leaving it to effective state of 0 regardless of any write to it.
This patch introduces the DISABLE_MTPMU flag, which allows to diable
multithread event count from EL3 (or EL2). The flag is disabled
by default so the behavior is consistent with those architectures
that do not implement FEAT_MTPMU.
Signed-off-by: Javier Almansa Sobrino <javier.almansasobrino@arm.com>
Change-Id: Iee3a8470ae8ba13316af1bd40c8d4aa86e0cb85e
Usually, C has no problem up-converting types to larger bit sizes. MISRA
rule 10.7 requires that you not do this, or be very explicit about this.
This resolves the following required rule:
bl1/aarch64/bl1_context_mgmt.c:81:[MISRA C-2012 Rule 10.7 (required)]<None>
The width of the composite expression "0U | ((mode & 3U) << 2U) | 1U |
0x3c0U" (32 bits) is less that the right hand operand
"18446744073709547519ULL" (64 bits).
This also resolves MISRA defects such as:
bl2/aarch64/bl2arch_setup.c:18:[MISRA C-2012 Rule 12.2 (required)]
In the expression "3U << 20", shifting more than 7 bits, the number
of bits in the essential type of the left expression, "3U", is
not allowed.
Further, MISRA requires that all shifts don't overflow. The definition of
PAGE_SIZE was (1U << 12), and 1U is 8 bits. This caused about 50 issues.
This fixes the violation by changing the definition to 1UL << 12. Since
this uses 32bits, it should not create any issues for aarch32.
This patch also contains a fix for a build failure in the sun50i_a64
platform. Specifically, these misra fixes removed a single and
instruction,
92407e73 and x19, x19, #0xffffffff
from the cm_setup_context function caused a relocation in
psci_cpus_on_start to require a linker-generated stub. This increased the
size of the .text section and caused an alignment later on to go over a
page boundary and round up to the end of RAM before placing the .data
section. This sectionn is of non-zero size and therefore causes a link
error.
The fix included in this reorders the functions during link time
without changing their ording with respect to alignment.
Change-Id: I76b4b662c3d262296728a8b9aab7a33b02087f16
Signed-off-by: Jimmy Brisson <jimmy.brisson@arm.com>
This patch fixes the bug when AMUv1 group1 counters was
always assumed being implemented without checking for its
presence which was causing exception otherwise.
The AMU extension code was also modified as listed below:
- Added detection of AMUv1 for ARMv8.6
- 'PLAT_AMU_GROUP1_NR_COUNTERS' build option is removed and
number of group1 counters 'AMU_GROUP1_NR_COUNTERS' is now
calculated based on 'AMU_GROUP1_COUNTERS_MASK' value
- Added bit fields definitions and access functions for
AMCFGR_EL0/AMCFGR and AMCGCR_EL0/AMCGCR registers
- Unification of amu.c Aarch64 and Aarch32 source files
- Bug fixes and TF-A coding style compliant changes.
Change-Id: I14e407be62c3026ebc674ec7045e240ccb71e1fb
Signed-off-by: Alexei Fedorov <Alexei.Fedorov@arm.com>
By writing 0 to CLUSTERPWRDN DSU register bit 0, we send an
advisory to the power controller that cluster power is not required
when all cores are powered down.
The AArch32 CLUSTERPWRDN register is architecturally mapped to the
AArch64 CLUSTERPWRDN_EL1 register
Change-Id: Ie6e67c1c7d811fa25c51e2e405ca7f59bd20c81b
Signed-off-by: Madhukar Pappireddy <madhukar.pappireddy@arm.com>
Attempts to address MISRA compliance issues in BL1, BL2, and BL31 code.
Mainly issues like not using boolean expressions in conditionals,
conflicting variable names, ignoring return values without (void), adding
explicit casts, etc.
Change-Id: If1fa18ab621b9c374db73fa6eaa6f6e5e55c146a
Signed-off-by: John Powell <john.powell@arm.com>
This patch changes implementation for disabling Secure Cycle
Counter. For ARMv8.5 the counter gets disabled by setting
SDCR.SCCD bit on CPU cold/warm boot. For the earlier
architectures PMCR register is saved/restored on secure
world entry/exit from/to Non-secure state, and cycle counting
gets disabled by setting PMCR.DP bit.
In 'include\aarch32\arch.h' header file new
ARMv8.5-PMU related definitions were added.
Change-Id: Ia8845db2ebe8de940d66dff479225a5b879316f8
Signed-off-by: Alexei Fedorov <Alexei.Fedorov@arm.com>
This patch introduces an additional precautionary step to further
enhance protection against variant 4. During the context initialisation
before we enter the various BL stages, the SPSR.SSBS bit is explicitly
set to zero. As such, speculative loads/stores are by default disabled
for all BL stages when they start executing. Subsequently, each BL
stage, can choose to enable speculative loads/stores or keep them
disabled.
This change doesn't affect the initial execution context of BL33 which
is totally platform dependent and, thus, it is intentionally left up to
each platform to initialise.
For Arm platforms, SPSR.SSBS is set to zero for BL33 too. This means
that, for Arm platforms, all BL stages start with speculative
loads/stores disabled.
Change-Id: Ie47d39c391d3f20fc2852fc59dbd336f8cacdd6c
Signed-off-by: John Tsichritzis <john.tsichritzis@arm.com>
Those defines are used in STM32MP1 clock driver.
It is better to put them altogether with already defined registers.
Change-Id: I6f8ad8c2477b947af6f76283a4ef5c40212d0027
Signed-off-by: Yann Gautier <yann.gautier@st.com>
The workarounds for these errata are so closely related that it is
better to only have one patch to make it easier to understand.
Change-Id: I0287fa69aefa8b72f884833f6ed0e7775ca834e9
Signed-off-by: Ambroise Vincent <ambroise.vincent@arm.com>
In a system with ARMv8.5-PMU implemented:
- If EL3 is using AArch32, setting MDCR_EL3.SCCD to 1 disables counting
in Secure state in PMCCNTR.
- If EL3 is using AArch64, setting SDCR.SCCD to 1 disables counting in
Secure state in PMCCNTR_EL0.
So far this effect has been achieved by setting PMCR_EL0.DP (in AArch64)
or PMCR.DP (in AArch32) to 1 instead, but this isn't considered secure
as any EL can change that value.
Change-Id: I82cbb3e48f2e5a55c44d9c4445683c5881ef1f6f
Signed-off-by: Antonio Nino Diaz <antonio.ninodiaz@arm.com>
The Generic Timer is an optional extension to an ARMv7-A implementation.
The generic delay timer can be used from any architecture supported by
the Trusted Firmware. In ARMv7 it is needed to check that this feature
is present. In ARMv8 it is always present.
Change-Id: Ib7e8ec13ffbb2f64445d4ee48ed00f26e34b79b7
Signed-off-by: Antonio Nino Diaz <antonio.ninodiaz@arm.com>
ARMv8.2-TTCNP is mandatory from ARMv8.2 onwards, but it can be implemented
in CPUs that don't implement all mandatory 8.2 features (and so have to
claim to be a lower version).
This patch removes usage of the ARM_ARCH_AT_LEAST() macro and uses system
ID registers to detect whether it is needed to set the bit or not.
Change-Id: I7bcbf0c7c937590dfc2ca668cfd9267c50f7d52c
Signed-off-by: Antonio Nino Diaz <antonio.ninodiaz@arm.com>
Enforce full include path for includes. Deprecate old paths.
The following folders inside include/lib have been left unchanged:
- include/lib/cpus/${ARCH}
- include/lib/el3_runtime/${ARCH}
The reason for this change is that having a global namespace for
includes isn't a good idea. It defeats one of the advantages of having
folders and it introduces problems that are sometimes subtle (because
you may not know the header you are actually including if there are two
of them).
For example, this patch had to be created because two headers were
called the same way: e0ea0928d5 ("Fix gpio includes of mt8173 platform
to avoid collision."). More recently, this patch has had similar
problems: 46f9b2c3a2 ("drivers: add tzc380 support").
This problem was introduced in commit 4ecca33988 ("Move include and
source files to logical locations"). At that time, there weren't too
many headers so it wasn't a real issue. However, time has shown that
this creates problems.
Platforms that want to preserve the way they include headers may add the
removed paths to PLAT_INCLUDES, but this is discouraged.
Change-Id: I39dc53ed98f9e297a5966e723d1936d6ccf2fc8f
Signed-off-by: Antonio Nino Diaz <antonio.ninodiaz@arm.com>
The architecture dependant header files in include/lib/${ARCH} and
include/common/${ARCH} have been moved to /include/arch/${ARCH}.
Change-Id: I96f30fdb80b191a51448ddf11b1d4a0624c03394
Signed-off-by: Antonio Nino Diaz <antonio.ninodiaz@arm.com>
2019-01-04 10:43:16 +00:00
Renamed from include/lib/aarch32/arch.h (Browse further)
