fix(security): add CVE-2024-7881 mitigation to C1-Premium CPU

This patch mitigates Cat B erratum 3651221 [2] / CVE-2024-7881 [1]
for C1-Premium CPU. This CVE applies to r0p0 and
is fixed in r1p0 [2]

fix(security): add CVE-2024-7881 mitigation to C1-Premium CPU

This patch mitigates Cat B erratum 3651221 [2] / CVE-2024-7881 [1]
for C1-Premium CPU. This CVE applies to r0p0 and
is fixed in r1p0 [2].

This CVE can be mitigated by disabling the affected prefetcher
setting CPUACTLR6_EL1[41].

[1] https://developer.arm.com/documentation/110326/latest/
[2] https://developer.arm.com/documentation/111078/latest/

Signed-off-by: Arvind Ram Prakash <arvind.ramprakash@arm.com>
Change-Id: I70b50700bc1618e0f8f4121efc9fe89e2742ed74

show more ...

Merge changes from topic "xl/a725-errata" into integration

* changes:
fix(cpus): workaround for Cortex-A725 erratum 3456106
fix(cpus): workaround for Cortex-A725 erratum 3711914
fix(cpus): wor

Merge changes from topic "xl/a725-errata" into integration

* changes:
fix(cpus): workaround for Cortex-A725 erratum 3456106
fix(cpus): workaround for Cortex-A725 erratum 3711914
fix(cpus): workaround for Cortex-A725 erratum 2936490
fix(cpus): workaround for Cortex-A725 erratum 2874943

show more ...

fix(cpus): workaround for Cortex-A725 erratum 3711914

Cortex-A725 erratum 3711914 is a Cat B erratum that applies
to revisions r0p0 and r0p1 and it is fixed in r0p2.

This erratum can be avoided by

fix(cpus): workaround for Cortex-A725 erratum 3711914

Cortex-A725 erratum 3711914 is a Cat B erratum that applies
to revisions r0p0 and r0p1 and it is fixed in r0p2.

This erratum can be avoided by inserting a DMB LD after each DSB ST instruction.

SDEN documentation:
https://developer.arm.com/documentation/SDEN-2832921/latest/

Change-Id: If3b9d3a0f495b3a172d3e6e5ca7afa8c30aeb4ea
Signed-off-by: Xialin Liu <xialin.liu@arm.com>

show more ...

fix(cpus): workaround for Cortex-A725 erratum 2936490

Cortex-A725 erratum 2936490 is a Cat B erratum that applies
to revisions in r0p0, and is fixed in r0p1.

This erratum can be avoided by setting

fix(cpus): workaround for Cortex-A725 erratum 2936490

Cortex-A725 erratum 2936490 is a Cat B erratum that applies
to revisions in r0p0, and is fixed in r0p1.

This erratum can be avoided by setting CPUACTLR2_EL1[37] to 1.
Setting this bit is expected to have a negligible performance impact.

SDEN documentation:
https://developer.arm.com/documentation/SDEN-2832921/latest/

Change-Id: I9833f8831ba3735a94763791a65be11b95c00bdb
Signed-off-by: Xialin Liu <xialin.liu@arm.com>

show more ...

fix(cpus): workaround for Cortex-A725 erratum 2874943

Cortex-A725 erratum 2874943 is a Cat B erratum that applies
to revision r0p0 when FEAT_SPE is enabled, it is fixed in r0p1.

This erratum can be

fix(cpus): workaround for Cortex-A725 erratum 2874943

Cortex-A725 erratum 2874943 is a Cat B erratum that applies
to revision r0p0 when FEAT_SPE is enabled, it is fixed in r0p1.

This erratum can be avoided by setting bits[58:57] to 0b11 in CPUACTLR_EL1.

SDEN documentation:
https://developer.arm.com/documentation/SDEN-2832921/latest/

Change-Id: I686bbde8756d52afee92097ec05b97138b550025
Signed-off-by: Xialin Liu <xialin.liu@arm.com>

show more ...

fix(cpus): workaround for Cortex-A76AE erratum 1969401

Cortex-A76AE erratum 1969401 is a Cat B erratum that applies
to r0p0 and r1p0, it is fixed in r1p1.

This erratum can be avoided by inserting a

fix(cpus): workaround for Cortex-A76AE erratum 1969401

Cortex-A76AE erratum 1969401 is a Cat B erratum that applies
to r0p0 and r1p0, it is fixed in r1p1.

This erratum can be avoided by inserting a DMB ST before acquire
atomic instructions without release semantics.

SDEN documentation:
https://developer.arm.com/documentation/SDEN-1277541/1700/?lang=en

Change-Id: I893452450d430833e6c5a8e33a1e37b708218576
Signed-off-by: Xialin Liu <xialin.liu@arm.com>

show more ...

fix(cpus): workaround for Cortex-A76AE erratum 1931435

Cortex-A76AE erratum 1931435 is a Cat B erratum that applies
to r0p0 and r1p0, it is fixed in r1p1.

This erratum can be avoided by setting CPU

fix(cpus): workaround for Cortex-A76AE erratum 1931435

Cortex-A76AE erratum 1931435 is a Cat B erratum that applies
to r0p0 and r1p0, it is fixed in r1p1.

This erratum can be avoided by setting CPUACTLR_EL1[13] to 1. This bit
delays instruction fetch after branch misprediction. This workaround
will have a small impact on performance.

SDEN documentation:
https://developer.arm.com/documentation/SDEN-1277541/1700/?lang=en

Change-Id: I1baba8752f5f2e2ab5c873030e1f00cbb8cf1e60
Signed-off-by: Xialin Liu <xialin.liu@arm.com>

show more ...

fix(cpus): workaround for Cortex-A76AE erratum 1931427

Cortex-A76AE erratum 1931427 is a Cat B erratum that applies
to r0p0 and r1p0, it is fixed in r1p1.

This erratum can be avoided by setting CPU

fix(cpus): workaround for Cortex-A76AE erratum 1931427

Cortex-A76AE erratum 1931427 is a Cat B erratum that applies
to r0p0 and r1p0, it is fixed in r1p1.

This erratum can be avoided by setting CPUACTLR2_EL1[2] to 1. The bit
to force Atomic Store operations to write-back memory to be performed
in the L1 data cache.

SDEN documentation:
https://developer.arm.com/documentation/SDEN-1277541/1700/?lang=en

Change-Id: I31566838f894372e5627abda8b0bea1505f11f5d
Signed-off-by: Xialin Liu <xialin.liu@arm.com>

show more ...

Merge changes from topic "tc-lsc-25-cpu-libs" into integration

* changes:
feat(cpus): add support for LSC25 E-core CPU
feat(cpus): add support for LSC25 P-core CPU

Merge "fix(gpt): remove unused `gpt_disable` function" into integration

fix(gpt): remove unused `gpt_disable` function

After GPT protections are enabled, there are no scenarios where they
need to be disabled, similarly to how TZC-400 protections are not
disabled after b

fix(gpt): remove unused `gpt_disable` function

After GPT protections are enabled, there are no scenarios where they
need to be disabled, similarly to how TZC-400 protections are not
disabled after being setup.

Change-Id: I7eae3147130c7a6c3b7b3e9c10e8e7229f32505d
Signed-off-by: Ludovic Mermod <ludovic.mermod@arm.com>

show more ...

fix(psci): get the cpu_ops before exiting coherency

It is possible for the cpu_data structure to be cached somewhere in the
cache hierarchy. When HW_ASSISTED_COHERENCY == 0 we flush the core's
priva

fix(psci): get the cpu_ops before exiting coherency

It is possible for the cpu_data structure to be cached somewhere in the
cache hierarchy. When HW_ASSISTED_COHERENCY == 0 we flush the core's
private caches (usually the L1). However, the destination might be
shared caches (eg DSU L2 cache) so when we subsequently dereference the
cpu_data pointer we could get a stale value.

So dereference it prior to disabling the caches to avoid this scenario
and do all accesses from a coherent view of memory.

Change-Id: If118ca8c0436dd04d6ad0d57073d69305a7f41cb
Signed-off-by: Boyan Karatotev <boyan.karatotev@arm.com>

show more ...

fix(per-cpu): remove redundant casts

The casts replaced in this change were redundant; they were initially
added after some consideration of pointer provenance, but in these
particular cases loss of

fix(per-cpu): remove redundant casts

The casts replaced in this change were redundant; they were initially
added after some consideration of pointer provenance, but in these
particular cases loss of provenance is deliberate.

Change-Id: I9971fd47155b4ec395b2d8d7991c215d0c6a06d3
Signed-off-by: Chris Kay <chris.kay@arm.com>

show more ...

feat(cpus): add support for LSC25 E-core CPU

Add basic CPU library code to support the Large Screen Compute 2025
E-core CPU.

Change-Id: Ibda2e8441d3a3e35941448b483d07e17db2ef234
Signed-off-by: Ryan

feat(cpus): add support for LSC25 E-core CPU

Add basic CPU library code to support the Large Screen Compute 2025
E-core CPU.

Change-Id: Ibda2e8441d3a3e35941448b483d07e17db2ef234
Signed-off-by: Ryan Everett <ryan.everett@arm.com>
Signed-off-by: Aditya Deshpande <aditya.deshpande@arm.com>

show more ...

feat(cpus): add support for LSC25 P-core CPU

Add basic CPU library code to support the Large Screen Compute 2025
P-core CPU.

Change-Id: Icfd2fdbaed577e64cb2db028416a6eca5ba2cfcf
Signed-off-by: Ryan

feat(cpus): add support for LSC25 P-core CPU

Add basic CPU library code to support the Large Screen Compute 2025
P-core CPU.

Change-Id: Icfd2fdbaed577e64cb2db028416a6eca5ba2cfcf
Signed-off-by: Ryan Everett <ryan.everett@arm.com>
Signed-off-by: Aditya Deshpande <aditya.deshpande@arm.com>

show more ...

Merge changes from topic "gr/cov_fixes" into integration

* changes:
fix(libc): fix coverity overflowed constant
fix(libc): fix coverity overflowed constant
fix(psci): fix coverity issue with o

Merge changes from topic "gr/cov_fixes" into integration

* changes:
fix(libc): fix coverity overflowed constant
fix(libc): fix coverity overflowed constant
fix(psci): fix coverity issue with out-of-bounds read
fix(fvp): fix coverity issue unsigned_compare

show more ...

feat(cpufeat): add support for FEAT_IDTE3

This patch adds support for FEAT_IDTE3, which introduces support
for handling the trapping of Group 3 and Group 5 (only GMID_EL1)
registers to EL3 (unless t

feat(cpufeat): add support for FEAT_IDTE3

This patch adds support for FEAT_IDTE3, which introduces support
for handling the trapping of Group 3 and Group 5 (only GMID_EL1)
registers to EL3 (unless trapped to EL2). IDTE3 allows EL3 to
modify the view of ID registers for lower ELs, and this capability
is used to disable fields of ID registers tied to disabled features.

The ID registers are initially read as-is and stored in context.
Then, based on the feature enablement status for each world, if a
particular feature is disabled, its corresponding field in the
cached ID register is set to Res0. When lower ELs attempt to read
an ID register, the cached ID register value is returned. This
allows EL3 to prevent lower ELs from accessing feature-specific
system registers that are disabled in EL3, even though the hardware
implements them.

The emulated ID register values are stored primarily in per-world
context, except for certain debug-related ID registers such as
ID_AA64DFR0_EL1 and ID_AA64DFR1_EL1, which are stored in the
cpu_data and are unique to each PE. This is done to support feature
asymmetry that is commonly seen in debug features.

FEAT_IDTE3 traps all Group 3 ID registers in the range
op0 == 3, op1 == 0, CRn == 0, CRm == {2–7}, op2 == {0–7} and the
Group 5 GMID_EL1 register. However, only a handful of ID registers
contain fields used to detect features enabled in EL3. Hence, we
only cache those ID registers, while the rest are transparently
returned as is to the lower EL.

This patch updates the CREATE_FEATURE_FUNCS macro to generate
update_feat_xyz_idreg_field() functions that disable ID register
fields on a per-feature basis. The enabled_worlds scope is used to
disable ID register fields for security states where the feature is
not enabled.

This EXPERIMENTAL feature is controlled by the ENABLE_FEAT_IDTE3
build flag and is currently disabled by default.

Signed-off-by: Arvind Ram Prakash <arvind.ramprakash@arm.com>
Change-Id: I5f998eeab81bb48c7595addc5595313a9ebb96d5

show more ...

feat(per-cpu): integrate per-cpu framework into BL31/BL32

Integrate per-cpu support into BL31/BL32 by extending the following
areas:

Zero-initialization: Treats per-cpu sections like .bss and clear

feat(per-cpu): integrate per-cpu framework into BL31/BL32

Integrate per-cpu support into BL31/BL32 by extending the following
areas:

Zero-initialization: Treats per-cpu sections like .bss and clears them
during early C runtime initialization. For platforms that enable
NUMA_AWARE_PER_CPU, invokes a platform hook to zero-initialize
node-specific per-cpu regions.

Cache maintenance: Extends the BL31 exit path to clean dcache lines
covering the per-cpu region, ensuring data written by the primary core
is visible to secondary cores.

tpidr_el3 setup: Initializes tpidr_el3 with the base address of the
current CPU’s per-cpu section. This allows per-cpu framework to
resolve local cpu accesses efficiently.

The percpu_data object is currently stored in tpidr_el3. Since the
per-cpu framework will use tpidr_el3 for this-cpu access, percpu_data
must be migrated to avoid conflict. This commit moves percpu_data to
the per-cpu framework.

Signed-off-by: Sammit Joshi <sammit.joshi@arm.com>
Signed-off-by: Rohit Mathew <rohit.mathew@arm.com>
Change-Id: Iff0c2e1f8c0ebd25c4bb0b09bfe15dd4fbe20561

show more ...

feat(per-cpu): introduce framework accessors/definers

Introduce per-cpu framework definers and accessors for allocation and
access of per-cpu objects. The accessors support "per_cpu_cur" variants
fo

feat(per-cpu): introduce framework accessors/definers

Introduce per-cpu framework definers and accessors for allocation and
access of per-cpu objects. The accessors support "per_cpu_cur" variants
for access on the calling CPU as well as "per_cpu_by_index" variants for
access on any CPU. Additionally, the framework supports NUMA-aware
allocation, allowing the per-cpu data to be distributed across different
memory nodes. This enables the system to allocate per-cpu data on memory
nodes closest to the respective CPU, optimising memory access and
performance.

Signed-off-by: Sammit Joshi <sammit.joshi@arm.com>
Signed-off-by: Rohit Mathew <rohit.mathew@arm.com>
Change-Id: I8361602ff626dcfe9405e7e2a28c5d143aaac574

show more ...

feat(per-cpu): introduce linker changes for NUMA aware per-cpu framework

This commit introduces linker changes for NUMA aware per-cpu objects in
the BL31 and BL32 images. The per-cpu framework is de

feat(per-cpu): introduce linker changes for NUMA aware per-cpu framework

This commit introduces linker changes for NUMA aware per-cpu objects in
the BL31 and BL32 images. The per-cpu framework is designed to minimise
cache thrashing, and the linker layout ensures each CPU’s per-cpu data
is placed on a separate cache line. This isolation is expected to
improve performance when the per-cpu framework is enabled.

Signed-off-by: Sammit Joshi <sammit.joshi@arm.com>
Signed-off-by: Rohit Mathew <rohit.mathew@arm.com>
Change-Id: Ie4d8b4e444971adbd9dba0446d1ab8cafaca1556

show more ...

feat(cpufeat): introduce FEAT_RME_GDI support

This patch adds a new build flag ENABLE_FEAT_RME_GDI to enable this
feature, along with defining various related register fields. At this
point, when en

feat(cpufeat): introduce FEAT_RME_GDI support

This patch adds a new build flag ENABLE_FEAT_RME_GDI to enable this
feature, along with defining various related register fields. At this
point, when enabled, this feature enables the SA and NSP GPI encodings
by setting the corresponding bits in GPCCR_EL3.

Change-Id: I54152fbb3d19b176264e5d16acbcc866725dc290
Signed-off-by: John Powell <john.powell@arm.com>
Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>

show more ...

feat(cpufeat): add support for FEAT_RME_GPC2

This change adds support for FEAT_RME_GPC2 and Non-Secure-Only (NSO)
Physical Address Space.

Previously, all non-secure (NS) memory was accessible to th

feat(cpufeat): add support for FEAT_RME_GPC2

This change adds support for FEAT_RME_GPC2 and Non-Secure-Only (NSO)
Physical Address Space.

Previously, all non-secure (NS) memory was accessible to the secure
world and realm world. With GPC2 and the NSO bit in the GPT, memory
can now be restricted to the non-secure world only. This is enabled
automatically on supported systems when ENABLE_RME is true.

Change-Id: I9b70c3a23c5ec7d83bd787d0fb3edd55934f1d05
Signed-off-by: John Powell <john.powell@arm.com>
Signed-off-by: Girish Pathak <girish.pathak@arm.com>

show more ...

fix(psci): fix coverity issue with out-of-bounds read

Avoid OVERRUN on parent indices if accidental return negative value
from `get_pwr_lvl_state_idx`, so convert everything to use unsigned
int to a

fix(psci): fix coverity issue with out-of-bounds read

Avoid OVERRUN on parent indices if accidental return negative value
from `get_pwr_lvl_state_idx`, so convert everything to use unsigned
int to avoid Out-of-bounds read (OVERRUN)

Change-Id: Ie6d6fd34db9903e99b29e004fb46908aea8acd46
Signed-off-by: Govindraj Raja <govindraj.raja@arm.com>

show more ...

Merge changes from topic "ck/tf-a/tpip-updates" into integration

* changes:
chore(compiler-rt): update compiler-rt to v21.1.4
chore(zlib): update zlib to v1.3.1
chore(libfdt): update libfdt to

Merge changes from topic "ck/tf-a/tpip-updates" into integration

* changes:
chore(compiler-rt): update compiler-rt to v21.1.4
chore(zlib): update zlib to v1.3.1
chore(libfdt): update libfdt to v1.7.2

show more ...

feat(cpus): add support for Neoverse-N2 prefetcher

To get accurate and repeatable L2 cache performance metrics,
the L2 region prefetcher must be disabled. This prevents
speculative fetches from inte

feat(cpus): add support for Neoverse-N2 prefetcher

To get accurate and repeatable L2 cache performance metrics,
the L2 region prefetcher must be disabled. This prevents
speculative fetches from interfering with the measurements.

This patch adds a build-time option, NEOVERSE_N2_PREFETCHER_DISABLE,
to set the PF_DIS bit (bit 15) in the CPUECTLR_EL1 register for this
purpose.

Change-Id: Ie7ab9e84bb29d042d0bb2ec697e0c1e39ad5032e
Signed-off-by: Rohit Ner <rohitner@google.com>

show more ...