Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas: "The major features are support for LPA2 (52-bit VA/PA with 4K and 16K pages), the dpISA extension and Rust enabled on arm64. The changes are mostly contained within the usual arch/arm64/, drivers/perf, the arm64 Documentation and kselftests. The exception is the Rust support which touches some generic build files. Summary: - Reorganise the arm64 kernel VA space and add support for LPA2 (at stage 1, KVM stage 2 was merged earlier) - 52-bit VA/PA address range with 4KB and 16KB pages - Enable Rust on arm64 - Support for the 2023 dpISA extensions (data processing ISA), host only - arm64 perf updates: - StarFive's StarLink (integrates one or more CPU cores with a shared L3 memory system) PMU support - Enable HiSilicon Erratum 162700402 quirk for HIP09 - Several updates for the HiSilicon PCIe PMU driver - Arm CoreSight PMU support - Convert all drivers under drivers/perf/ to use .remove_new() - Miscellaneous: - Don't enable workarounds for "rare" errata by default - Clean up the DAIF flags handling for EL0 returns (in preparation for NMI support) - Kselftest update for ptrace() - Update some of the sysreg field definitions - Slight improvement in the code generation for inline asm I/O accessors to permit offset addressing - kretprobes: acquire regs via a BRK exception (previously done via a trampoline handler) - SVE/SME cleanups, comment updates - Allow CALL_OPS+CC_OPTIMIZE_FOR_SIZE with clang (previously disabled due to gcc silently ignoring -falign-functions=N)" * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (134 commits) Revert "mm: add arch hook to validate mmap() prot flags" Revert "arm64: mm: add support for WXN memory translation attribute" Revert "ARM64: Dynamically allocate cpumasks and increase supported CPUs to 512" ARM64: Dynamically allocate cpumasks and increase supported CPUs to 512 kselftest/arm64: Add 2023 DPISA hwcap test coverage kselftest/arm64: Add basic FPMR test kselftest/arm64: Handle FPMR context in generic signal frame parser arm64/hwcap: Define hwcaps for 2023 DPISA features arm64/ptrace: Expose FPMR via ptrace arm64/signal: Add FPMR signal handling arm64/fpsimd: Support FEAT_FPMR arm64/fpsimd: Enable host kernel access to FPMR arm64/cpufeature: Hook new identification registers up to cpufeature docs: perf: Fix build warning of hisi-pcie-pmu.rst perf: starfive: Only allow COMPILE_TEST for 64-bit architectures MAINTAINERS: Add entry for StarFive StarLink PMU docs: perf: Add description for StarFive's StarLink PMU dt-bindings: perf: starfive: Add JH8100 StarLink PMU perf: starfive: Add StarLink PMU support docs: perf: Update usage for target filter of hisi-pcie-pmu ...
2026-08-13 14:19:53 -07:00 · 2024-03-14 15:35:42 -07:00
parent fe46a7dd18 1ef21fcd6a
commit 6d75c6f40a
137 changed files with 5513 additions and 1583 deletions
@@ -37,9 +37,21 @@ Example usage of perf::
  hisi_pcie0_core0/rx_mwr_cnt/ [kernel PMU event]
  ------------------------------------------

-  $# perf stat -e hisi_pcie0_core0/rx_mwr_latency/
-  $# perf stat -e hisi_pcie0_core0/rx_mwr_cnt/
-  $# perf stat -g -e hisi_pcie0_core0/rx_mwr_latency/ -e hisi_pcie0_core0/rx_mwr_cnt/
+  $# perf stat -e hisi_pcie0_core0/rx_mwr_latency,port=0xffff/
+  $# perf stat -e hisi_pcie0_core0/rx_mwr_cnt,port=0xffff/
+
+The related events usually used to calculate the bandwidth, latency or others.
+They need to start and end counting at the same time, therefore related events
+are best used in the same event group to get the expected value. There are two
+ways to know if they are related events:
+
+a) By event name, such as the latency events "xxx_latency, xxx_cnt" or
+   bandwidth events "xxx_flux, xxx_time".
+b) By event type, such as "event=0xXXXX, event=0x1XXXX".
+
+Example usage of perf group::
+
+  $# perf stat -e "{hisi_pcie0_core0/rx_mwr_latency,port=0xffff/,hisi_pcie0_core0/rx_mwr_cnt,port=0xffff/}"

 The current driver does not support sampling. So "perf record" is unsupported.
 Also attach to a task is unsupported for PCIe PMU.
@@ -51,8 +63,12 @@ Filter options

   PMU could only monitor the performance of traffic downstream target Root
   Ports or downstream target Endpoint. PCIe PMU driver support "port" and
-   "bdf" interfaces for users, and these two interfaces aren't supported at the
-   same time.
+   "bdf" interfaces for users.
+   Please notice that, one of these two interfaces must be set, and these two
+   interfaces aren't supported at the same time. If they are both set, only
+   "port" filter is valid.
+   If "port" filter not being set or is set explicitly to zero (default), the
+   "bdf" filter will be in effect, because "bdf=0" meaning 0000:000:00.0.

   - port

@@ -95,7 +111,7 @@ Filter options

   Example usage of perf::

-     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,trig_len=0x4,trig_mode=1/ sleep 5
+     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,port=0xffff,trig_len=0x4,trig_mode=1/ sleep 5

 3. Threshold filter

@@ -109,7 +125,7 @@ Filter options

   Example usage of perf::

-     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,thr_len=0x4,thr_mode=1/ sleep 5
+     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,port=0xffff,thr_len=0x4,thr_mode=1/ sleep 5

 4. TLP Length filter

@@ -127,4 +143,4 @@ Filter options

   Example usage of perf::

-     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,len_mode=0x1/ sleep 5
+     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,port=0xffff,len_mode=0x1/ sleep 5
@@ -13,6 +13,7 @@ Performance monitor support
   imx-ddr
   qcom_l2_pmu
   qcom_l3_pmu
+   starfive_starlink_pmu
   arm-ccn
   arm-cmn
   xgene-pmu
@@ -0,0 +1,46 @@
+================================================
+StarFive StarLink Performance Monitor Unit (PMU)
+================================================
+
+StarFive StarLink Performance Monitor Unit (PMU) exists within the
+StarLink Coherent Network on Chip (CNoC) that connects multiple CPU
+clusters with an L3 memory system.
+
+The uncore PMU supports overflow interrupt, up to 16 programmable 64bit
+event counters, and an independent 64bit cycle counter.
+The PMU can only be accessed via Memory Mapped I/O and are common to the
+cores connected to the same PMU.
+
+Driver exposes supported PMU events in sysfs "events" directory under::
+
+  /sys/bus/event_source/devices/starfive_starlink_pmu/events/
+
+Driver exposes cpu used to handle PMU events in sysfs "cpumask" directory
+under::
+
+  /sys/bus/event_source/devices/starfive_starlink_pmu/cpumask/
+
+Driver describes the format of config (event ID) in sysfs "format" directory
+under::
+
+  /sys/bus/event_source/devices/starfive_starlink_pmu/format/
+
+Example of perf usage::
+
+	$ perf list
+
+	starfive_starlink_pmu/cycles/                      [Kernel PMU event]
+	starfive_starlink_pmu/read_hit/                    [Kernel PMU event]
+	starfive_starlink_pmu/read_miss/                   [Kernel PMU event]
+	starfive_starlink_pmu/read_request/                [Kernel PMU event]
+	starfive_starlink_pmu/release_request/             [Kernel PMU event]
+	starfive_starlink_pmu/write_hit/                   [Kernel PMU event]
+	starfive_starlink_pmu/write_miss/                  [Kernel PMU event]
+	starfive_starlink_pmu/write_request/               [Kernel PMU event]
+	starfive_starlink_pmu/writeback/                   [Kernel PMU event]
+
+
+	$ perf stat -a -e /starfive_starlink_pmu/cycles/ sleep 1
+
+Sampling is not supported. As a result, "perf record" is not supported.
+Attaching to a task is not supported, only system-wide counting is supported.
@@ -317,6 +317,55 @@ HWCAP2_LRCPC3
 HWCAP2_LSE128
    Functionality implied by ID_AA64ISAR0_EL1.Atomic == 0b0011.

+HWCAP2_FPMR
+    Functionality implied by ID_AA64PFR2_EL1.FMR == 0b0001.
+
+HWCAP2_LUT
+    Functionality implied by ID_AA64ISAR2_EL1.LUT == 0b0001.
+
+HWCAP2_FAMINMAX
+    Functionality implied by ID_AA64ISAR3_EL1.FAMINMAX == 0b0001.
+
+HWCAP2_F8CVT
+    Functionality implied by ID_AA64FPFR0_EL1.F8CVT == 0b1.
+
+HWCAP2_F8FMA
+    Functionality implied by ID_AA64FPFR0_EL1.F8FMA == 0b1.
+
+HWCAP2_F8DP4
+    Functionality implied by ID_AA64FPFR0_EL1.F8DP4 == 0b1.
+
+HWCAP2_F8DP2
+    Functionality implied by ID_AA64FPFR0_EL1.F8DP2 == 0b1.
+
+HWCAP2_F8E4M3
+    Functionality implied by ID_AA64FPFR0_EL1.F8E4M3 == 0b1.
+
+HWCAP2_F8E5M2
+    Functionality implied by ID_AA64FPFR0_EL1.F8E5M2 == 0b1.
+
+HWCAP2_SME_LUTV2
+    Functionality implied by ID_AA64SMFR0_EL1.LUTv2 == 0b1.
+
+HWCAP2_SME_F8F16
+    Functionality implied by ID_AA64SMFR0_EL1.F8F16 == 0b1.
+
+HWCAP2_SME_F8F32
+    Functionality implied by ID_AA64SMFR0_EL1.F8F32 == 0b1.
+
+HWCAP2_SME_SF8FMA
+    Functionality implied by ID_AA64SMFR0_EL1.SF8FMA == 0b1.
+
+HWCAP2_SME_SF8DP4
+    Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1.
+
+HWCAP2_SME_SF8DP2
+    Functionality implied by ID_AA64SMFR0_EL1.SF8DP2 == 0b1.
+
+HWCAP2_SME_SF8DP4
+    Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1.
+
+
 4. Unused AT_HWCAP bits
 -----------------------

@@ -35,8 +35,9 @@ can be triggered by Linux).
 For software workarounds that may adversely impact systems unaffected by
 the erratum in question, a Kconfig entry is added under "Kernel
 Features" -> "ARM errata workarounds via the alternatives framework".
-These are enabled by default and patched in at runtime when an affected
-CPU is detected. For less-intrusive workarounds, a Kconfig option is not
+With the exception of workarounds for errata deemed "rare" by Arm, these
+are enabled by default and patched in at runtime when an affected CPU is
+detected. For less-intrusive workarounds, a Kconfig option is not
 available and the code is structured (preferably with a comment) in such
 a way that the erratum will not be hit.

@@ -75,7 +75,7 @@ model features for SME is included in Appendix A.
 2.  Vector lengths
 ------------------

-SME defines a second vector length similar to the SVE vector length which is
+SME defines a second vector length similar to the SVE vector length which
 controls the size of the streaming mode SVE vectors and the ZA matrix array.
 The ZA matrix is square with each side having as many bytes as a streaming
 mode SVE vector.
@@ -238,12 +238,12 @@ prctl(PR_SME_SET_VL, unsigned long arg)
      bits of Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become
      unspecified, including both streaming and non-streaming SVE state.
      Calling PR_SME_SET_VL with vl equal to the thread's current vector
-      length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag,
+      length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag,
      does not constitute a change to the vector length for this purpose.

    * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared.
      Calling PR_SME_SET_VL with vl equal to the thread's current vector
-      length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag,
+      length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag,
      does not constitute a change to the vector length for this purpose.


@@ -379,9 +379,8 @@ The regset data starts with struct user_za_header, containing:
 /proc/sys/abi/sme_default_vector_length

    Writing the text representation of an integer to this file sets the system
-    default vector length to the specified value, unless the value is greater
-    than the maximum vector length supported by the system in which case the
-    default vector length is set to that maximum.
+    default vector length to the specified value rounded to a supported value
+    using the same rules as for setting vector length via PR_SME_SET_VL.

    The result can be determined by reopening the file and reading its
    contents.
@@ -117,11 +117,6 @@ the SVE instruction set architecture.
 * The SVE registers are not used to pass arguments to or receive results from
  any syscall.

-* In practice the affected registers/bits will be preserved or will be replaced
-  with zeros on return from a syscall, but userspace should not make
-  assumptions about this.  The kernel behaviour may vary on a case-by-case
-  basis.
-
 * All other SVE state of a thread, including the currently configured vector
  length, the state of the PR_SVE_VL_INHERIT flag, and the deferred vector
  length (if any), is preserved across all syscalls, subject to the specific
@@ -428,9 +423,8 @@ The regset data starts with struct user_sve_header, containing:
 /proc/sys/abi/sve_default_vector_length

    Writing the text representation of an integer to this file sets the system
-    default vector length to the specified value, unless the value is greater
-    than the maximum vector length supported by the system in which case the
-    default vector length is set to that maximum.
+    default vector length to the specified value rounded to a supported value
+    using the same rules as for setting vector length via PR_SVE_SET_VL.

    The result can be determined by reopening the file and reading its
    contents.
@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/perf/arm,coresight-pmu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Arm Coresight Performance Monitoring Unit Architecture
+
+maintainers:
+  - Robin Murphy <robin.murphy@arm.com>
+
+properties:
+  compatible:
+    const: arm,coresight-pmu
+
+  reg:
+    items:
+      - description: Register page 0
+      - description: Register page 1, if the PMU implements the dual-page extension
+    minItems: 1
+
+  interrupts:
+    items:
+      - description: Overflow interrupt
+
+  cpus:
+    description: If the PMU is associated with a particular CPU or subset of CPUs,
+      array of phandles to the appropriate CPU node(s)
+
+  reg-io-width:
+    description: Granularity at which PMU register accesses are single-copy atomic
+    default: 4
+    enum: [4, 8]
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/perf/starfive,jh8100-starlink-pmu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: StarFive JH8100 StarLink PMU
+
+maintainers:
+  - Ji Sheng Teoh <jisheng.teoh@starfivetech.com>
+
+description:
+  StarFive's JH8100 StarLink PMU integrates one or more CPU cores with a
+  shared L3 memory system. The PMU support overflow interrupt, up to
+  16 programmable 64bit event counters, and an independent 64bit cycle
+  counter. StarFive's JH8100 StarLink PMU is accessed via MMIO.
+
+properties:
+  compatible:
+    const: starfive,jh8100-starlink-pmu
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        pmu@12900000 {
+            compatible = "starfive,jh8100-starlink-pmu";
+            reg = <0x0 0x12900000 0x0 0x10000>;
+            interrupts = <34>;
+        };
+    };
@@ -15,6 +15,7 @@ support corresponds to ``S`` values in the ``MAINTAINERS`` file.
 =============  ================  ==============================================
 Architecture   Level of support  Constraints
 =============  ================  ==============================================
+``arm64``      Maintained        Little Endian only.
 ``loongarch``  Maintained        -
 ``um``         Maintained        ``x86_64`` only.
 ``x86``        Maintained        ``x86_64`` only.
@@ -20974,6 +20974,13 @@ S:	Maintained
 T:	git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/
 F:	Documentation/devicetree/bindings/soc/starfive/

+STARFIVE STARLINK PMU DRIVER
+M:	Ji Sheng Teoh <jisheng.teoh@starfivetech.com>
+S:	Maintained
+F:	Documentation/admin-guide/perf/starfive_starlink_pmu.rst
+F:	Documentation/devicetree/bindings/perf/starfive,jh8100-starlink-pmu.yaml
+F:	drivers/perf/starfive_starlink_pmu.c
+
 STARFIVE TRNG DRIVER
 M:	Jia Jie Ho <jiajie.ho@starfivetech.com>
 S:	Supported
@@ -561,7 +561,6 @@ KBUILD_CFLAGS += -fno-strict-aliasing

 KBUILD_CPPFLAGS := -D__KERNEL__
 KBUILD_RUSTFLAGS := $(rust_common_flags) \
-		    --target=$(objtree)/scripts/target.json \
 		    -Cpanic=abort -Cembed-bitcode=n -Clto=n \
 		    -Cforce-unwind-tables=n -Ccodegen-units=1 \
 		    -Csymbol-mangling-version=v0 \
@@ -164,7 +164,7 @@ config ARM64
 	select HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
-	select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
+	select HAVE_ARCH_KASAN
 	select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN
 	select HAVE_ARCH_KASAN_SW_TAGS if HAVE_ARCH_KASAN
 	select HAVE_ARCH_KASAN_HW_TAGS if (HAVE_ARCH_KASAN && ARM64_MTE)
@@ -198,7 +198,7 @@ config ARM64
 		if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS
 	select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \
 		if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG && \
-		    !CC_OPTIMIZE_FOR_SIZE)
+		    (CC_IS_CLANG || !CC_OPTIMIZE_FOR_SIZE))
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
 		if DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_SAMPLE_FTRACE_DIRECT
@@ -229,6 +229,7 @@ config ARM64
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select MMU_GATHER_RCU_TABLE_FREE
 	select HAVE_RSEQ
+	select HAVE_RUST if CPU_LITTLE_ENDIAN
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KPROBES
@@ -362,7 +363,9 @@ config PGTABLE_LEVELS
 	default 3 if ARM64_64K_PAGES && (ARM64_VA_BITS_48 || ARM64_VA_BITS_52)
 	default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39
 	default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47
+	default 4 if ARM64_16K_PAGES && (ARM64_VA_BITS_48 || ARM64_VA_BITS_52)
 	default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48
+	default 5 if ARM64_4K_PAGES && ARM64_VA_BITS_52

 config ARCH_SUPPORTS_UPROBES
 	def_bool y
@@ -390,13 +393,13 @@ config BUILTIN_RETURN_ADDRESS_STRIPS_PAC
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN_GENERIC || KASAN_SW_TAGS
-	default 0xdfff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS
-	default 0xdfffc00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS
+	default 0xdfff800000000000 if (ARM64_VA_BITS_48 || (ARM64_VA_BITS_52 && !ARM64_16K_PAGES)) && !KASAN_SW_TAGS
+	default 0xdfffc00000000000 if (ARM64_VA_BITS_47 || ARM64_VA_BITS_52) && ARM64_16K_PAGES && !KASAN_SW_TAGS
 	default 0xdffffe0000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS
 	default 0xdfffffc000000000 if ARM64_VA_BITS_39 && !KASAN_SW_TAGS
 	default 0xdffffff800000000 if ARM64_VA_BITS_36 && !KASAN_SW_TAGS
-	default 0xefff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && KASAN_SW_TAGS
-	default 0xefffc00000000000 if ARM64_VA_BITS_47 && KASAN_SW_TAGS
+	default 0xefff800000000000 if (ARM64_VA_BITS_48 || (ARM64_VA_BITS_52 && !ARM64_16K_PAGES)) && KASAN_SW_TAGS
+	default 0xefffc00000000000 if (ARM64_VA_BITS_47 || ARM64_VA_BITS_52) && ARM64_16K_PAGES && KASAN_SW_TAGS
 	default 0xeffffe0000000000 if ARM64_VA_BITS_42 && KASAN_SW_TAGS
 	default 0xefffffc000000000 if ARM64_VA_BITS_39 && KASAN_SW_TAGS
 	default 0xeffffff800000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS
@@ -541,9 +544,8 @@ config ARM64_ERRATUM_832075
 	  If unsure, say Y.

 config ARM64_ERRATUM_834220
-	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault"
+	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault (rare)"
 	depends on KVM
-	default y
 	help
 	  This option adds an alternative code sequence to work around ARM
 	  erratum 834220 on Cortex-A57 parts up to r1p2.
@@ -559,7 +561,7 @@ config ARM64_ERRATUM_834220
 	  as it depends on the alternative framework, which will only patch
 	  the kernel if an affected CPU is detected.

-	  If unsure, say Y.
+	  If unsure, say N.

 config ARM64_ERRATUM_1742098
 	bool "Cortex-A57/A72: 1742098: ELR recorded incorrectly on interrupt taken between cryptographic instructions in a sequence"
@@ -686,8 +688,7 @@ config ARM64_WORKAROUND_REPEAT_TLBI
 	bool

 config ARM64_ERRATUM_2441007
-	bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI"
-	default y
+	bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)"
 	select ARM64_WORKAROUND_REPEAT_TLBI
 	help
 	  This option adds a workaround for ARM Cortex-A55 erratum #2441007.
@@ -700,11 +701,10 @@ config ARM64_ERRATUM_2441007
 	  Work around this by adding the affected CPUs to the list that needs
 	  TLB sequences to be done twice.

-	  If unsure, say Y.
+	  If unsure, say N.

 config ARM64_ERRATUM_1286807
-	bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation"
-	default y
+	bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation (rare)"
 	select ARM64_WORKAROUND_REPEAT_TLBI
 	help
 	  This option adds a workaround for ARM Cortex-A76 erratum 1286807.
@@ -718,6 +718,8 @@ config ARM64_ERRATUM_1286807
 	  invalidated has been observed by other observers. The
 	  workaround repeats the TLBI+DSB operation.

+	  If unsure, say N.
+
 config ARM64_ERRATUM_1463225
 	bool "Cortex-A76: Software Step might prevent interrupt recognition"
 	default y
@@ -737,8 +739,7 @@ config ARM64_ERRATUM_1463225
 	  If unsure, say Y.

 config ARM64_ERRATUM_1542419
-	bool "Neoverse-N1: workaround mis-ordering of instruction fetches"
-	default y
+	bool "Neoverse-N1: workaround mis-ordering of instruction fetches (rare)"
 	help
 	  This option adds a workaround for ARM Neoverse-N1 erratum
 	  1542419.
@@ -750,7 +751,7 @@ config ARM64_ERRATUM_1542419
 	  Workaround the issue by hiding the DIC feature from EL0. This
 	  forces user-space to perform cache maintenance.

-	  If unsure, say Y.
+	  If unsure, say N.

 config ARM64_ERRATUM_1508412
 	bool "Cortex-A77: 1508412: workaround deadlock on sequence of NC/Device load and store exclusive or PAR read"
@@ -925,8 +926,7 @@ config ARM64_ERRATUM_2224489
 	  If unsure, say Y.

 config ARM64_ERRATUM_2441009
-	bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI"
-	default y
+	bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)"
 	select ARM64_WORKAROUND_REPEAT_TLBI
 	help
 	  This option adds a workaround for ARM Cortex-A510 erratum #2441009.
@@ -939,7 +939,7 @@ config ARM64_ERRATUM_2441009
 	  Work around this by adding the affected CPUs to the list that needs
 	  TLB sequences to be done twice.

-	  If unsure, say Y.
+	  If unsure, say N.

 config ARM64_ERRATUM_2064142
 	bool "Cortex-A510: 2064142: workaround TRBE register writes while disabled"
@@ -1278,9 +1278,7 @@ endchoice

 choice
 	prompt "Virtual address space size"
-	default ARM64_VA_BITS_39 if ARM64_4K_PAGES
-	default ARM64_VA_BITS_47 if ARM64_16K_PAGES
-	default ARM64_VA_BITS_42 if ARM64_64K_PAGES
+	default ARM64_VA_BITS_52
 	help
 	  Allows choosing one of multiple possible virtual address
 	  space sizes. The level of translation table is determined by
@@ -1307,7 +1305,7 @@ config ARM64_VA_BITS_48

 config ARM64_VA_BITS_52
 	bool "52-bit"
-	depends on ARM64_64K_PAGES && (ARM64_PAN || !ARM64_SW_TTBR0_PAN)
+	depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
 	help
 	  Enable 52-bit virtual addressing for userspace when explicitly
 	  requested via a hint to mmap(). The kernel will also use 52-bit
@@ -1354,10 +1352,11 @@ choice

 config ARM64_PA_BITS_48
 	bool "48-bit"
+	depends on ARM64_64K_PAGES || !ARM64_VA_BITS_52

 config ARM64_PA_BITS_52
-	bool "52-bit (ARMv8.2)"
-	depends on ARM64_64K_PAGES
+	bool "52-bit"
+	depends on ARM64_64K_PAGES || ARM64_VA_BITS_52
 	depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
 	help
 	  Enable support for a 52-bit physical address space, introduced as
@@ -1374,6 +1373,10 @@ config ARM64_PA_BITS
 	default 48 if ARM64_PA_BITS_48
 	default 52 if ARM64_PA_BITS_52

+config ARM64_LPA2
+	def_bool y
+	depends on ARM64_PA_BITS_52 && !ARM64_64K_PAGES
+
 choice
 	prompt "Endianness"
 	default CPU_LITTLE_ENDIAN
@@ -41,6 +41,8 @@ KBUILD_CFLAGS	+= -mgeneral-regs-only	\
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
 KBUILD_AFLAGS	+= $(compat_vdso)

+KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon"
+
 KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
 KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)

@@ -65,7 +67,9 @@ endif

 ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
  KBUILD_CFLAGS += -mbranch-protection=pac-ret+bti
+  KBUILD_RUSTFLAGS += -Zbranch-protection=bti,pac-ret
 else ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
+  KBUILD_RUSTFLAGS += -Zbranch-protection=pac-ret
  ifeq ($(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET),y)
    KBUILD_CFLAGS += -mbranch-protection=pac-ret
  else
@@ -76,7 +76,6 @@ CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_VISCONTI=y
 CONFIG_ARCH_XGENE=y
 CONFIG_ARCH_ZYNQMP=y
-CONFIG_ARM64_VA_BITS_48=y
 CONFIG_SCHED_MC=y
 CONFIG_SCHED_SMT=y
 CONFIG_NUMA=y
@@ -129,6 +129,4 @@ static inline bool __init __early_cpu_has_rndr(void)
 	return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf;
 }

-u64 kaslr_early_init(void *fdt);
-
 #endif /* _ASM_ARCHRANDOM_H */
@@ -38,10 +38,6 @@
 	msr	daifset, #0xf
 	.endm

-	.macro enable_daif
-	msr	daifclr, #0xf
-	.endm
-
 /*
 * Save/restore interrupts.
 */
@@ -345,20 +341,6 @@ alternative_cb_end
 	bfi	\valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH
 	.endm

-/*
- * idmap_get_t0sz - get the T0SZ value needed to cover the ID map
- *
- * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
- * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
- * this number conveniently equals the number of leading zeroes in
- * the physical address of _end.
- */
-	.macro	idmap_get_t0sz, reg
-	adrp	\reg, _end
-	orr	\reg, \reg, #(1 << VA_BITS_MIN) - 1
-	clz	\reg, \reg
-	.endm
-
 /*
 * tcr_compute_pa_size - set TCR.(I)PS to the highest supported
 * ID_AA64MMFR0_EL1.PARange value
@@ -590,18 +572,27 @@ alternative_endif
 	.endm

 /*
- * Offset ttbr1 to allow for 48-bit kernel VAs set with 52-bit PTRS_PER_PGD.
+ * If the kernel is built for 52-bit virtual addressing but the hardware only
+ * supports 48 bits, we cannot program the pgdir address into TTBR1 directly,
+ * but we have to add an offset so that the TTBR1 address corresponds with the
+ * pgdir entry that covers the lowest 48-bit addressable VA.
+ *
+ * Note that this trick is only used for LVA/64k pages - LPA2/4k pages uses an
+ * additional paging level, and on LPA2/16k pages, we would end up with a root
+ * level table with only 2 entries, which is suboptimal in terms of TLB
+ * utilization, so there we fall back to 47 bits of translation if LPA2 is not
+ * supported.
+ *
 * orr is used as it can cover the immediate value (and is idempotent).
- * In future this may be nop'ed out when dealing with 52-bit kernel VAs.
 * 	ttbr: Value of ttbr to set, modified.
 */
 	.macro	offset_ttbr1, ttbr, tmp
-#ifdef CONFIG_ARM64_VA_BITS_52
-	mrs_s	\tmp, SYS_ID_AA64MMFR2_EL1
-	and	\tmp, \tmp, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT)
-	cbnz	\tmp, .Lskipoffs_\@
-	orr	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
-.Lskipoffs_\@ :
+#if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2)
+	mrs	\tmp, tcr_el1
+	and	\tmp, \tmp, #TCR_T1SZ_MASK
+	cmp	\tmp, #TCR_T1SZ(VA_BITS_MIN)
+	orr	\tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET
+	csel	\ttbr, \tmp, \ttbr, eq
 #endif
 	.endm

@@ -623,25 +614,13 @@ alternative_endif

 	.macro	phys_to_pte, pte, phys
 #ifdef CONFIG_ARM64_PA_BITS_52
-	/*
-	 * We assume \phys is 64K aligned and this is guaranteed by only
-	 * supporting this configuration with 64K pages.
-	 */
-	orr	\pte, \phys, \phys, lsr #36
-	and	\pte, \pte, #PTE_ADDR_MASK
+	orr	\pte, \phys, \phys, lsr #PTE_ADDR_HIGH_SHIFT
+	and	\pte, \pte, #PHYS_TO_PTE_ADDR_MASK
 #else
 	mov	\pte, \phys
 #endif
 	.endm

-	.macro	pte_to_phys, phys, pte
-	and	\phys, \pte, #PTE_ADDR_MASK
-#ifdef CONFIG_ARM64_PA_BITS_52
-	orr	\phys, \phys, \phys, lsl #PTE_ADDR_HIGH_SHIFT
-	and	\phys, \phys, GENMASK_ULL(PHYS_MASK_SHIFT - 1, PAGE_SHIFT)
-#endif
-	.endm
-
 /*
 * tcr_clear_errata_bits - Clear TCR bits that trigger an errata on this CPU.
 */
@@ -11,6 +11,7 @@
 * 0x004: for installing kprobes
 * 0x005: for installing uprobes
 * 0x006: for kprobe software single-step
+ * 0x007: for kretprobe return
 * Allowed values for kgdb are 0x400 - 0x7ff
 * 0x100: for triggering a fault on purpose (reserved)
 * 0x400: for dynamic BRK instruction
@@ -23,6 +24,7 @@
 #define KPROBES_BRK_IMM			0x004
 #define UPROBES_BRK_IMM			0x005
 #define KPROBES_BRK_SS_IMM		0x006
+#define KRETPROBES_BRK_IMM		0x007
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401
@@ -52,14 +52,17 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64isar0;
 	u64		reg_id_aa64isar1;
 	u64		reg_id_aa64isar2;
+	u64		reg_id_aa64isar3;
 	u64		reg_id_aa64mmfr0;
 	u64		reg_id_aa64mmfr1;
 	u64		reg_id_aa64mmfr2;
 	u64		reg_id_aa64mmfr3;
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
+	u64		reg_id_aa64pfr2;
 	u64		reg_id_aa64zfr0;
 	u64		reg_id_aa64smfr0;
+	u64		reg_id_aa64fpfr0;

 	struct cpuinfo_32bit	aarch32;
 };
@@ -17,6 +17,7 @@

 #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR	0
 #define ARM64_SW_FEATURE_OVERRIDE_HVHE		4
+#define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF	8

 #ifndef __ASSEMBLY__

@@ -768,6 +769,11 @@ static __always_inline bool system_supports_tpidr2(void)
 	return system_supports_sme();
 }

+static __always_inline bool system_supports_fpmr(void)
+{
+	return alternative_has_cap_unlikely(ARM64_HAS_FPMR);
+}
+
 static __always_inline bool system_supports_cnp(void)
 {
 	return alternative_has_cap_unlikely(ARM64_HAS_CNP);
@@ -905,7 +911,9 @@ static inline unsigned int get_vmid_bits(u64 mmfr1)
 s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur);
 struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id);

+extern struct arm64_ftr_override id_aa64mmfr0_override;
 extern struct arm64_ftr_override id_aa64mmfr1_override;
+extern struct arm64_ftr_override id_aa64mmfr2_override;
 extern struct arm64_ftr_override id_aa64pfr0_override;
 extern struct arm64_ftr_override id_aa64pfr1_override;
 extern struct arm64_ftr_override id_aa64zfr0_override;
@@ -915,9 +923,114 @@ extern struct arm64_ftr_override id_aa64isar2_override;

 extern struct arm64_ftr_override arm64_sw_feature_override;

+static inline
+u64 arm64_apply_feature_override(u64 val, int feat, int width,
+				 const struct arm64_ftr_override *override)
+{
+	u64 oval = override->val;
+
+	/*
+	 * When it encounters an invalid override (e.g., an override that
+	 * cannot be honoured due to a missing CPU feature), the early idreg
+	 * override code will set the mask to 0x0 and the value to non-zero for
+	 * the field in question. In order to determine whether the override is
+	 * valid or not for the field we are interested in, we first need to
+	 * disregard bits belonging to other fields.
+	 */
+	oval &= GENMASK_ULL(feat + width - 1, feat);
+
+	/*
+	 * The override is valid if all value bits are accounted for in the
+	 * mask. If so, replace the masked bits with the override value.
+	 */
+	if (oval == (oval & override->mask)) {
+		val &= ~override->mask;
+		val |= oval;
+	}
+
+	/* Extract the field from the updated value */
+	return cpuid_feature_extract_unsigned_field(val, feat);
+}
+
+static inline bool arm64_test_sw_feature_override(int feat)
+{
+	/*
+	 * Software features are pseudo CPU features that have no underlying
+	 * CPUID system register value to apply the override to.
+	 */
+	return arm64_apply_feature_override(0, feat, 4,
+					    &arm64_sw_feature_override);
+}
+
+static inline bool kaslr_disabled_cmdline(void)
+{
+	return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR);
+}
+
 u32 get_kvm_ipa_limit(void);
 void dump_cpu_features(void);

+static inline bool cpu_has_bti(void)
+{
+	if (!IS_ENABLED(CONFIG_ARM64_BTI))
+		return false;
+
+	return arm64_apply_feature_override(read_cpuid(ID_AA64PFR1_EL1),
+					    ID_AA64PFR1_EL1_BT_SHIFT, 4,
+					    &id_aa64pfr1_override);
+}
+
+static inline bool cpu_has_pac(void)
+{
+	u64 isar1, isar2;
+
+	if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH))
+		return false;
+
+	isar1 = read_cpuid(ID_AA64ISAR1_EL1);
+	isar2 = read_cpuid(ID_AA64ISAR2_EL1);
+
+	if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_APA_SHIFT, 4,
+					 &id_aa64isar1_override))
+		return true;
+
+	if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_API_SHIFT, 4,
+					 &id_aa64isar1_override))
+		return true;
+
+	return arm64_apply_feature_override(isar2, ID_AA64ISAR2_EL1_APA3_SHIFT, 4,
+					    &id_aa64isar2_override);
+}
+
+static inline bool cpu_has_lva(void)
+{
+	u64 mmfr2;
+
+	mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1);
+	mmfr2 &= ~id_aa64mmfr2_override.mask;
+	mmfr2 |= id_aa64mmfr2_override.val;
+	return cpuid_feature_extract_unsigned_field(mmfr2,
+						    ID_AA64MMFR2_EL1_VARange_SHIFT);
+}
+
+static inline bool cpu_has_lpa2(void)
+{
+#ifdef CONFIG_ARM64_LPA2
+	u64 mmfr0;
+	int feat;
+
+	mmfr0 = read_sysreg(id_aa64mmfr0_el1);
+	mmfr0 &= ~id_aa64mmfr0_override.mask;
+	mmfr0 |= id_aa64mmfr0_override.val;
+	feat = cpuid_feature_extract_signed_field(mmfr0,
+						  ID_AA64MMFR0_EL1_TGRAN_SHIFT);
+
+	return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2;
+#else
+	return false;
+#endif
+}
+
 #endif /* __ASSEMBLY__ */

 #endif
--- a/Show More
+++ b/Show More