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
  ...

1 files changed, 18 insertions, 0 deletions

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index f27acca550d5..ebb0158997ca 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -359,6 +359,9 @@ static void task_fpsimd_load(void)
 	WARN_ON(preemptible());
 	WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE));
 
+	if (system_supports_fpmr())
+		write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR);
+
 	if (system_supports_sve() || system_supports_sme()) {
 		switch (current->thread.fp_type) {
 		case FP_STATE_FPSIMD:
@@ -446,6 +449,9 @@ static void fpsimd_save_user_state(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
+	if (system_supports_fpmr())
+		*(last->fpmr) = read_sysreg_s(SYS_FPMR);
+
 	/*
 	 * If a task is in a syscall the ABI allows us to only
 	 * preserve the state shared with FPSIMD so don't bother
@@ -688,6 +694,12 @@ static void sve_to_fpsimd(struct task_struct *task)
 	}
 }
 
+void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p)
+{
+	write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK,
+		       SYS_SCTLR_EL1);
+}
+
 #ifdef CONFIG_ARM64_SVE
 /*
  * Call __sve_free() directly only if you know task can't be scheduled
@@ -1134,6 +1146,8 @@ void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p)
 {
 	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1);
 	isb();
+
+	write_sysreg_s(0, SYS_ZCR_EL1);
 }
 
 void __init sve_setup(void)
@@ -1245,6 +1259,9 @@ void cpu_enable_sme(const struct arm64_cpu_capabilities *__always_unused p)
 	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1);
 	isb();
 
+	/* Ensure all bits in SMCR are set to known values */
+	write_sysreg_s(0, SYS_SMCR_EL1);
+
 	/* Allow EL0 to access TPIDR2 */
 	write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1);
 	isb();
@@ -1696,6 +1713,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->sve_vl = task_get_sve_vl(current);
 	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
+	last->fpmr = &current->thread.uw.fpmr;
 	last->fp_type = &current->thread.fp_type;
 	last->to_save = FP_STATE_CURRENT;
 	current->thread.fpsimd_cpu = smp_processor_id();