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, 217 insertions, 0 deletions

diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 1189e77c8152..d8909b2b535a 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -58,11 +58,46 @@ static void cssc_sigill(void)
 	asm volatile(".inst 0xdac01c00" : : : "x0");
 }
 
+static void f8cvt_sigill(void)
+{
+	/* FSCALE V0.4H, V0.4H, V0.4H */
+	asm volatile(".inst 0x2ec03c00");
+}
+
+static void f8dp2_sigill(void)
+{
+	/* FDOT V0.4H, V0.4H, V0.5H */
+	asm volatile(".inst 0xe40fc00");
+}
+
+static void f8dp4_sigill(void)
+{
+	/* FDOT V0.2S, V0.2S, V0.2S */
+	asm volatile(".inst 0xe00fc00");
+}
+
+static void f8fma_sigill(void)
+{
+	/* FMLALB V0.8H, V0.16B, V0.16B */
+	asm volatile(".inst 0xec0fc00");
+}
+
+static void faminmax_sigill(void)
+{
+	/* FAMIN V0.4H, V0.4H, V0.4H */
+	asm volatile(".inst 0x2ec01c00");
+}
+
 static void fp_sigill(void)
 {
 	asm volatile("fmov s0, #1");
 }
 
+static void fpmr_sigill(void)
+{
+	asm volatile("mrs x0, S3_3_C4_C4_2" : : : "x0");
+}
+
 static void ilrcpc_sigill(void)
 {
 	/* LDAPUR W0, [SP, #8] */
@@ -95,6 +130,12 @@ static void lse128_sigill(void)
 		     : "cc", "memory");
 }
 
+static void lut_sigill(void)
+{
+	/* LUTI2 V0.16B, { V0.16B }, V[0] */
+	asm volatile(".inst 0x4e801000");
+}
+
 static void mops_sigill(void)
 {
 	char dst[1], src[1];
@@ -216,6 +257,78 @@ static void smef16f16_sigill(void)
 	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
 }
 
+static void smef8f16_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FDOT ZA.H[W0, 0], Z0.B-Z1.B, Z0.B-Z1.B */
+	asm volatile(".inst 0xc1a01020" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smef8f32_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FDOT ZA.S[W0, 0], { Z0.B-Z1.B }, Z0.B[0] */
+	asm volatile(".inst 0xc1500038" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smelutv2_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* LUTI4 { Z0.B-Z3.B }, ZT0, { Z0-Z1 } */
+	asm volatile(".inst 0xc08b0000" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesf8dp2_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FDOT Z0.H, Z0.B, Z0.B[0] */
+	asm volatile(".inst 0x64204400" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesf8dp4_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FDOT Z0.S, Z0.B, Z0.B[0] */
+	asm volatile(".inst 0xc1a41C00" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesf8fma_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FMLALB V0.8H, V0.16B, V0.16B */
+	asm volatile(".inst 0xec0fc00");
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
 static void sve_sigill(void)
 {
 	/* RDVL x0, #0 */
@@ -354,6 +467,53 @@ static const struct hwcap_data {
 		.sigill_fn = cssc_sigill,
 	},
 	{
+		.name = "F8CVT",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8CVT,
+		.cpuinfo = "f8cvt",
+		.sigill_fn = f8cvt_sigill,
+	},
+	{
+		.name = "F8DP4",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8DP4,
+		.cpuinfo = "f8dp4",
+		.sigill_fn = f8dp4_sigill,
+	},
+	{
+		.name = "F8DP2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8DP2,
+		.cpuinfo = "f8dp4",
+		.sigill_fn = f8dp2_sigill,
+	},
+	{
+		.name = "F8E5M2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8E5M2,
+		.cpuinfo = "f8e5m2",
+	},
+	{
+		.name = "F8E4M3",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8E4M3,
+		.cpuinfo = "f8e4m3",
+	},
+	{
+		.name = "F8FMA",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8FMA,
+		.cpuinfo = "f8fma",
+		.sigill_fn = f8fma_sigill,
+	},
+	{
+		.name = "FAMINMAX",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_FAMINMAX,
+		.cpuinfo = "faminmax",
+		.sigill_fn = faminmax_sigill,
+	},
+	{
 		.name = "FP",
 		.at_hwcap = AT_HWCAP,
 		.hwcap_bit = HWCAP_FP,
@@ -361,6 +521,14 @@ static const struct hwcap_data {
 		.sigill_fn = fp_sigill,
 	},
 	{
+		.name = "FPMR",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_FPMR,
+		.cpuinfo = "fpmr",
+		.sigill_fn = fpmr_sigill,
+		.sigill_reliable = true,
+	},
+	{
 		.name = "JSCVT",
 		.at_hwcap = AT_HWCAP,
 		.hwcap_bit = HWCAP_JSCVT,
@@ -412,6 +580,13 @@ static const struct hwcap_data {
 		.sigill_fn = lse128_sigill,
 	},
 	{
+		.name = "LUT",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_LUT,
+		.cpuinfo = "lut",
+		.sigill_fn = lut_sigill,
+	},
+	{
 		.name = "MOPS",
 		.at_hwcap = AT_HWCAP2,
 		.hwcap_bit = HWCAP2_MOPS,
@@ -512,6 +687,48 @@ static const struct hwcap_data {
 		.sigill_fn = smef16f16_sigill,
 	},
 	{
+		.name = "SME F8F16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_F8F16,
+		.cpuinfo = "smef8f16",
+		.sigill_fn = smef8f16_sigill,
+	},
+	{
+		.name = "SME F8F32",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_F8F32,
+		.cpuinfo = "smef8f32",
+		.sigill_fn = smef8f32_sigill,
+	},
+	{
+		.name = "SME LUTV2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_LUTV2,
+		.cpuinfo = "smelutv2",
+		.sigill_fn = smelutv2_sigill,
+	},
+	{
+		.name = "SME SF8FMA",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_SF8FMA,
+		.cpuinfo = "smesf8fma",
+		.sigill_fn = smesf8fma_sigill,
+	},
+	{
+		.name = "SME SF8DP2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_SF8DP2,
+		.cpuinfo = "smesf8dp2",
+		.sigill_fn = smesf8dp2_sigill,
+	},
+	{
+		.name = "SME SF8DP4",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_SF8DP4,
+		.cpuinfo = "smesf8dp4",
+		.sigill_fn = smesf8dp4_sigill,
+	},
+	{
 		.name = "SVE",
 		.at_hwcap = AT_HWCAP,
 		.hwcap_bit = HWCAP_SVE,