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

Pull arm64 fixes from Will Deacon:
 "It's a little busier than normal, but it's still not a lot of code and
  things seem fairly quiet in general:

   - Fix allocation failure during SVE coredumps

   - Fix handling of SVE context on signal delivery

   - Enable Neoverse N2 CPU errata workarounds for Microsoft's "Azure
     Cobalt 100" clone

   - Work around CMN PMU erratum in AmpereOneX implementation

   - Fix typo in CXL PMU event definition

   - Fix jump label asm constraints"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64/sve: Lower the maximum allocation for the SVE ptrace regset
  arm64: Subscribe Microsoft Azure Cobalt 100 to ARM Neoverse N2 errata
  perf/arm-cmn: Workaround AmpereOneX errata AC04_MESH_1 (incorrect child count)
  arm64: jump_label: use constraints "Si" instead of "i"
  arm64: fix typo in comments
  perf: CXL: fix mismatched cpmu event opcode
  arm64/signal: Don't assume that TIF_SVE means we saved SVE state

4 files changed, 19 insertions, 11 deletions

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 21c824edf8ce..bd8d4ca81a48 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -83,7 +83,7 @@ struct arm64_ftr_bits {
  * to full-0 denotes that this field has no override
  *
  * A @mask field set to full-0 with the corresponding @val field set
- * to full-1 denotes thath this field has an invalid override.
+ * to full-1 denotes that this field has an invalid override.
  */
 struct arm64_ftr_override {
 	u64		val;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 7c7493cb571f..52f076afeb96 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -61,6 +61,7 @@
 #define ARM_CPU_IMP_HISI		0x48
 #define ARM_CPU_IMP_APPLE		0x61
 #define ARM_CPU_IMP_AMPERE		0xC0
+#define ARM_CPU_IMP_MICROSOFT		0x6D
 
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
@@ -135,6 +136,8 @@
 
 #define AMPERE_CPU_PART_AMPERE1		0xAC3
 
+#define MICROSOFT_CPU_PART_AZURE_COBALT_100	0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -193,6 +196,7 @@
 #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
 #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 50e5f25d3024..481d94416d69 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -62,13 +62,13 @@ static inline void cpacr_restore(unsigned long cpacr)
  * When we defined the maximum SVE vector length we defined the ABI so
  * that the maximum vector length included all the reserved for future
  * expansion bits in ZCR rather than those just currently defined by
- * the architecture. While SME follows a similar pattern the fact that
- * it includes a square matrix means that any allocations that attempt
- * to cover the maximum potential vector length (such as happen with
- * the regset used for ptrace) end up being extremely large. Define
- * the much lower actual limit for use in such situations.
+ * the architecture.  Using this length to allocate worst size buffers
+ * results in excessively large allocations, and this effect is even
+ * more pronounced for SME due to ZA.  Define more suitable VLs for
+ * these situations.
  */
-#define SME_VQ_MAX	16
+#define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1)
+#define SME_VQ_MAX	((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1)
 
 struct task_struct;
 
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 6aafbb789991..b360c4c2b5e7 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -15,6 +15,10 @@
 
 #define JUMP_LABEL_NOP_SIZE		AARCH64_INSN_SIZE
 
+/*
+ * Prefer the constraint "S" to support PIC with GCC. Clang before 19 does not
+ * support "S" on a symbol with a constant offset, so we use "i" as a fallback.
+ */
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
@@ -23,9 +27,9 @@ static __always_inline bool arch_static_branch(struct static_key * const key,
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
 		 "	.long		1b - ., %l[l_yes] - .	\n\t"
-		 "	.quad		%c0 - .			\n\t"
+		 "	.quad		(%[key] - .) + %[bit0]  \n\t"
 		 "	.popsection				\n\t"
-		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
+		 :  :  [key]"Si"(key), [bit0]"i"(branch) :  : l_yes);
 
 	return false;
 l_yes:
@@ -40,9 +44,9 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
 		 "	.long		1b - ., %l[l_yes] - .	\n\t"
-		 "	.quad		%c0 - .			\n\t"
+		 "	.quad		(%[key] - .) + %[bit0]  \n\t"
 		 "	.popsection				\n\t"
-		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
+		 :  :  [key]"Si"(key), [bit0]"i"(branch) :  : l_yes);
 
 	return false;
 l_yes: