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

Documentation/arch/arm64/silicon-errata.rst

@@ -243,3 +243,10 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ASR            | ASR8601         | #8601001        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2139208        | ARM64_ERRATUM_2139208       |
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2067961        | ARM64_ERRATUM_2067961       |
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2253138        | ARM64_ERRATUM_2253138       |
++----------------+-----------------+-----------------+-----------------------------+

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;

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

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;
 

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:

arch/arm64/kernel/cpu_errata.c

@@ -374,6 +374,7 @@ static const struct midr_range erratum_1463225[] = {
 static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2139208
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2119858
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -387,6 +388,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 static const struct midr_range tsb_flush_fail_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2067961
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2054223
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -399,6 +401,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = {
 static struct midr_range trbe_write_out_of_range_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2253138
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2224489
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),

arch/arm64/kernel/fpsimd.c

@@ -1635,7 +1635,7 @@ void fpsimd_preserve_current_state(void)
 void fpsimd_signal_preserve_current_state(void)
 {
 	fpsimd_preserve_current_state();
-	if (test_thread_flag(TIF_SVE))
+	if (current->thread.fp_type == FP_STATE_SVE)
 		sve_to_fpsimd(current);
 }
 

arch/arm64/kernel/ptrace.c

@@ -1500,7 +1500,8 @@ static const struct user_regset aarch64_regsets[] = {
 #ifdef CONFIG_ARM64_SVE
 	[REGSET_SVE] = { /* Scalable Vector Extension */
 		.core_note_type = NT_ARM_SVE,
-		.n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX,
+					      SVE_PT_REGS_SVE),
 				  SVE_VQ_BYTES),
 		.size = SVE_VQ_BYTES,
 		.align = SVE_VQ_BYTES,

arch/arm64/kernel/signal.c

@@ -242,7 +242,7 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 		vl = task_get_sme_vl(current);
 		vq = sve_vq_from_vl(vl);
 		flags |= SVE_SIG_FLAG_SM;
-	} else if (test_thread_flag(TIF_SVE)) {
+	} else if (current->thread.fp_type == FP_STATE_SVE) {
 		vq = sve_vq_from_vl(vl);
 	}
 
@@ -878,7 +878,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 	if (system_supports_sve() || system_supports_sme()) {
 		unsigned int vq = 0;
 
-		if (add_all || test_thread_flag(TIF_SVE) ||
+		if (add_all || current->thread.fp_type == FP_STATE_SVE ||
 		    thread_sm_enabled(&current->thread)) {
 			int vl = max(sve_max_vl(), sme_max_vl());
 

drivers/perf/arm-cmn.c

@@ -2305,6 +2305,17 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
 				dev_dbg(cmn->dev, "ignoring external node %llx\n", reg);
 				continue;
 			}
+			/*
+			 * AmpereOneX erratum AC04_MESH_1 makes some XPs report a bogus
+			 * child count larger than the number of valid child pointers.
+			 * A child offset of 0 can only occur on CMN-600; otherwise it
+			 * would imply the root node being its own grandchild, which
+			 * we can safely dismiss in general.
+			 */
+			if (reg == 0 && cmn->part != PART_CMN600) {
+				dev_dbg(cmn->dev, "bogus child pointer?\n");
+				continue;
+			}
 
 			arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, dn);
 

drivers/perf/cxl_pmu.c

@@ -419,7 +419,7 @@ static struct attribute *cxl_pmu_event_attrs[] = {
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmp,			CXL_PMU_GID_S2M_NDR, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmps,			CXL_PMU_GID_S2M_NDR, BIT(1)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmpe,			CXL_PMU_GID_S2M_NDR, BIT(2)),
-	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack,		CXL_PMU_GID_S2M_NDR, BIT(3)),
+	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack,		CXL_PMU_GID_S2M_NDR, BIT(4)),
 	/* CXL rev 3.0 Table 3-46 S2M DRS opcodes */
 	CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdata,			CXL_PMU_GID_S2M_DRS, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdatanxm,		CXL_PMU_GID_S2M_DRS, BIT(1)),