arm64 fixes for -rc1

- Fix broken FP register state tracking which resulted in filesystem
   corruption when dm-crypt is used
 
 - Workarounds for Arm CPU errata affecting the SSBS Spectre mitigation
 
 - Fix lockdep assertion in DMC620 memory controller PMU driver
 
 - Fix alignment of BUG table when CONFIG_DEBUG_BUGVERBOSE is disabled
 -----BEGIN PGP SIGNATURE-----
 
 iQFEBAABCgAuFiEEPxTL6PPUbjXGY88ct6xw3ITBYzQFAmZN3xcQHHdpbGxAa2Vy
 bmVsLm9yZwAKCRC3rHDchMFjNMWjCACBIwegWWitCxgvujTPzOc0AwbxJjJWVGF4
 0Y3sthbirIJc8e5K7HYv4wbbCHbaqHX4T9noAKx3wvskEomcNqYyI5Wzr/KTR82f
 OHWHeMebFCAvo+UKTBa71JZcjgB4wi4+UuXIV1tViuMvGRKJW3nXKSwIt4SSQOYM
 VmS8bvqyyJZtnpNDgniY6QHRCWatagHpQFNFePkvsJiSoi78+FZWb2k2h55rz0iE
 EG2Vuzw5r1MNqXHCpPaU7fNwsLFbNYiJz3CQYisBLondyDDMsK1XUkLWoxWgGJbK
 SNbE3becd0C2SlOTwllV4R59AsmMPvA7tOHbD41aGOSBlKY1Hi91
 =ivar
 -----END PGP SIGNATURE-----

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

Pull arm64 fixes from Will Deacon:
 "The major fix here is for a filesystem corruption issue reported on
  Apple M1 as a result of buggy management of the floating point
  register state introduced in 6.8. I initially reverted one of the
  offending patches, but in the end Ard cooked a proper fix so there's a
  revert+reapply in the series.

  Aside from that, we've got some CPU errata workarounds and misc other
  fixes.

   - Fix broken FP register state tracking which resulted in filesystem
     corruption when dm-crypt is used

   - Workarounds for Arm CPU errata affecting the SSBS Spectre
     mitigation

   - Fix lockdep assertion in DMC620 memory controller PMU driver

   - Fix alignment of BUG table when CONFIG_DEBUG_BUGVERBOSE is
     disabled"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64/fpsimd: Avoid erroneous elide of user state reload
  Reapply "arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD"
  arm64: asm-bug: Add .align 2 to the end of __BUG_ENTRY
  perf/arm-dmc620: Fix lockdep assert in ->event_init()
  Revert "arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD"
  arm64: errata: Add workaround for Arm errata 3194386 and 3312417
  arm64: cputype: Add Neoverse-V3 definitions
  arm64: cputype: Add Cortex-X4 definitions
  arm64: barrier: Restore spec_bar() macro

Documentation/arch/arm64/silicon-errata.rst

@@ -140,6 +140,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2224489        | ARM64_ERRATUM_2224489       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-X4       | #3194386        | ARM64_ERRATUM_3194386       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1188873,1418040| ARM64_ERRATUM_1418040       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
@@ -156,6 +158,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-V1     | #1619801        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-V3     | #3312417        | ARM64_ERRATUM_3312417       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-600         | #1076982,1209401| N/A                         |

arch/arm64/Kconfig

@@ -1067,6 +1067,48 @@ config ARM64_ERRATUM_3117295
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_SPECULATIVE_SSBS
+	bool
+
+config ARM64_ERRATUM_3194386
+	bool "Cortex-X4: 3194386: workaround for MSR SSBS not self-synchronizing"
+	select ARM64_WORKAROUND_SPECULATIVE_SSBS
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-X4 erratum 3194386.
+
+	  On affected cores "MSR SSBS, #0" instructions may not affect
+	  subsequent speculative instructions, which may permit unexepected
+	  speculative store bypassing.
+
+	  Work around this problem by placing a speculation barrier after
+	  kernel changes to SSBS. The presence of the SSBS special-purpose
+	  register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such
+	  that userspace will use the PR_SPEC_STORE_BYPASS prctl to change
+	  SSBS.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_3312417
+	bool "Neoverse-V3: 3312417: workaround for MSR SSBS not self-synchronizing"
+	select ARM64_WORKAROUND_SPECULATIVE_SSBS
+	default y
+	help
+	  This option adds the workaround for ARM Neoverse-V3 erratum 3312417.
+
+	  On affected cores "MSR SSBS, #0" instructions may not affect
+	  subsequent speculative instructions, which may permit unexepected
+	  speculative store bypassing.
+
+	  Work around this problem by placing a speculation barrier after
+	  kernel changes to SSBS. The presence of the SSBS special-purpose
+	  register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such
+	  that userspace will use the PR_SPEC_STORE_BYPASS prctl to change
+	  SSBS.
+
+	  If unsure, say Y.
+
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y

arch/arm64/include/asm/asm-bug.h

@@ -28,6 +28,7 @@
 	14470:	.long 14471f - .;			\
 _BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
 		.short flags; 				\
+		.align 2;				\
 		.popsection;				\
 	14471:
 #else

arch/arm64/include/asm/barrier.h

@@ -40,6 +40,10 @@
  */
 #define dgh()		asm volatile("hint #6" : : : "memory")
 
+#define spec_bar()	asm volatile(ALTERNATIVE("dsb nsh\nisb\n",		\
+						 SB_BARRIER_INSN"nop\n",	\
+						 ARM64_HAS_SB))
+
 #ifdef CONFIG_ARM64_PSEUDO_NMI
 #define pmr_sync()						\
 	do {							\

arch/arm64/include/asm/cpucaps.h

@@ -58,6 +58,8 @@ cpucap_is_possible(const unsigned int cap)
 		return IS_ENABLED(CONFIG_NVIDIA_CARMEL_CNP_ERRATUM);
 	case ARM64_WORKAROUND_REPEAT_TLBI:
 		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI);
+	case ARM64_WORKAROUND_SPECULATIVE_SSBS:
+		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS);
 	}
 
 	return true;

arch/arm64/include/asm/cputype.h

@@ -87,6 +87,8 @@
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
 #define ARM_CPU_PART_NEOVERSE_V2	0xD4F
+#define ARM_CPU_PART_CORTEX_X4		0xD82
+#define ARM_CPU_PART_NEOVERSE_V3	0xD84
 
 #define APM_CPU_PART_XGENE		0x000
 #define APM_CPU_VAR_POTENZA		0x00
@@ -161,6 +163,8 @@
 #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
 #define MIDR_CORTEX_A78C	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
 #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2)
+#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4)
+#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)

arch/arm64/kernel/cpu_errata.c

@@ -432,6 +432,18 @@ static const struct midr_range erratum_spec_unpriv_load_list[] = {
 };
 #endif
 
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS
+static const struct midr_range erratum_spec_ssbs_list[] = {
+#ifdef CONFIG_ARM64_ERRATUM_3194386
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_X4),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_3312417
+	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3),
+#endif
+	{}
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -729,6 +741,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)),
 	},
 #endif
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS
+	{
+		.desc = "ARM errata 3194386, 3312417",
+		.capability = ARM64_WORKAROUND_SPECULATIVE_SSBS,
+		ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list),
+	},
+#endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	{
 		.desc = "ARM errata 2966298, 3117295",

arch/arm64/kernel/cpufeature.c

@@ -2307,6 +2307,14 @@ static void user_feature_fixup(void)
 		if (regp)
 			regp->user_mask &= ~ID_AA64ISAR1_EL1_BF16_MASK;
 	}
+
+	if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_SSBS)) {
+		struct arm64_ftr_reg *regp;
+
+		regp = get_arm64_ftr_reg(SYS_ID_AA64PFR1_EL1);
+		if (regp)
+			regp->user_mask &= ~ID_AA64PFR1_EL1_SSBS_MASK;
+	}
 }
 
 static void elf_hwcap_fixup(void)

arch/arm64/kernel/fpsimd.c

@@ -1535,6 +1535,27 @@ static void fpsimd_save_kernel_state(struct task_struct *task)
 	task->thread.kernel_fpsimd_cpu = smp_processor_id();
 }
 
+/*
+ * Invalidate any task's FPSIMD state that is present on this cpu.
+ * The FPSIMD context should be acquired with get_cpu_fpsimd_context()
+ * before calling this function.
+ */
+static void fpsimd_flush_cpu_state(void)
+{
+	WARN_ON(!system_supports_fpsimd());
+	__this_cpu_write(fpsimd_last_state.st, NULL);
+
+	/*
+	 * Leaving streaming mode enabled will cause issues for any kernel
+	 * NEON and leaving streaming mode or ZA enabled may increase power
+	 * consumption.
+	 */
+	if (system_supports_sme())
+		sme_smstop();
+
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+}
+
 void fpsimd_thread_switch(struct task_struct *next)
 {
 	bool wrong_task, wrong_cpu;
@@ -1552,7 +1573,7 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 	if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) {
 		fpsimd_load_kernel_state(next);
-		set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
+		fpsimd_flush_cpu_state();
 	} else {
 		/*
 		 * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
@@ -1842,27 +1863,6 @@ void fpsimd_flush_task_state(struct task_struct *t)
 	barrier();
 }
 
-/*
- * Invalidate any task's FPSIMD state that is present on this cpu.
- * The FPSIMD context should be acquired with get_cpu_fpsimd_context()
- * before calling this function.
- */
-static void fpsimd_flush_cpu_state(void)
-{
-	WARN_ON(!system_supports_fpsimd());
-	__this_cpu_write(fpsimd_last_state.st, NULL);
-
-	/*
-	 * Leaving streaming mode enabled will cause issues for any kernel
-	 * NEON and leaving streaming mode or ZA enabled may increase power
-	 * consumption.
-	 */
-	if (system_supports_sme())
-		sme_smstop();
-
-	set_thread_flag(TIF_FOREIGN_FPSTATE);
-}
-
 /*
  * Save the FPSIMD state to memory and invalidate cpu view.
  * This function must be called with preemption disabled.

arch/arm64/kernel/proton-pack.c

@@ -558,6 +558,18 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void)
 
 	/* SCTLR_EL1.DSSBS was initialised to 0 during boot */
 	set_pstate_ssbs(0);
+
+	/*
+	 * SSBS is self-synchronizing and is intended to affect subsequent
+	 * speculative instructions, but some CPUs can speculate with a stale
+	 * value of SSBS.
+	 *
+	 * Mitigate this with an unconditional speculation barrier, as CPUs
+	 * could mis-speculate branches and bypass a conditional barrier.
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS))
+		spec_bar();
+
 	return SPECTRE_MITIGATED;
 }
 

arch/arm64/tools/cpucaps

@@ -102,4 +102,5 @@ WORKAROUND_NVIDIA_CARMEL_CNP
 WORKAROUND_QCOM_FALKOR_E1003
 WORKAROUND_REPEAT_TLBI
 WORKAROUND_SPECULATIVE_AT
+WORKAROUND_SPECULATIVE_SSBS
 WORKAROUND_SPECULATIVE_UNPRIV_LOAD

drivers/perf/arm_dmc620_pmu.c

@@ -542,12 +542,16 @@ static int dmc620_pmu_event_init(struct perf_event *event)
 	if (event->cpu < 0)
 		return -EINVAL;
 
+	hwc->idx = -1;
+
+	if (event->group_leader == event)
+		return 0;
+
 	/*
 	 * We can't atomically disable all HW counters so only one event allowed,
 	 * although software events are acceptable.
 	 */
-	if (event->group_leader != event &&
+	if (!is_software_event(event->group_leader))
-			!is_software_event(event->group_leader))
 		return -EINVAL;
 
 	for_each_sibling_event(sibling, event->group_leader) {
@@ -556,7 +560,6 @@ static int dmc620_pmu_event_init(struct perf_event *event)
 			return -EINVAL;
 	}
 
-	hwc->idx = -1;
 	return 0;
 }