Merge remote-tracking branch 'stable/linux-6.18.y' into rpi-6.18.y

Author: popcornmix

Documentation/arch/arm64/silicon-errata.rst

@@ -202,6 +202,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-V3AE   | #3312417        | ARM64_ERRATUM_3194386       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | C1-Pro          | #4193714        | ARM64_ERRATUM_4193714       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | ARM_SMMU_MMU_500_CPRE_ERRATA|
 |                |                 | #562869,1047329 |                             |
 +----------------+-----------------+-----------------+-----------------------------+

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 18
-SUBLEVEL = 24
+SUBLEVEL = 26
 EXTRAVERSION =
 NAME = Baby Opossum Posse
 

arch/arm64/Kconfig

@@ -1155,6 +1155,18 @@ config ARM64_ERRATUM_3194386
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_4193714
+	bool "C1-Pro: 4193714: SME DVMSync early acknowledgement"
+	depends on ARM64_SME
+	default y
+	help
+	  Enable workaround for C1-Pro acknowledging the DVMSync before
+	  the SME memory accesses are complete. This will cause TLB
+	  maintenance for processes using SME to also issue an IPI to
+	  the affected CPUs.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y

arch/arm64/include/asm/cpucaps.h

@@ -66,6 +66,8 @@ cpucap_is_possible(const unsigned int cap)
 		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI);
 	case ARM64_WORKAROUND_SPECULATIVE_SSBS:
 		return IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386);
+	case ARM64_WORKAROUND_4193714:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_4193714);
 	case ARM64_MPAM:
 		/*
 		 * KVM MPAM support doesn't rely on the host kernel supporting MPAM.

arch/arm64/include/asm/cputype.h

@@ -98,6 +98,7 @@
 #define ARM_CPU_PART_CORTEX_A725	0xD87
 #define ARM_CPU_PART_CORTEX_A720AE	0xD89
 #define ARM_CPU_PART_NEOVERSE_N3	0xD8E
+#define ARM_CPU_PART_C1_PRO		0xD8B
 
 #define APM_CPU_PART_XGENE		0x000
 #define APM_CPU_VAR_POTENZA		0x00
@@ -189,6 +190,7 @@
 #define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725)
 #define MIDR_CORTEX_A720AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720AE)
 #define MIDR_NEOVERSE_N3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N3)
+#define MIDR_C1_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_C1_PRO)
 #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/include/asm/fpsimd.h

@@ -428,6 +428,24 @@ static inline size_t sme_state_size(struct task_struct const *task)
 	return __sme_state_size(task_get_sme_vl(task));
 }
 
+void sme_enable_dvmsync(void);
+void sme_set_active(void);
+void sme_clear_active(void);
+
+static inline void sme_enter_from_user_mode(void)
+{
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714) &&
+	    test_thread_flag(TIF_SME))
+		sme_clear_active();
+}
+
+static inline void sme_exit_to_user_mode(void)
+{
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714) &&
+	    test_thread_flag(TIF_SME))
+		sme_set_active();
+}
+
 #else
 
 static inline void sme_user_disable(void) { BUILD_BUG(); }
@@ -456,6 +474,9 @@ static inline size_t sme_state_size(struct task_struct const *task)
 	return 0;
 }
 
+static inline void sme_enter_from_user_mode(void) { }
+static inline void sme_exit_to_user_mode(void) { }
+
 #endif /* ! CONFIG_ARM64_SME */
 
 /* For use by EFI runtime services calls only */

arch/arm64/include/asm/tlbbatch.h

@@ -2,11 +2,17 @@
 #ifndef _ARCH_ARM64_TLBBATCH_H
 #define _ARCH_ARM64_TLBBATCH_H
 
+#include <linux/cpumask.h>
+
 struct arch_tlbflush_unmap_batch {
+#ifdef CONFIG_ARM64_ERRATUM_4193714
 	/*
-	 * For arm64, HW can do tlb shootdown, so we don't
-	 * need to record cpumask for sending IPI
+	 * Track CPUs that need SME DVMSync on completion of this batch.
+	 * Otherwise, the arm64 HW can do tlb shootdown, so we don't need to
+	 * record cpumask for sending IPI
 	 */
+	cpumask_var_t cpumask;
+#endif
 };
 
 #endif /* _ARCH_ARM64_TLBBATCH_H */

arch/arm64/include/asm/tlbflush.h

@@ -31,19 +31,11 @@
  */
 #define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
 			       "tlbi " #op "\n"				       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op,	       \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : )
 
 #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
-			       "tlbi " #op ", %0\n"			       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op ", %0",     \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
-			    : : "r" (arg))
+			       "tlbi " #op ", %x0\n"			       \
+			    : : "rZ" (arg))
 
 #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
 
@@ -88,6 +80,71 @@ static inline unsigned long get_trans_granule(void)
 	}
 }
 
+#ifdef CONFIG_ARM64_ERRATUM_4193714
+
+void sme_do_dvmsync(const struct cpumask *mask);
+
+static inline void sme_dvmsync(struct mm_struct *mm)
+{
+	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
+		return;
+
+	sme_do_dvmsync(mm_cpumask(mm));
+}
+
+static inline void sme_dvmsync_add_pending(struct arch_tlbflush_unmap_batch *batch,
+					   struct mm_struct *mm)
+{
+	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
+		return;
+
+	/*
+	 * Order the mm_cpumask() read after the hardware DVMSync.
+	 */
+	dsb(ish);
+	if (cpumask_empty(mm_cpumask(mm)))
+		return;
+
+	/*
+	 * Allocate the batch cpumask on first use. Fall back to an immediate
+	 * IPI for this mm in case of failure.
+	 */
+	if (!cpumask_available(batch->cpumask) &&
+	    !zalloc_cpumask_var(&batch->cpumask, GFP_ATOMIC)) {
+		sme_do_dvmsync(mm_cpumask(mm));
+		return;
+	}
+
+	cpumask_or(batch->cpumask, batch->cpumask, mm_cpumask(mm));
+}
+
+static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch)
+{
+	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
+		return;
+
+	if (!cpumask_available(batch->cpumask))
+		return;
+
+	sme_do_dvmsync(batch->cpumask);
+	cpumask_clear(batch->cpumask);
+}
+
+#else
+
+static inline void sme_dvmsync(struct mm_struct *mm)
+{
+}
+static inline void sme_dvmsync_add_pending(struct arch_tlbflush_unmap_batch *batch,
+					   struct mm_struct *mm)
+{
+}
+static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch)
+{
+}
+
+#endif /* CONFIG_ARM64_ERRATUM_4193714 */
+
 /*
  * Level-based TLBI operations.
  *
@@ -181,6 +238,48 @@ static inline unsigned long get_trans_granule(void)
 		(__pages >> (5 * (scale) + 1)) - 1;			\
 	})
 
+#define __repeat_tlbi_sync(op, arg...)						\
+do {										\
+	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))	\
+		break;								\
+	__tlbi(op, ##arg);							\
+	dsb(ish);								\
+} while (0)
+
+/*
+ * Complete broadcast TLB maintenance issued by the host which invalidates
+ * stage 1 information in the host's own translation regime.
+ */
+static inline void __tlbi_sync_s1ish(struct mm_struct *mm)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale1is, 0);
+	sme_dvmsync(mm);
+}
+
+static inline void __tlbi_sync_s1ish_batch(struct arch_tlbflush_unmap_batch *batch)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale1is, 0);
+	sme_dvmsync_batch(batch);
+}
+
+static inline void __tlbi_sync_s1ish_kernel(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale1is, 0);
+}
+
+/*
+ * Complete broadcast TLB maintenance issued by hyp code which invalidates
+ * stage 1 translation information in any translation regime.
+ */
+static inline void __tlbi_sync_s1ish_hyp(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale2is, 0);
+}
+
 /*
  *	TLB Invalidation
  *	================
@@ -266,7 +365,7 @@ static inline void flush_tlb_all(void)
 {
 	dsb(ishst);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_kernel();
 	isb();
 }
 
@@ -278,7 +377,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	asid = __TLBI_VADDR(0, ASID(mm));
 	__tlbi(aside1is, asid);
 	__tlbi_user(aside1is, asid);
-	dsb(ish);
+	__tlbi_sync_s1ish(mm);
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
@@ -305,20 +404,11 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long uaddr)
 {
 	flush_tlb_page_nosync(vma, uaddr);
-	dsb(ish);
+	__tlbi_sync_s1ish(vma->vm_mm);
 }
 
 static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 {
-	/*
-	 * TLB flush deferral is not required on systems which are affected by
-	 * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
-	 * will have two consecutive TLBI instructions with a dsb(ish) in between
-	 * defeating the purpose (i.e save overall 'dsb ish' cost).
-	 */
-	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
-		return false;
-
 	return true;
 }
 
@@ -334,7 +424,7 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
  */
 static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	dsb(ish);
+	__tlbi_sync_s1ish_batch(batch);
 }
 
 /*
@@ -469,7 +559,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 {
 	__flush_tlb_range_nosync(vma->vm_mm, start, end, stride,
 				 last_level, tlb_level);
-	dsb(ish);
+	__tlbi_sync_s1ish(vma->vm_mm);
 }
 
 static inline void flush_tlb_range(struct vm_area_struct *vma,
@@ -501,7 +591,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 	dsb(ishst);
 	__flush_tlb_range_op(vaale1is, start, pages, stride, 0,
 			     TLBI_TTL_UNKNOWN, false, lpa2_is_enabled());
-	dsb(ish);
+	__tlbi_sync_s1ish_kernel();
 	isb();
 }
 
@@ -515,14 +605,15 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 
 	dsb(ishst);
 	__tlbi(vaae1is, addr);
-	dsb(ish);
+	__tlbi_sync_s1ish_kernel();
 	isb();
 }
 
 static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
 		struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
+	sme_dvmsync_add_pending(batch, mm);
 }
 #endif
 

arch/arm64/kernel/cpu_errata.c

@@ -11,6 +11,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/fpsimd.h>
 #include <asm/kvm_asm.h>
 #include <asm/smp_plat.h>
 
@@ -551,6 +552,23 @@ static const struct midr_range erratum_spec_ssbs_list[] = {
 };
 #endif
 
+#ifdef CONFIG_ARM64_ERRATUM_4193714
+static bool has_sme_dvmsync_erratum(const struct arm64_cpu_capabilities *entry,
+				    int scope)
+{
+	if (!id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1)))
+		return false;
+
+	return is_affected_midr_range(entry, scope);
+}
+
+static void cpu_enable_sme_dvmsync(const struct arm64_cpu_capabilities *__unused)
+{
+	if (this_cpu_has_cap(ARM64_WORKAROUND_4193714))
+		sme_enable_dvmsync();
+}
+#endif
+
 #ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38
 static const struct midr_range erratum_ac03_cpu_38_list[] = {
 	MIDR_ALL_VERSIONS(MIDR_AMPERE1),
@@ -870,6 +888,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_4193714
+	{
+		.desc = "C1-Pro SME DVMSync early acknowledgement",
+		.capability = ARM64_WORKAROUND_4193714,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_sme_dvmsync_erratum,
+		.cpu_enable = cpu_enable_sme_dvmsync,
+		/* C1-Pro r0p0 - r1p2 (the latter only when REVIDR_EL1[0]==0) */
+		.midr_range = MIDR_RANGE(MIDR_C1_PRO, 0, 0, 1, 2),
+		MIDR_FIXED(MIDR_CPU_VAR_REV(1, 2), BIT(0)),
+	},
+#endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	{
 		.desc = "ARM errata 2966298, 3117295",