Merge branch 'for-next/neoverse-n1-stale-instr' into for-next/core

Neoverse-N1 cores with the 'COHERENT_ICACHE' feature may fetch stale
instructions when software depends on prefetch-speculation-protection
instead of explicit synchronization. [0]

The workaround is to trap I-Cache maintenance and issue an
inner-shareable TLBI. The affected cores have a Coherent I-Cache, so the
I-Cache maintenance isn't necessary. The core tells user-space it can
skip it with CTR_EL0.DIC. We also have to trap this register to hide the
bit forcing DIC-aware user-space to perform the maintenance.

To avoid trapping all cache-maintenance, this workaround depends on
a firmware component that only traps I-cache maintenance from EL0 and
performs the workaround.

For user-space, the kernel's work is to trap CTR_EL0 to hide DIC, and
produce a fake IminLine. EL3 traps the now-necessary I-Cache maintenance
and performs the inner-shareable-TLBI that makes everything better.

[0] https://developer.arm.com/docs/sden885747/latest/arm-neoverse-n1-mp050-software-developer-errata-notice

* for-next/neoverse-n1-stale-instr:
  arm64: Silence clang warning on mismatched value/register sizes
  arm64: compat: Workaround Neoverse-N1 #1542419 for compat user-space
  arm64: Fake the IminLine size on systems affected by Neoverse-N1 #1542419
  arm64: errata: Hide CTR_EL0.DIC on systems affected by Neoverse-N1 #1542419

6 files changed, 71 insertions, 3 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3f047afb982c..56647b995a2b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -558,6 +558,22 @@ config ARM64_ERRATUM_1463225
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1542419
+	bool "Neoverse-N1: workaround mis-ordering of instruction fetches"
+	default y
+	help
+	  This option adds a workaround for ARM Neoverse-N1 erratum
+	  1542419.
+
+	  Affected Neoverse-N1 cores could execute a stale instruction when
+	  modified by another CPU. The workaround depends on a firmware
+	  counterpart.
+
+	  Workaround the issue by hiding the DIC feature from EL0. This
+	  forces user-space to perform cache maintenance.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 43da6dd29592..806e9dc2a852 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -11,6 +11,7 @@
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
 #define CTR_IMINLINE_SHIFT	0
+#define CTR_IMINLINE_MASK	0xf
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
@@ -18,7 +19,7 @@
 #define CTR_DIC_SHIFT		29
 
 #define CTR_CACHE_MINLINE_MASK	\
-	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+	(0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT)
 
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index ac1dbca3d0cd..1dc3c762fdcb 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -54,7 +54,8 @@
 #define ARM64_WORKAROUND_1463225		44
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
+#define ARM64_WORKAROUND_1542419		47
 
-#define ARM64_NCAPS				47
+#define ARM64_NCAPS				48
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 6c3b10a41bd8..548e980ebb70 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -88,13 +88,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 }
 
 static void
-cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
+cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 {
 	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+	bool enable_uct_trap = false;
 
 	/* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
 	if ((read_cpuid_cachetype() & mask) !=
 	    (arm64_ftr_reg_ctrel0.sys_val & mask))
+		enable_uct_trap = true;
+
+	/* ... or if the system is affected by an erratum */
+	if (cap->capability == ARM64_WORKAROUND_1542419)
+		enable_uct_trap = true;
+
+	if (enable_uct_trap)
 		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
@@ -648,6 +656,18 @@ needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
 	return false;
 }
 
+static bool __maybe_unused
+has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	u32 midr = read_cpuid_id();
+	bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT);
+	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && has_dic;
+}
+
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
 static const struct midr_range arm64_harden_el2_vectors[] = {
@@ -890,6 +910,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_1542419
+	{
+		/* we depend on the firmware portion for correctness */
+		.desc = "ARM erratum 1542419 (kernel portion)",
+		.capability = ARM64_WORKAROUND_1542419,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_neoverse_n1_erratum_1542419,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index f1cb64959427..3c18c2454089 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/compat.h>
+#include <linux/cpufeature.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
@@ -17,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/system_misc.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 
 static long
@@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
+		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+			/*
+			 * The workaround requires an inner-shareable tlbi.
+			 * We pick the reserved-ASID to minimise the impact.
+			 */
+			__tlbi(aside1is, __TLBI_VADDR(0, 0));
+			dsb(ish);
+		}
+
 		ret = __flush_cache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 34739e80211b..4e3e9d9c8151 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -470,6 +470,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		/* Hide DIC so that we can trap the unnecessary maintenance...*/
+		val &= ~BIT(CTR_DIC_SHIFT);
+
+		/* ... and fake IminLine to reduce the number of traps. */
+		val &= ~CTR_IMINLINE_MASK;
+		val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK;
+	}
+
 	pt_regs_write_reg(regs, rt, val);
 
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);