arm64: kernel: disable CNP on Carmel

On NVIDIA Carmel cores, CNP behaves differently than it does on standard
ARM cores. On Carmel, if two cores have CNP enabled and share an L2 TLB
entry created by core0 for a specific ASID, a non-shareable TLBI from
core1 may still see the shared entry. On standard ARM cores, that TLBI
will invalidate the shared entry as well.

This causes issues with patchsets that attempt to do local TLBIs based
on cpumasks instead of broadcast TLBIs. Avoid these issues by disabling
CNP support for NVIDIA Carmel cores.

Signed-off-by: Rich Wiley <rwiley@nvidia.com>
Link: https://lore.kernel.org/r/20210324002809.30271-1-rwiley@nvidia.com
[will: Fix pre-existing whitespace issue]
Signed-off-by: Will Deacon <will@kernel.org>

Documentation/arm64/silicon-errata.rst

@@ -130,6 +130,9 @@ stable kernels.
 | Marvell        | ARM-MMU-500     | #582743         | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | Carmel Core     | N/A             | NVIDIA_CARMEL_CNP_ERRATUM   |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+

arch/arm64/Kconfig

@@ -810,6 +810,16 @@ config QCOM_FALKOR_ERRATUM_E1041
 
 	  If unsure, say Y.
 
+config NVIDIA_CARMEL_CNP_ERRATUM
+	bool "NVIDIA Carmel CNP: CNP on Carmel semantically different than ARM cores"
+	default y
+	help
+	  If CNP is enabled on Carmel cores, non-sharable TLBIs on a core will not
+	  invalidate shared TLB entries installed by a different core, as it would
+	  on standard ARM cores.
+
+	  If unsure, say Y.
+
 config SOCIONEXT_SYNQUACER_PREITS
 	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
 	default y

arch/arm64/include/asm/cpucaps.h

@@ -66,7 +66,8 @@
 #define ARM64_WORKAROUND_1508412		58
 #define ARM64_HAS_LDAPR				59
 #define ARM64_KVM_PROTECTED_MODE		60
+#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP	61
 
-#define ARM64_NCAPS				61
+#define ARM64_NCAPS				62
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/kernel/cpu_errata.c

@@ -525,6 +525,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 				  0, 0,
 				  1, 0),
 	},
+#endif
+#ifdef CONFIG_NVIDIA_CARMEL_CNP_ERRATUM
+	{
+		/* NVIDIA Carmel */
+		.desc = "NVIDIA Carmel CNP erratum",
+		.capability = ARM64_WORKAROUND_NVIDIA_CARMEL_CNP,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+	},
 #endif
 	{
 	}

arch/arm64/kernel/cpufeature.c

@@ -1321,7 +1321,10 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
 	 * may share TLB entries with a CPU stuck in the crashed
 	 * kernel.
 	 */
-	 if (is_kdump_kernel())
+	if (is_kdump_kernel())
+		return false;
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP))
 		return false;
 
 	return has_cpuid_feature(entry, scope);