Merge tag 'arm64-spectre-bhb-for-v5.17-2' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 spectre fixes from James Morse:
 "ARM64 Spectre-BHB mitigations:

   - Make EL1 vectors per-cpu

   - Add mitigation sequences to the EL1 and EL2 vectors on vulnerble
     CPUs

   - Implement ARCH_WORKAROUND_3 for KVM guests

   - Report Vulnerable when unprivileged eBPF is enabled"

* tag 'arm64-spectre-bhb-for-v5.17-2' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: proton-pack: Include unprivileged eBPF status in Spectre v2 mitigation reporting
  arm64: Use the clearbhb instruction in mitigations
  KVM: arm64: Allow SMCCC_ARCH_WORKAROUND_3 to be discovered and migrated
  arm64: Mitigate spectre style branch history side channels
  arm64: proton-pack: Report Spectre-BHB vulnerabilities as part of Spectre-v2
  arm64: Add percpu vectors for EL1
  arm64: entry: Add macro for reading symbol addresses from the trampoline
  arm64: entry: Add vectors that have the bhb mitigation sequences
  arm64: entry: Add non-kpti __bp_harden_el1_vectors for mitigations
  arm64: entry: Allow the trampoline text to occupy multiple pages
  arm64: entry: Make the kpti trampoline's kpti sequence optional
  arm64: entry: Move trampoline macros out of ifdef'd section
  arm64: entry: Don't assume tramp_vectors is the start of the vectors
  arm64: entry: Allow tramp_alias to access symbols after the 4K boundary
  arm64: entry: Move the trampoline data page before the text page
  arm64: entry: Free up another register on kpti's tramp_exit path
  arm64: entry: Make the trampoline cleanup optional
  KVM: arm64: Allow indirect vectors to be used without SPECTRE_V3A
  arm64: spectre: Rename spectre_v4_patch_fw_mitigation_conduit
  arm64: entry.S: Add ventry overflow sanity checks

11 files changed, 189 insertions, 2 deletions

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index e8bd0af0141c..6ebdc0f834a7 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -109,6 +109,13 @@
 	.endm
 
 /*
+ * Clear Branch History instruction
+ */
+	.macro clearbhb
+	hint	#22
+	.endm
+
+/*
  * Speculation barrier
  */
 	.macro	sb
@@ -850,4 +857,50 @@ alternative_endif
 
 #endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */
 
+	.macro __mitigate_spectre_bhb_loop      tmp
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb  spectre_bhb_patch_loop_iter
+	mov	\tmp, #32		// Patched to correct the immediate
+alternative_cb_end
+.Lspectre_bhb_loop\@:
+	b	. + 4
+	subs	\tmp, \tmp, #1
+	b.ne	.Lspectre_bhb_loop\@
+	sb
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	.macro mitigate_spectre_bhb_loop	tmp
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb	spectre_bhb_patch_loop_mitigation_enable
+	b	.L_spectre_bhb_loop_done\@	// Patched to NOP
+alternative_cb_end
+	__mitigate_spectre_bhb_loop	\tmp
+.L_spectre_bhb_loop_done\@:
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	/* Save/restores x0-x3 to the stack */
+	.macro __mitigate_spectre_bhb_fw
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	stp	x0, x1, [sp, #-16]!
+	stp	x2, x3, [sp, #-16]!
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_3
+alternative_cb	smccc_patch_fw_mitigation_conduit
+	nop					// Patched to SMC/HVC #0
+alternative_cb_end
+	ldp	x2, x3, [sp], #16
+	ldp	x0, x1, [sp], #16
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	.macro mitigate_spectre_bhb_clear_insn
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb	spectre_bhb_patch_clearbhb
+	/* Patched to NOP when not supported */
+	clearbhb
+	isb
+alternative_cb_end
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
 #endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index ef6be92b1921..a77b5f49b3a6 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -637,6 +637,35 @@ static inline bool cpu_supports_mixed_endian_el0(void)
 	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
 }
 
+
+static inline bool supports_csv2p3(int scope)
+{
+	u64 pfr0;
+	u8 csv2_val;
+
+	if (scope == SCOPE_LOCAL_CPU)
+		pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
+	else
+		pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	csv2_val = cpuid_feature_extract_unsigned_field(pfr0,
+							ID_AA64PFR0_CSV2_SHIFT);
+	return csv2_val == 3;
+}
+
+static inline bool supports_clearbhb(int scope)
+{
+	u64 isar2;
+
+	if (scope == SCOPE_LOCAL_CPU)
+		isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
+	else
+		isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1);
+
+	return cpuid_feature_extract_unsigned_field(isar2,
+						    ID_AA64ISAR2_CLEARBHB_SHIFT);
+}
+
 const struct cpumask *system_32bit_el0_cpumask(void);
 DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 999b9149f856..bfbf0c4c7c5e 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -73,10 +73,14 @@
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
 #define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
+#define ARM_CPU_PART_NEOVERSE_V1	0xD40
+#define ARM_CPU_PART_CORTEX_A78		0xD41
+#define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
+#define ARM_CPU_PART_CORTEX_A78C	0xD4B
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -117,10 +121,14 @@
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
 #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
+#define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
+#define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
 #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_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)
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 4335800201c9..daff882883f9 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -62,9 +62,11 @@ enum fixed_addresses {
 #endif /* CONFIG_ACPI_APEI_GHES */
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	FIX_ENTRY_TRAMP_TEXT3,
+	FIX_ENTRY_TRAMP_TEXT2,
+	FIX_ENTRY_TRAMP_TEXT1,
 	FIX_ENTRY_TRAMP_DATA,
-	FIX_ENTRY_TRAMP_TEXT,
-#define TRAMP_VALIAS		(__fix_to_virt(FIX_ENTRY_TRAMP_TEXT))
+#define TRAMP_VALIAS		(__fix_to_virt(FIX_ENTRY_TRAMP_TEXT1))
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 	__end_of_permanent_fixed_addresses,
 
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 6b776c8667b2..b02f0c328c8e 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -65,6 +65,7 @@ enum aarch64_insn_hint_cr_op {
 	AARCH64_INSN_HINT_PSB  = 0x11 << 5,
 	AARCH64_INSN_HINT_TSB  = 0x12 << 5,
 	AARCH64_INSN_HINT_CSDB = 0x14 << 5,
+	AARCH64_INSN_HINT_CLEARBHB = 0x16 << 5,
 
 	AARCH64_INSN_HINT_BTI   = 0x20 << 5,
 	AARCH64_INSN_HINT_BTIC  = 0x22 << 5,
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5bc01e62c08a..031e3a2537fc 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -714,6 +714,11 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
 	ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr();
 }
 
+static inline bool kvm_system_needs_idmapped_vectors(void)
+{
+	return cpus_have_const_cap(ARM64_SPECTRE_V3A);
+}
+
 void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
 
 static inline void kvm_arch_hardware_unsetup(void) {}
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 152cb35bf9df..40971ac1303f 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -23,4 +23,9 @@ extern char __mmuoff_data_start[], __mmuoff_data_end[];
 extern char __entry_tramp_text_start[], __entry_tramp_text_end[];
 extern char __relocate_new_kernel_start[], __relocate_new_kernel_end[];
 
+static inline size_t entry_tramp_text_size(void)
+{
+	return __entry_tramp_text_end - __entry_tramp_text_start;
+}
+
 #endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index f62ca39da6c5..86e0cc9b9c68 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -93,5 +93,9 @@ void spectre_v4_enable_task_mitigation(struct task_struct *tsk);
 
 enum mitigation_state arm64_get_meltdown_state(void);
 
+enum mitigation_state arm64_get_spectre_bhb_state(void);
+bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
+u8 spectre_bhb_loop_affected(int scope);
+void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 #endif	/* __ASSEMBLY__ */
 #endif	/* __ASM_SPECTRE_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 898bee0004ae..932d45b17877 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -773,6 +773,7 @@
 #define ID_AA64ISAR1_GPI_IMP_DEF		0x1
 
 /* id_aa64isar2 */
+#define ID_AA64ISAR2_CLEARBHB_SHIFT	28
 #define ID_AA64ISAR2_RPRES_SHIFT	4
 #define ID_AA64ISAR2_WFXT_SHIFT		0
 
@@ -904,6 +905,7 @@
 #endif
 
 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_ECBHB_SHIFT	60
 #define ID_AA64MMFR1_AFP_SHIFT		44
 #define ID_AA64MMFR1_ETS_SHIFT		36
 #define ID_AA64MMFR1_TWED_SHIFT		32
diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h
new file mode 100644
index 000000000000..f64613a96d53
--- /dev/null
+++ b/arch/arm64/include/asm/vectors.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 ARM Ltd.
+ */
+#ifndef __ASM_VECTORS_H
+#define __ASM_VECTORS_H
+
+#include <linux/bug.h>
+#include <linux/percpu.h>
+
+#include <asm/fixmap.h>
+
+extern char vectors[];
+extern char tramp_vectors[];
+extern char __bp_harden_el1_vectors[];
+
+/*
+ * Note: the order of this enum corresponds to two arrays in entry.S:
+ * tramp_vecs and __bp_harden_el1_vectors. By default the canonical
+ * 'full fat' vectors are used directly.
+ */
+enum arm64_bp_harden_el1_vectors {
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	/*
+	 * Perform the BHB loop mitigation, before branching to the canonical
+	 * vectors.
+	 */
+	EL1_VECTOR_BHB_LOOP,
+
+	/*
+	 * Make the SMC call for firmware mitigation, before branching to the
+	 * canonical vectors.
+	 */
+	EL1_VECTOR_BHB_FW,
+
+	/*
+	 * Use the ClearBHB instruction, before branching to the canonical
+	 * vectors.
+	 */
+	EL1_VECTOR_BHB_CLEAR_INSN,
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+
+	/*
+	 * Remap the kernel before branching to the canonical vectors.
+	 */
+	EL1_VECTOR_KPTI,
+};
+
+#ifndef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+#define EL1_VECTOR_BHB_LOOP		-1
+#define EL1_VECTOR_BHB_FW		-1
+#define EL1_VECTOR_BHB_CLEAR_INSN	-1
+#endif /* !CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+
+/* The vectors to use on return from EL0. e.g. to remap the kernel */
+DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector);
+
+#ifndef CONFIG_UNMAP_KERNEL_AT_EL0
+#define TRAMP_VALIAS	0
+#endif
+
+static inline const char *
+arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot)
+{
+	if (arm64_kernel_unmapped_at_el0())
+		return (char *)TRAMP_VALIAS + SZ_2K * slot;
+
+	WARN_ON_ONCE(slot == EL1_VECTOR_KPTI);
+
+	return __bp_harden_el1_vectors + SZ_2K * slot;
+}
+
+#endif /* __ASM_VECTORS_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index b3edde68bc3e..323e251ed37b 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags {
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED	3
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED     	(1U << 4)
 
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3	KVM_REG_ARM_FW_REG(3)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL		0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL		1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED	2
+
 /* SVE registers */
 #define KVM_REG_ARM64_SVE		(0x15 << KVM_REG_ARM_COPROC_SHIFT)