arm64: Mitigate spectre style branch history side channels

commit 558c303 upstream.

Speculation attacks against some high-performance processors can
make use of branch history to influence future speculation.
When taking an exception from user-space, a sequence of branches
or a firmware call overwrites or invalidates the branch history.

The sequence of branches is added to the vectors, and should appear
before the first indirect branch. For systems using KPTI the sequence
is added to the kpti trampoline where it has a free register as the exit
from the trampoline is via a 'ret'. For systems not using KPTI, the same
register tricks are used to free up a register in the vectors.

For the firmware call, arch-workaround-3 clobbers 4 registers, so
there is no choice but to save them to the EL1 stack. This only happens
for entry from EL0, so if we take an exception due to the stack access,
it will not become re-entrant.

For KVM, the existing branch-predictor-hardening vectors are used.
When a spectre version of these vectors is in use, the firmware call
is sufficient to mitigate against Spectre-BHB. For the non-spectre
versions, the sequence of branches is added to the indirect vector.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: <stable@kernel.org> # <v5.17.x 72bb9dc arm64: Add Cortex-X2 CPU part definition
Cc: <stable@kernel.org> # <v5.16.x 2d0d656 arm64: Add Neoverse-N2, Cortex-A710 CPU part definition
Cc: <stable@kernel.org> # <v5.10.x 8a6b88e arm64: Add part number for Arm Cortex-A77
[ modified for stable, moved code to cpu_errata.c removed bitmap of
  mitigations, use kvm template infrastructure ]
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

Author: James Morse

Diff for: arch/arm64/Kconfig

@@ -1139,6 +1139,15 @@ config ARM64_SSBD
 
 	  If unsure, say Y.
 
+config MITIGATE_SPECTRE_BRANCH_HISTORY
+	bool "Mitigate Spectre style attacks against branch history" if EXPERT
+	default y
+	help
+	  Speculation attacks against some high-performance processors can
+	  make use of branch history to influence future speculation.
+	  When taking an exception from user-space, a sequence of branches
+	  or a firmware call overwrites the branch history.
+
 config RODATA_FULL_DEFAULT_ENABLED
 	bool "Apply r/o permissions of VM areas also to their linear aliases"
 	default y

Diff for: arch/arm64/include/asm/assembler.h

@@ -759,7 +759,9 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 
 	.macro __mitigate_spectre_bhb_loop      tmp
 #ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
-	mov	\tmp, #32
+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
@@ -774,7 +776,7 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 	stp	x0, x1, [sp, #-16]!
 	stp	x2, x3, [sp, #-16]!
 	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_3
-alternative_cb	smccc_patch_fw_mitigation_conduit
+alternative_cb	arm64_update_smccc_conduit
 	nop					// Patched to SMC/HVC #0
 alternative_cb_end
 	ldp	x2, x3, [sp], #16

Diff for: arch/arm64/include/asm/cpufeature.h

@@ -508,6 +508,21 @@ 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 system_supports_32bit_el0(void)
 {
 	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
@@ -647,6 +662,9 @@ enum mitigation_state {
 };
 
 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);
 
 extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 

Diff for: arch/arm64/include/asm/cputype.h

@@ -72,9 +72,13 @@
 #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_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
 
@@ -107,9 +111,13 @@
 #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_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 for: arch/arm64/include/asm/sysreg.h

@@ -661,6 +661,7 @@
 #endif
 
 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_ECBHB_SHIFT	60
 #define ID_AA64MMFR1_PAN_SHIFT		20
 #define ID_AA64MMFR1_LOR_SHIFT		16
 #define ID_AA64MMFR1_HPD_SHIFT		12

Diff for: arch/arm64/include/asm/vectors.h

@@ -40,6 +40,11 @@ enum arm64_bp_harden_el1_vectors {
 	EL1_VECTOR_KPTI,
 };
 
+#ifndef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+#define EL1_VECTOR_BHB_LOOP		-1
+#define EL1_VECTOR_BHB_FW		-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);