arm64: Add support for SB barrier and patch in over DSB; ISB sequences

We currently use a DSB; ISB sequence to inhibit speculation in set_fs().
Whilst this works for current CPUs, future CPUs may implement a new SB
barrier instruction which acts as an architected speculation barrier.

On CPUs that support it, patch in an SB; NOP sequence over the DSB; ISB
sequence and advertise the presence of the new instruction to userspace.

Signed-off-by: Will Deacon <will.deacon@arm.com>

8 files changed, 40 insertions, 3 deletions

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 6142402c2eb4..953208267252 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -123,6 +123,19 @@
 	.endm
 
 /*
+ * Speculation barrier
+ */
+	.macro	sb
+alternative_if_not ARM64_HAS_SB
+	dsb	nsh
+	isb
+alternative_else
+	SB_BARRIER_INSN
+	nop
+alternative_endif
+	.endm
+
+/*
  * Sanitise a 64-bit bounded index wrt speculation, returning zero if out
  * of bounds.
  */
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 822a9192c551..f66bb04fdf2d 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -34,6 +34,10 @@
 #define psb_csync()	asm volatile("hint #17" : : : "memory")
 #define csdb()		asm volatile("hint #20" : : : "memory")
 
+#define spec_bar()	asm volatile(ALTERNATIVE("dsb nsh\nisb\n",		\
+						 SB_BARRIER_INSN"nop\n",	\
+						 ARM64_HAS_SB))
+
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
 #define wmb()		dsb(st)
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 6e2d254c09eb..b7f0709a21af 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -54,7 +54,8 @@
 #define ARM64_HAS_CRC32				33
 #define ARM64_SSBS				34
 #define ARM64_WORKAROUND_1188873		35
+#define ARM64_HAS_SB				36
 
-#define ARM64_NCAPS				36
+#define ARM64_NCAPS				37
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 0c909c4a932f..78f15858535e 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -104,6 +104,11 @@
 #define SET_PSTATE_UAO(x)		__emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
 #define SET_PSTATE_SSBS(x)		__emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
 
+#define __SYS_BARRIER_INSN(CRm, op2, Rt) \
+	__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
+
+#define SB_BARRIER_INSN			__SYS_BARRIER_INSN(0, 7, 31)
+
 #define SYS_DC_ISW			sys_insn(1, 0, 7, 6, 2)
 #define SYS_DC_CSW			sys_insn(1, 0, 7, 10, 2)
 #define SYS_DC_CISW			sys_insn(1, 0, 7, 14, 2)
@@ -528,6 +533,7 @@
 #define ID_AA64ISAR0_AES_SHIFT		4
 
 /* id_aa64isar1 */
+#define ID_AA64ISAR1_SB_SHIFT		36
 #define ID_AA64ISAR1_LRCPC_SHIFT	20
 #define ID_AA64ISAR1_FCMA_SHIFT		16
 #define ID_AA64ISAR1_JSCVT_SHIFT	12
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 07c34087bd5e..fad33f5fde47 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -45,8 +45,7 @@ static inline void set_fs(mm_segment_t fs)
 	 * Prevent a mispredicted conditional call to set_fs from forwarding
 	 * the wrong address limit to access_ok under speculation.
 	 */
-	dsb(nsh);
-	isb();
+	spec_bar();
 
 	/* On user-mode return, check fs is correct */
 	set_thread_flag(TIF_FSCHECK);
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 2bcd6e4f3474..7784f7cba16c 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -49,5 +49,6 @@
 #define HWCAP_ILRCPC		(1 << 26)
 #define HWCAP_FLAGM		(1 << 27)
 #define HWCAP_SSBS		(1 << 28)
+#define HWCAP_SB		(1 << 29)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 1aeb62500fd4..e6467e64ee91 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -142,6 +142,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FCMA_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0),
@@ -1398,6 +1399,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.cpu_enable = cpu_enable_cnp,
 	},
 #endif
+	{
+		.desc = "Speculation barrier (SB)",
+		.capability = ARM64_HAS_SB,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.field_pos = ID_AA64ISAR1_SB_SHIFT,
+		.sign = FTR_UNSIGNED,
+		.min_field_value = 1,
+	},
 	{},
 };
 
@@ -1439,6 +1450,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ILRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SB),
 	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index bcc2831399cb..7cb0b08ab0a7 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -82,6 +82,7 @@ static const char *const hwcap_str[] = {
 	"ilrcpc",
 	"flagm",
 	"ssbs",
+	"sb",
 	NULL
 };