Merge 56cf5326bd ("arm64: entry: Add macro for reading symbol addresses from the trampoline") into android12-5.10-lts

Steps on the way to 5.10.105 Fixes up merge issues with: arch/arm64/include/asm/cpu.h arch/arm64/kernel/cpufeature.c Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: I4285e73db81b6760e046747779f6aa0b022f7cc8
2022-03-16 15:01:36 +01:00
parent 5c5685cc64 56cf5326bd
commit 9e96a3d6ae
18 changed files with 294 additions and 63 deletions
--- a/Documentation/arm64/cpu-feature-registers.rst
+++ b/Documentation/arm64/cpu-feature-registers.rst
@@ -275,6 +275,23 @@ infrastructure:
     | SVEVer                       | [3-0]   |    y    |
     +------------------------------+---------+---------+

+  8) ID_AA64MMFR1_EL1 - Memory model feature register 1
+
+     +------------------------------+---------+---------+
+     | Name                         |  bits   | visible |
+     +------------------------------+---------+---------+
+     | AFP                          | [47-44] |    y    |
+     +------------------------------+---------+---------+
+
+  9) ID_AA64ISAR2_EL1 - Instruction set attribute register 2
+
+     +------------------------------+---------+---------+
+     | Name                         |  bits   | visible |
+     +------------------------------+---------+---------+
+     | RPRES                        | [7-4]   |    y    |
+     +------------------------------+---------+---------+
+
+
 Appendix I: Example
 -------------------

--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -249,6 +249,14 @@ HWCAP2_ECV

    Functionality implied by ID_AA64MMFR0_EL1.ECV == 0b0001.

+HWCAP2_AFP
+
+    Functionality implied by ID_AA64MFR1_EL1.AFP == 0b0001.
+
+HWCAP2_RPRES
+
+    Functionality implied by ID_AA64ISAR2_EL1.RPRES == 0b0001.
+
 4. Unused AT_HWCAP bits
 -----------------------

--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -801,4 +801,28 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU

 #endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */

+	.macro __mitigate_spectre_bhb_loop      tmp
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	mov	\tmp, #32
+.Lspectre_bhb_loop\@:
+	b	. + 4
+	subs	\tmp, \tmp, #1
+	b.ne	.Lspectre_bhb_loop\@
+	sb
+#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
 #endif	/* __ASM_ASSEMBLER_H */
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -50,6 +50,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64dfr1;
 	u64		reg_id_aa64isar0;
 	u64		reg_id_aa64isar1;
+	u64		reg_id_aa64isar2;
 	u64		reg_id_aa64mmfr0;
 	u64		reg_id_aa64mmfr1;
 	u64		reg_id_aa64mmfr2;
--- 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,

--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -106,6 +106,8 @@
 #define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
 #define KERNEL_HWCAP_MTE		__khwcap2_feature(MTE)
 #define KERNEL_HWCAP_ECV		__khwcap2_feature(ECV)
+#define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
+#define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)

 /*
 * This yields a mask that user programs can use to figure out what
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -22,4 +22,9 @@ extern char __irqentry_text_start[], __irqentry_text_end[];
 extern char __mmuoff_data_start[], __mmuoff_data_end[];
 extern char __entry_tramp_text_start[], __entry_tramp_text_end[];

+static inline size_t entry_tramp_text_size(void)
+{
+	return __entry_tramp_text_end - __entry_tramp_text_start;
+}
+
 #endif /* __ASM_SECTIONS_H */
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -180,6 +180,7 @@

 #define SYS_ID_AA64ISAR0_EL1		sys_reg(3, 0, 0, 6, 0)
 #define SYS_ID_AA64ISAR1_EL1		sys_reg(3, 0, 0, 6, 1)
+#define SYS_ID_AA64ISAR2_EL1		sys_reg(3, 0, 0, 6, 2)

 #define SYS_ID_AA64MMFR0_EL1		sys_reg(3, 0, 0, 7, 0)
 #define SYS_ID_AA64MMFR1_EL1		sys_reg(3, 0, 0, 7, 1)
@@ -753,6 +754,20 @@
 #define ID_AA64ISAR1_GPI_NI			0x0
 #define ID_AA64ISAR1_GPI_IMP_DEF		0x1

+/* id_aa64isar2 */
+#define ID_AA64ISAR2_RPRES_SHIFT	4
+#define ID_AA64ISAR2_WFXT_SHIFT		0
+
+#define ID_AA64ISAR2_RPRES_8BIT		0x0
+#define ID_AA64ISAR2_RPRES_12BIT	0x1
+/*
+ * Value 0x1 has been removed from the architecture, and is
+ * reserved, but has not yet been removed from the ARM ARM
+ * as of ARM DDI 0487G.b.
+ */
+#define ID_AA64ISAR2_WFXT_NI		0x0
+#define ID_AA64ISAR2_WFXT_SUPPORTED	0x2
+
 /* id_aa64pfr0 */
 #define ID_AA64PFR0_CSV3_SHIFT		60
 #define ID_AA64PFR0_CSV2_SHIFT		56
@@ -852,6 +867,7 @@
 #endif

 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_AFP_SHIFT		44
 #define ID_AA64MMFR1_ETS_SHIFT		36
 #define ID_AA64MMFR1_TWED_SHIFT		32
 #define ID_AA64MMFR1_XNX_SHIFT		28
--- a/arch/arm64/include/asm/vectors.h
+++ b/arch/arm64/include/asm/vectors.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 ARM Ltd.
+ */
+#ifndef __ASM_VECTORS_H
+#define __ASM_VECTORS_H
+
+/*
+ * 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,
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+
+	/*
+	 * Remap the kernel before branching to the canonical vectors.
+	 */
+	EL1_VECTOR_KPTI,
+};
+
+#endif /* __ASM_VECTORS_H */
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -76,5 +76,7 @@
 #define HWCAP2_BTI		(1 << 17)
 #define HWCAP2_MTE		(1 << 18)
 #define HWCAP2_ECV		(1 << 19)
+#define HWCAP2_AFP		(1 << 20)
+#define HWCAP2_RPRES		(1 << 21)

 #endif /* _UAPI__ASM_HWCAP_H */
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -226,6 +226,11 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 	ARM64_FTR_END,
 };

+static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_RPRES_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
@@ -326,6 +331,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 };

 static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_AFP_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_ETS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TWED_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_XNX_SHIFT, 4, 0),
@@ -633,6 +639,7 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0),
 	ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1,
 			       &id_aa64isar1_override),
+	ARM64_FTR_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2),

 	/* Op1 = 0, CRn = 0, CRm = 7 */
 	ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0),
@@ -920,6 +927,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64DFR1_EL1, info->reg_id_aa64dfr1);
 	init_cpu_ftr_reg(SYS_ID_AA64ISAR0_EL1, info->reg_id_aa64isar0);
 	init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1);
+	init_cpu_ftr_reg(SYS_ID_AA64ISAR2_EL1, info->reg_id_aa64isar2);
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0);
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1);
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2);
@@ -1135,6 +1143,8 @@ void update_cpu_features(int cpu,
 				      info->reg_id_aa64isar0, boot->reg_id_aa64isar0);
 	taint |= check_update_ftr_reg(SYS_ID_AA64ISAR1_EL1, cpu,
 				      info->reg_id_aa64isar1, boot->reg_id_aa64isar1);
+	taint |= check_update_ftr_reg(SYS_ID_AA64ISAR2_EL1, cpu,
+				      info->reg_id_aa64isar2, boot->reg_id_aa64isar2);

 	/*
 	 * Differing PARange support is fine as long as all peripherals and
@@ -1245,6 +1255,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id)
 	read_sysreg_case(SYS_ID_AA64MMFR2_EL1);
 	read_sysreg_case(SYS_ID_AA64ISAR0_EL1);
 	read_sysreg_case(SYS_ID_AA64ISAR1_EL1);
+	read_sysreg_case(SYS_ID_AA64ISAR2_EL1);

 	read_sysreg_case(SYS_CNTFRQ_EL0);
 	read_sysreg_case(SYS_CTR_EL0);
@@ -2435,6 +2446,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_MTE, CAP_HWCAP, KERNEL_HWCAP_MTE),
 #endif /* CONFIG_ARM64_MTE */
 	HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
+	HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
+	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
 	{},
 };

--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -95,6 +95,8 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_BTI]		= "bti",
 	[KERNEL_HWCAP_MTE]		= "mte",
 	[KERNEL_HWCAP_ECV]		= "ecv",
+	[KERNEL_HWCAP_AFP]		= "afp",
+	[KERNEL_HWCAP_RPRES]		= "rpres",
 };

 #ifdef CONFIG_COMPAT
@@ -391,6 +393,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64dfr1 = read_cpuid(ID_AA64DFR1_EL1);
 	info->reg_id_aa64isar0 = read_cpuid(ID_AA64ISAR0_EL1);
 	info->reg_id_aa64isar1 = read_cpuid(ID_AA64ISAR1_EL1);
+	info->reg_id_aa64isar2 = read_cpuid(ID_AA64ISAR2_EL1);
 	info->reg_id_aa64mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 	info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
 	info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1);
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -62,16 +62,21 @@

 	.macro kernel_ventry, el, label, regsize = 64
 	.align 7
+.Lventry_start\@:
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	.if	\el == 0
-alternative_if ARM64_UNMAP_KERNEL_AT_EL0
+	/*
+	 * This must be the first instruction of the EL0 vector entries. It is
+	 * skipped by the trampoline vectors, to trigger the cleanup.
+	 */
+	b	.Lskip_tramp_vectors_cleanup\@
 	.if	\regsize == 64
 	mrs	x30, tpidrro_el0
 	msr	tpidrro_el0, xzr
 	.else
 	mov	x30, xzr
 	.endif
-alternative_else_nop_endif
+.Lskip_tramp_vectors_cleanup\@:
 	.endif
 #endif

@@ -120,11 +125,15 @@ alternative_else_nop_endif
 	mrs	x0, tpidrro_el0
 #endif
 	b	el\()\el\()_\label
+.org .Lventry_start\@ + 128	// Did we overflow the ventry slot?
 	.endm

-	.macro tramp_alias, dst, sym
+	.macro tramp_alias, dst, sym, tmp
 	mov_q	\dst, TRAMP_VALIAS
-	add	\dst, \dst, #(\sym - .entry.tramp.text)
+	adr_l	\tmp, \sym
+	add	\dst, \dst, \tmp
+	adr_l	\tmp, .entry.tramp.text
+	sub	\dst, \dst, \tmp
 	.endm

 	/*
@@ -141,7 +150,7 @@ alternative_cb_end
 	tbnz	\tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@
 	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
 	mov	w1, #\state
-alternative_cb	spectre_v4_patch_fw_mitigation_conduit
+alternative_cb	smccc_patch_fw_mitigation_conduit
 	nop					// Patched to SMC/HVC #0
 alternative_cb_end
 .L__asm_ssbd_skip\@:
@@ -450,21 +459,26 @@ alternative_else_nop_endif
 	ldp	x24, x25, [sp, #16 * 12]
 	ldp	x26, x27, [sp, #16 * 13]
 	ldp	x28, x29, [sp, #16 * 14]
-	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #S_FRAME_SIZE		// restore sp

 	.if	\el == 0
-alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
+alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
+	ldr	lr, [sp, #S_LR]
+	add	sp, sp, #S_FRAME_SIZE		// restore sp
+	eret
+alternative_else_nop_endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	bne	4f
-	msr	far_el1, x30
-	tramp_alias	x30, tramp_exit_native
+	msr	far_el1, x29
+	tramp_alias	x30, tramp_exit_native, x29
 	br	x30
 4:
-	tramp_alias	x30, tramp_exit_compat
+	tramp_alias	x30, tramp_exit_compat, x29
 	br	x30
 #endif
 	.else
+	ldr	lr, [sp, #S_LR]
+	add	sp, sp, #S_FRAME_SIZE		// restore sp
+
 	/* Ensure any device/NC reads complete */
 	alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412

@@ -861,12 +875,6 @@ SYM_CODE_END(ret_to_user)

 	.popsection				// .entry.text

-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-/*
- * Exception vectors trampoline.
- */
-	.pushsection ".entry.tramp.text", "ax"
-
 	// Move from tramp_pg_dir to swapper_pg_dir
 	.macro tramp_map_kernel, tmp
 	mrs	\tmp, ttbr1_el1
@@ -900,12 +908,41 @@ alternative_else_nop_endif
 	 */
 	.endm

-	.macro tramp_ventry, regsize = 64
+	.macro tramp_data_page	dst
+	adr_l	\dst, .entry.tramp.text
+	sub	\dst, \dst, PAGE_SIZE
+	.endm
+
+	.macro tramp_data_read_var	dst, var
+#ifdef CONFIG_RANDOMIZE_BASE
+	tramp_data_page		\dst
+	add	\dst, \dst, #:lo12:__entry_tramp_data_\var
+	ldr	\dst, [\dst]
+#else
+	ldr	\dst, =\var
+#endif
+	.endm
+
+#define BHB_MITIGATION_NONE	0
+#define BHB_MITIGATION_LOOP	1
+#define BHB_MITIGATION_FW	2
+
+	.macro tramp_ventry, vector_start, regsize, kpti, bhb
 	.align	7
 1:
 	.if	\regsize == 64
 	msr	tpidrro_el0, x30	// Restored in kernel_ventry
 	.endif
+
+	.if	\bhb == BHB_MITIGATION_LOOP
+	/*
+	 * This sequence must appear before the first indirect branch. i.e. the
+	 * ret out of tramp_ventry. It appears here because x30 is free.
+	 */
+	__mitigate_spectre_bhb_loop	x30
+	.endif // \bhb == BHB_MITIGATION_LOOP
+
+	.if	\kpti == 1
 	/*
 	 * Defend against branch aliasing attacks by pushing a dummy
 	 * entry onto the return stack and using a RET instruction to
@@ -915,46 +952,74 @@ alternative_else_nop_endif
 	b	.
 2:
 	tramp_map_kernel	x30
-#ifdef CONFIG_RANDOMIZE_BASE
-	adr	x30, tramp_vectors + PAGE_SIZE
 alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
-	ldr	x30, [x30]
-#else
-	ldr	x30, =vectors
-#endif
+	tramp_data_read_var	x30, vectors
 alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM
-	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
+	prfm	plil1strm, [x30, #(1b - \vector_start)]
 alternative_else_nop_endif
+
 	msr	vbar_el1, x30
-	add	x30, x30, #(1b - tramp_vectors)
 	isb
+	.else
+	ldr	x30, =vectors
+	.endif // \kpti == 1
+
+	.if	\bhb == BHB_MITIGATION_FW
+	/*
+	 * The firmware sequence must appear before the first indirect branch.
+	 * i.e. the ret out of tramp_ventry. But it also needs the stack to be
+	 * mapped to save/restore the registers the SMC clobbers.
+	 */
+	__mitigate_spectre_bhb_fw
+	.endif // \bhb == BHB_MITIGATION_FW
+
+	add	x30, x30, #(1b - \vector_start + 4)
 	ret
+.org 1b + 128	// Did we overflow the ventry slot?
 	.endm

 	.macro tramp_exit, regsize = 64
 	adr	x30, tramp_vectors
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	add	x30, x30, SZ_4K
+#endif
 	msr	vbar_el1, x30
-	tramp_unmap_kernel	x30
+	ldr	lr, [sp, #S_LR]
+	tramp_unmap_kernel	x29
 	.if	\regsize == 64
-	mrs	x30, far_el1
+	mrs	x29, far_el1
 	.endif
+	add	sp, sp, #S_FRAME_SIZE		// restore sp
 	eret
 	sb
 	.endm

-	.align	11
-SYM_CODE_START_NOALIGN(tramp_vectors)
+	.macro	generate_tramp_vector,	kpti, bhb
+.Lvector_start\@:
 	.space	0x400

-	tramp_ventry
-	tramp_ventry
-	tramp_ventry
-	tramp_ventry
+	.rept	4
+	tramp_ventry	.Lvector_start\@, 64, \kpti, \bhb
+	.endr
+	.rept	4
+	tramp_ventry	.Lvector_start\@, 32, \kpti, \bhb
+	.endr
+	.endm

-	tramp_ventry	32
-	tramp_ventry	32
-	tramp_ventry	32
-	tramp_ventry	32
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * Exception vectors trampoline.
+ * The order must match __bp_harden_el1_vectors and the
+ * arm64_bp_harden_el1_vectors enum.
+ */
+	.pushsection ".entry.tramp.text", "ax"
+	.align	11
+SYM_CODE_START_NOALIGN(tramp_vectors)
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_LOOP
+	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_FW
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_NONE
 SYM_CODE_END(tramp_vectors)

 SYM_CODE_START(tramp_exit_native)
@@ -971,12 +1036,53 @@ SYM_CODE_END(tramp_exit_compat)
 	.pushsection ".rodata", "a"
 	.align PAGE_SHIFT
 SYM_DATA_START(__entry_tramp_data_start)
+__entry_tramp_data_vectors:
 	.quad	vectors
+#ifdef CONFIG_ARM_SDE_INTERFACE
+__entry_tramp_data___sdei_asm_handler:
+	.quad	__sdei_asm_handler
+#endif /* CONFIG_ARM_SDE_INTERFACE */
 SYM_DATA_END(__entry_tramp_data_start)
 	.popsection				// .rodata
 #endif /* CONFIG_RANDOMIZE_BASE */
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */

+/*
+ * Exception vectors for spectre mitigations on entry from EL1 when
+ * kpti is not in use.
+ */
+	.macro generate_el1_vector, bhb
+.Lvector_start\@:
+	kernel_ventry	1, sync_invalid			// Synchronous EL1t
+	kernel_ventry	1, irq_invalid			// IRQ EL1t
+	kernel_ventry	1, fiq_invalid			// FIQ EL1t
+	kernel_ventry	1, error_invalid		// Error EL1t
+
+	kernel_ventry	1, sync				// Synchronous EL1h
+	kernel_ventry	1, irq				// IRQ EL1h
+	kernel_ventry	1, fiq_invalid			// FIQ EL1h
+	kernel_ventry	1, error			// Error EL1h
+
+	.rept	4
+	tramp_ventry	.Lvector_start\@, 64, 0, \bhb
+	.endr
+	.rept 4
+	tramp_ventry	.Lvector_start\@, 32, 0, \bhb
+	.endr
+	.endm
+
+/* The order must match tramp_vecs and the arm64_bp_harden_el1_vectors enum. */
+	.pushsection ".entry.text", "ax"
+	.align	11
+SYM_CODE_START(__bp_harden_el1_vectors)
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	generate_el1_vector	bhb=BHB_MITIGATION_LOOP
+	generate_el1_vector	bhb=BHB_MITIGATION_FW
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+SYM_CODE_END(__bp_harden_el1_vectors)
+	.popsection
+
+
 /*
 * Register switch for AArch64. The callee-saved registers need to be saved
 * and restored. On entry:
@@ -1066,13 +1172,7 @@ SYM_CODE_START(__sdei_asm_entry_trampoline)
 	 */
 1:	str	x4, [x1, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]

-#ifdef CONFIG_RANDOMIZE_BASE
-	adr	x4, tramp_vectors + PAGE_SIZE
-	add	x4, x4, #:lo12:__sdei_asm_trampoline_next_handler
-	ldr	x4, [x4]
-#else
-	ldr	x4, =__sdei_asm_handler
-#endif
+	tramp_data_read_var     x4, __sdei_asm_handler
 	br	x4
 SYM_CODE_END(__sdei_asm_entry_trampoline)
 NOKPROBE(__sdei_asm_entry_trampoline)
@@ -1095,13 +1195,6 @@ SYM_CODE_END(__sdei_asm_exit_trampoline)
 NOKPROBE(__sdei_asm_exit_trampoline)
 	.ltorg
 .popsection		// .entry.tramp.text
-#ifdef CONFIG_RANDOMIZE_BASE
-.pushsection ".rodata", "a"
-SYM_DATA_START(__sdei_asm_trampoline_next_handler)
-	.quad	__sdei_asm_handler
-SYM_DATA_END(__sdei_asm_trampoline_next_handler)
-.popsection		// .rodata
-#endif /* CONFIG_RANDOMIZE_BASE */
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */

 /*
@@ -1209,7 +1302,7 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
 alternative_else_nop_endif

 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	tramp_alias	dst=x5, sym=__sdei_asm_exit_trampoline
+	tramp_alias	dst=x5, sym=__sdei_asm_exit_trampoline, tmp=x3
 	br	x5
 #endif
 SYM_CODE_END(__sdei_asm_handler)
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -554,9 +554,9 @@ void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt,
 * Patch a NOP in the Spectre-v4 mitigation code with an SMC/HVC instruction
 * to call into firmware to adjust the mitigation state.
 */
-void __init spectre_v4_patch_fw_mitigation_conduit(struct alt_instr *alt,
-						   __le32 *origptr,
-						   __le32 *updptr, int nr_inst)
+void __init smccc_patch_fw_mitigation_conduit(struct alt_instr *alt,
+					       __le32 *origptr,
+					       __le32 *updptr, int nr_inst)
 {
 	u32 insn;

--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -330,7 +330,7 @@ ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
 	<= SZ_4K, "Hibernate exit text too big or misaligned")
 #endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE,
+ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE,
 	"Entry trampoline text too big")
 #endif
 #ifdef CONFIG_KVM
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1447,7 +1447,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	/* CRm=6 */
 	ID_SANITISED(ID_AA64ISAR0_EL1),
 	ID_SANITISED(ID_AA64ISAR1_EL1),
-	ID_UNALLOCATED(6,2),
+	ID_SANITISED(ID_AA64ISAR2_EL1),
 	ID_UNALLOCATED(6,3),
 	ID_UNALLOCATED(6,4),
 	ID_UNALLOCATED(6,5),
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -593,6 +593,8 @@ early_param("rodata", parse_rodata);
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static int __init map_entry_trampoline(void)
 {
+	int i;
+
 	pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
 	phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);

@@ -601,11 +603,15 @@ static int __init map_entry_trampoline(void)

 	/* Map only the text into the trampoline page table */
 	memset(tramp_pg_dir, 0, PGD_SIZE);
-	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
-			     prot, __pgd_pgtable_alloc, 0);
+	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
+			     entry_tramp_text_size(), prot,
+			     __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS);

 	/* Map both the text and data into the kernel page table */
-	__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+	for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++)
+		__set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i,
+			     pa_start + i * PAGE_SIZE, prot);
+
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern char __entry_tramp_data_start[];

--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -87,6 +87,11 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 0x7fff)

+#define ARM_SMCCC_ARCH_WORKAROUND_3					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 0x3fff)
+
 #define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED	1

 /* Paravirtualised time calls (defined by ARM DEN0057A) */