Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:

 - vDSO build improvements including support for building with BSD.

 - Cleanup to the AMU support code and initialisation rework to support
   cpufreq drivers built as modules.

 - Removal of synthetic frame record from exception stack when entering
   the kernel from EL0.

 - Add support for the TRNG firmware call introduced by Arm spec
   DEN0098.

 - Cleanup and refactoring across the board.

 - Avoid calling arch_get_random_seed_long() from
   add_interrupt_randomness()

 - Perf and PMU updates including support for Cortex-A78 and the v8.3
   SPE extensions.

 - Significant steps along the road to leaving the MMU enabled during
   kexec relocation.

 - Faultaround changes to initialise prefaulted PTEs as 'old' when
   hardware access-flag updates are supported, which drastically
   improves vmscan performance.

 - CPU errata updates for Cortex-A76 (#1463225) and Cortex-A55
   (#1024718)

 - Preparatory work for yielding the vector unit at a finer granularity
   in the crypto code, which in turn will one day allow us to defer
   softirq processing when it is in use.

 - Support for overriding CPU ID register fields on the command-line.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (85 commits)
  drivers/perf: Replace spin_lock_irqsave to spin_lock
  mm: filemap: Fix microblaze build failure with 'mmu_defconfig'
  arm64: Make CPU_BIG_ENDIAN depend on ld.bfd or ld.lld 13.0.0+
  arm64: cpufeatures: Allow disabling of Pointer Auth from the command-line
  arm64: Defer enabling pointer authentication on boot core
  arm64: cpufeatures: Allow disabling of BTI from the command-line
  arm64: Move "nokaslr" over to the early cpufeature infrastructure
  KVM: arm64: Document HVC_VHE_RESTART stub hypercall
  arm64: Make kvm-arm.mode={nvhe, protected} an alias of id_aa64mmfr1.vh=0
  arm64: Add an aliasing facility for the idreg override
  arm64: Honor VHE being disabled from the command-line
  arm64: Allow ID_AA64MMFR1_EL1.VH to be overridden from the command line
  arm64: cpufeature: Add an early command-line cpufeature override facility
  arm64: Extract early FDT mapping from kaslr_early_init()
  arm64: cpufeature: Use IDreg override in __read_sysreg_by_encoding()
  arm64: cpufeature: Add global feature override facility
  arm64: Move SCTLR_EL1 initialisation to EL-agnostic code
  arm64: Simplify init_el2_state to be non-VHE only
  arm64: Move VHE-specific SPE setup to mutate_to_vhe()
  arm64: Drop early setting of MDSCR_EL2.TPMS
  ...

61 files changed, 1268 insertions, 696 deletions

diff --git a/arch/arm/include/asm/archrandom.h b/arch/arm/include/asm/archrandom.h
new file mode 100644
index 000000000000..a8e84ca5c2ee
--- /dev/null
+++ b/arch/arm/include/asm/archrandom.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARCHRANDOM_H
+#define _ASM_ARCHRANDOM_H
+
+static inline bool __init smccc_probe_trng(void)
+{
+	return false;
+}
+
+#endif /* _ASM_ARCHRANDOM_H */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 52bc8f6206b7..1b8cecdc028e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -522,7 +522,7 @@ config ARM64_ERRATUM_1024718
 	help
 	  This option adds a workaround for ARM Cortex-A55 Erratum 1024718.
 
-	  Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect
+	  Affected Cortex-A55 cores (all revisions) could cause incorrect
 	  update of the hardware dirty bit when the DBM/AP bits are updated
 	  without a break-before-make. The workaround is to disable the usage
 	  of hardware DBM locally on the affected cores. CPUs not affected by
@@ -952,8 +952,9 @@ choice
 	  that is selected here.
 
 config CPU_BIG_ENDIAN
-       bool "Build big-endian kernel"
-       help
+	bool "Build big-endian kernel"
+	depends on !LD_IS_LLD || LLD_VERSION >= 130000
+	help
 	  Say Y if you plan on running a kernel with a big-endian userspace.
 
 config CPU_LITTLE_ENDIAN
@@ -1132,6 +1133,10 @@ config CRASH_DUMP
 
 	  For more details see Documentation/admin-guide/kdump/kdump.rst
 
+config TRANS_TABLE
+	def_bool y
+	depends on HIBERNATION
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 90309208bb28..5b84aec31ed3 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -188,10 +188,12 @@ ifeq ($(KBUILD_EXTMOD),)
 # this hack.
 prepare: vdso_prepare
 vdso_prepare: prepare0
-	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h
-	$(if $(CONFIG_COMPAT_VDSO),$(Q)$(MAKE) \
-		$(build)=arch/arm64/kernel/vdso32  \
-		include/generated/vdso32-offsets.h)
+	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso \
+	include/generated/vdso-offsets.h arch/arm64/kernel/vdso/vdso.so
+ifdef CONFIG_COMPAT_VDSO
+	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 \
+	include/generated/vdso32-offsets.h arch/arm64/kernel/vdso32/vdso.so
+endif
 endif
 
 define archhelp
diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h
index ffb1a40d5475..09e43272ccb0 100644
--- a/arch/arm64/include/asm/archrandom.h
+++ b/arch/arm64/include/asm/archrandom.h
@@ -4,10 +4,26 @@
 
 #ifdef CONFIG_ARCH_RANDOM
 
+#include <linux/arm-smccc.h>
 #include <linux/bug.h>
 #include <linux/kernel.h>
 #include <asm/cpufeature.h>
 
+#define ARM_SMCCC_TRNG_MIN_VERSION	0x10000UL
+
+extern bool smccc_trng_available;
+
+static inline bool __init smccc_probe_trng(void)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_VERSION, &res);
+	if ((s32)res.a0 < 0)
+		return false;
+
+	return res.a0 >= ARM_SMCCC_TRNG_MIN_VERSION;
+}
+
 static inline bool __arm64_rndr(unsigned long *v)
 {
 	bool ok;
@@ -38,26 +54,55 @@ static inline bool __must_check arch_get_random_int(unsigned int *v)
 
 static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
+	struct arm_smccc_res res;
+
+	/*
+	 * We prefer the SMCCC call, since its semantics (return actual
+	 * hardware backed entropy) is closer to the idea behind this
+	 * function here than what even the RNDRSS register provides
+	 * (the output of a pseudo RNG freshly seeded by a TRNG).
+	 */
+	if (smccc_trng_available) {
+		arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 64, &res);
+		if ((int)res.a0 >= 0) {
+			*v = res.a3;
+			return true;
+		}
+	}
+
 	/*
 	 * Only support the generic interface after we have detected
 	 * the system wide capability, avoiding complexity with the
 	 * cpufeature code and with potential scheduling between CPUs
 	 * with and without the feature.
 	 */
-	if (!cpus_have_const_cap(ARM64_HAS_RNG))
-		return false;
+	if (cpus_have_const_cap(ARM64_HAS_RNG) && __arm64_rndr(v))
+		return true;
 
-	return __arm64_rndr(v);
+	return false;
 }
 
-
 static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
+	struct arm_smccc_res res;
 	unsigned long val;
-	bool ok = arch_get_random_seed_long(&val);
 
-	*v = val;
-	return ok;
+	if (smccc_trng_available) {
+		arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 32, &res);
+		if ((int)res.a0 >= 0) {
+			*v = res.a3 & GENMASK(31, 0);
+			return true;
+		}
+	}
+
+	if (cpus_have_const_cap(ARM64_HAS_RNG)) {
+		if (__arm64_rndr(&val)) {
+			*v = val;
+			return true;
+		}
+	}
+
+	return false;
 }
 
 static inline bool __init __early_cpu_has_rndr(void)
@@ -72,12 +117,29 @@ arch_get_random_seed_long_early(unsigned long *v)
 {
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (!__early_cpu_has_rndr())
-		return false;
+	if (smccc_trng_available) {
+		struct arm_smccc_res res;
+
+		arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 64, &res);
+		if ((int)res.a0 >= 0) {
+			*v = res.a3;
+			return true;
+		}
+	}
+
+	if (__early_cpu_has_rndr() && __arm64_rndr(v))
+		return true;
 
-	return __arm64_rndr(v);
+	return false;
 }
 #define arch_get_random_seed_long_early arch_get_random_seed_long_early
 
+#else /* !CONFIG_ARCH_RANDOM */
+
+static inline bool __init smccc_probe_trng(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_ARCH_RANDOM */
 #endif /* _ASM_ARCHRANDOM_H */
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index 9990059be106..ccedf548dac9 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -15,10 +15,10 @@
 	.macro	__uaccess_ttbr0_disable, tmp1
 	mrs	\tmp1, ttbr1_el1			// swapper_pg_dir
 	bic	\tmp1, \tmp1, #TTBR_ASID_MASK
-	sub	\tmp1, \tmp1, #PAGE_SIZE		// reserved_pg_dir just before swapper_pg_dir
+	sub	\tmp1, \tmp1, #RESERVED_SWAPPER_OFFSET	// reserved_pg_dir
 	msr	ttbr0_el1, \tmp1			// set reserved TTBR0_EL1
 	isb
-	add	\tmp1, \tmp1, #PAGE_SIZE
+	add	\tmp1, \tmp1, #RESERVED_SWAPPER_OFFSET
 	msr	ttbr1_el1, \tmp1		// set reserved ASID
 	isb
 	.endm
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index bf125c591116..ca31594d3d6c 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -676,6 +676,23 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 	.endm
 
 /*
+ * Set SCTLR_EL1 to the passed value, and invalidate the local icache
+ * in the process. This is called when setting the MMU on.
+ */
+.macro set_sctlr_el1, reg
+	msr	sctlr_el1, \reg
+	isb
+	/*
+	 * Invalidate the local I-cache so that any instructions fetched
+	 * speculatively from the PoC are discarded, since they may have
+	 * been dynamically patched at the PoU.
+	 */
+	ic	iallu
+	dsb	nsh
+	isb
+.endm
+
+/*
  * Check whether to yield to another runnable task from kernel mode NEON code
  * (which runs with preemption disabled).
  *
@@ -745,6 +762,22 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 .Lyield_out_\@ :
 	.endm
 
+	/*
+	 * Check whether preempt-disabled code should yield as soon as it
+	 * is able. This is the case if re-enabling preemption a single
+	 * time results in a preempt count of zero, and the TIF_NEED_RESCHED
+	 * flag is set. (Note that the latter is stored negated in the
+	 * top word of the thread_info::preempt_count field)
+	 */
+	.macro		cond_yield, lbl:req, tmp:req
+#ifdef CONFIG_PREEMPTION
+	get_current_task \tmp
+	ldr		\tmp, [\tmp, #TSK_TI_PREEMPT]
+	sub		\tmp, \tmp, #PREEMPT_DISABLE_OFFSET
+	cbz		\tmp, \lbl
+#endif
+	.endm
+
 /*
  * This macro emits a program property note section identifying
  * architecture features which require special handling, mainly for
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 45217f21f1fe..52e5c1623224 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -30,11 +30,6 @@
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
  *	VIPT I-cache.
  *
- *	flush_cache_mm(mm)
- *
- *		Clean and invalidate all user space cache entries
- *		before a change of page tables.
- *
  *	flush_icache_range(start, end)
  *
  *		Ensure coherency between the I-cache and the D-cache in the
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 9a555809b89c..61177bac49fa 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -63,6 +63,11 @@ struct arm64_ftr_bits {
 	s64		safe_val; /* safe value for FTR_EXACT features */
 };
 
+struct arm64_ftr_override {
+	u64		val;
+	u64		mask;
+};
+
 /*
  * @arm64_ftr_reg - Feature register
  * @strict_mask		Bits which should match across all CPUs for sanity.
@@ -74,6 +79,7 @@ struct arm64_ftr_reg {
 	u64				user_mask;
 	u64				sys_val;
 	u64				user_val;
+	struct arm64_ftr_override	*override;
 	const struct arm64_ftr_bits	*ftr_bits;
 };
 
@@ -600,6 +606,7 @@ void __init setup_cpu_features(void);
 void check_local_cpu_capabilities(void);
 
 u64 read_sanitised_ftr_reg(u32 id);
+u64 __read_sysreg_by_encoding(u32 sys_id);
 
 static inline bool cpu_supports_mixed_endian_el0(void)
 {
@@ -811,6 +818,10 @@ static inline unsigned int get_vmid_bits(u64 mmfr1)
 	return 8;
 }
 
+extern struct arm64_ftr_override id_aa64mmfr1_override;
+extern struct arm64_ftr_override id_aa64pfr1_override;
+extern struct arm64_ftr_override id_aa64isar1_override;
+
 u32 get_kvm_ipa_limit(void);
 void dump_cpu_features(void);
 
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index a7f5a1bbc8ac..d77d358f9395 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -32,46 +32,39 @@
  * to transparently mess with the EL0 bits via CNTKCTL_EL1 access in
  * EL2.
  */
-.macro __init_el2_timers mode
-.ifeqs "\mode", "nvhe"
+.macro __init_el2_timers
 	mrs	x0, cnthctl_el2
 	orr	x0, x0, #3			// Enable EL1 physical timers
 	msr	cnthctl_el2, x0
-.endif
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 .endm
 
-.macro __init_el2_debug mode
+.macro __init_el2_debug
 	mrs	x1, id_aa64dfr0_el1
 	sbfx	x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
 	cmp	x0, #1
-	b.lt	1f				// Skip if no PMU present
+	b.lt	.Lskip_pmu_\@			// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
-1:
+.Lskip_pmu_\@:
 	csel	x2, xzr, x0, lt			// all PMU counters from EL1
 
 	/* Statistical profiling */
 	ubfx	x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
-	cbz	x0, 3f				// Skip if SPE not present
+	cbz	x0, .Lskip_spe_\@		// Skip if SPE not present
 
-.ifeqs "\mode", "nvhe"
 	mrs_s	x0, SYS_PMBIDR_EL1              // If SPE available at EL2,
 	and	x0, x0, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
-	cbnz	x0, 2f				// then permit sampling of physical
+	cbnz	x0, .Lskip_spe_el2_\@		// then permit sampling of physical
 	mov	x0, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
 		      1 << SYS_PMSCR_EL2_PA_SHIFT)
 	msr_s	SYS_PMSCR_EL2, x0		// addresses and physical counter
-2:
+.Lskip_spe_el2_\@:
 	mov	x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
 	orr	x2, x2, x0			// If we don't have VHE, then
 						// use EL1&0 translation.
-.else
-	orr	x2, x2, #MDCR_EL2_TPMS		// For VHE, use EL2 translation
-						// and disable access from EL1
-.endif
 
-3:
+.Lskip_spe_\@:
 	msr	mdcr_el2, x2			// Configure debug traps
 .endm
 
@@ -79,9 +72,9 @@
 .macro __init_el2_lor
 	mrs	x1, id_aa64mmfr1_el1
 	ubfx	x0, x1, #ID_AA64MMFR1_LOR_SHIFT, 4
-	cbz	x0, 1f
+	cbz	x0, .Lskip_lor_\@
 	msr_s	SYS_LORC_EL1, xzr
-1:
+.Lskip_lor_\@:
 .endm
 
 /* Stage-2 translation */
@@ -93,7 +86,7 @@
 .macro __init_el2_gicv3
 	mrs	x0, id_aa64pfr0_el1
 	ubfx	x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4
-	cbz	x0, 1f
+	cbz	x0, .Lskip_gicv3_\@
 
 	mrs_s	x0, SYS_ICC_SRE_EL2
 	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
@@ -103,7 +96,7 @@
 	mrs_s	x0, SYS_ICC_SRE_EL2		// Read SRE back,
 	tbz	x0, #0, 1f			// and check that it sticks
 	msr_s	SYS_ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
-1:
+.Lskip_gicv3_\@:
 .endm
 
 .macro __init_el2_hstr
@@ -128,14 +121,14 @@
 .macro __init_el2_nvhe_sve
 	mrs	x1, id_aa64pfr0_el1
 	ubfx	x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4
-	cbz	x1, 1f
+	cbz	x1, .Lskip_sve_\@
 
 	bic	x0, x0, #CPTR_EL2_TZ		// Also disable SVE traps
 	msr	cptr_el2, x0			// Disable copro. traps to EL2
 	isb
 	mov	x1, #ZCR_ELx_LEN_MASK		// SVE: Enable full vector
 	msr_s	SYS_ZCR_EL2, x1			// length for EL1.
-1:
+.Lskip_sve_\@:
 .endm
 
 .macro __init_el2_nvhe_prepare_eret
@@ -145,37 +138,24 @@
 
 /**
  * Initialize EL2 registers to sane values. This should be called early on all
- * cores that were booted in EL2.
+ * cores that were booted in EL2. Note that everything gets initialised as
+ * if VHE was not evailable. The kernel context will be upgraded to VHE
+ * if possible later on in the boot process
  *
  * Regs: x0, x1 and x2 are clobbered.
  */
-.macro init_el2_state mode
-.ifnes "\mode", "vhe"
-.ifnes "\mode", "nvhe"
-.error "Invalid 'mode' argument"
-.endif
-.endif
-
+.macro init_el2_state
 	__init_el2_sctlr
-	__init_el2_timers \mode
-	__init_el2_debug \mode
+	__init_el2_timers
+	__init_el2_debug
 	__init_el2_lor
 	__init_el2_stage2
 	__init_el2_gicv3
 	__init_el2_hstr
-
-	/*
-	 * When VHE is not in use, early init of EL2 needs to be done here.
-	 * When VHE _is_ in use, EL1 will not be used in the host and
-	 * requires no configuration, and all non-hyp-specific EL2 setup
-	 * will be done via the _EL1 system register aliases in __cpu_setup.
-	 */
-.ifeqs "\mode", "nvhe"
 	__init_el2_nvhe_idregs
 	__init_el2_nvhe_cptr
 	__init_el2_nvhe_sve
 	__init_el2_nvhe_prepare_eret
-.endif
 .endm
 
 #endif /* __ARM_KVM_INIT_H__ */
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index d24b527e8c00..9befcd87e9a8 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -90,18 +90,19 @@ static inline void crash_prepare_suspend(void) {}
 static inline void crash_post_resume(void) {}
 #endif
 
-#ifdef CONFIG_KEXEC_FILE
 #define ARCH_HAS_KIMAGE_ARCH
 
 struct kimage_arch {
 	void *dtb;
-	unsigned long dtb_mem;
+	phys_addr_t dtb_mem;
+	phys_addr_t kern_reloc;
 	/* Core ELF header buffer */
 	void *elf_headers;
 	unsigned long elf_headers_mem;
 	unsigned long elf_headers_sz;
 };
 
+#ifdef CONFIG_KEXEC_FILE
 extern const struct kexec_file_ops kexec_image_ops;
 
 struct kimage;
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 8a33d83ea843..7ccf770c53d9 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -199,12 +199,6 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
-#if defined(GCC_VERSION) && GCC_VERSION < 50000
-#define SYM_CONSTRAINT	"i"
-#else
-#define SYM_CONSTRAINT	"S"
-#endif
-
 /*
  * Obtain the PC-relative address of a kernel symbol
  * s: symbol
@@ -221,7 +215,7 @@ extern u32 __kvm_get_mdcr_el2(void);
 		typeof(s) *addr;					\
 		asm("adrp	%0, %1\n"				\
 		    "add	%0, %0, :lo12:%1\n"			\
-		    : "=r" (addr) : SYM_CONSTRAINT (&s));		\
+		    : "=r" (addr) : "S" (&s));				\
 		addr;							\
 	})
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ff4732785c32..bc09af26c1b8 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/