cpufeature.h

/*
 * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#ifndef __ASM_CPUFEATURE_H
#define __ASM_CPUFEATURE_H

#include <asm/cpucaps.h>
#include <asm/fpsimd.h>
#include <asm/hwcap.h>
#include <asm/sigcontext.h>
#include <asm/sysreg.h>

/*
 * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
 * in the kernel and for user space to keep track of which optional features
 * are supported by the current system. So let's map feature 'x' to HWCAP_x.
 * Note that HWCAP_x constants are bit fields so we need to take the log.
 */

#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
#define cpu_feature(x)		ilog2(HWCAP_ ## x)

#ifndef __ASSEMBLY__

#include <linux/bug.h>
#include <linux/jump_label.h>
#include <linux/kernel.h>

/*
 * CPU feature register tracking
 *
 * The safe value of a CPUID feature field is dependent on the implications
 * of the values assigned to it by the architecture. Based on the relationship
 * between the values, the features are classified into 3 types - LOWER_SAFE,
 * HIGHER_SAFE and EXACT.
 *
 * The lowest value of all the CPUs is chosen for LOWER_SAFE and highest
 * for HIGHER_SAFE. It is expected that all CPUs have the same value for
 * a field when EXACT is specified, failing which, the safe value specified
 * in the table is chosen.
 */

enum ftr_type {
	FTR_EXACT,	/* Use a predefined safe value */
	FTR_LOWER_SAFE,	/* Smaller value is safe */
	FTR_HIGHER_SAFE,/* Bigger value is safe */
};

#define FTR_STRICT	true	/* SANITY check strict matching required */
#define FTR_NONSTRICT	false	/* SANITY check ignored */

#define FTR_SIGNED	true	/* Value should be treated as signed */
#define FTR_UNSIGNED	false	/* Value should be treated as unsigned */

#define FTR_VISIBLE	true	/* Feature visible to the user space */
#define FTR_HIDDEN	false	/* Feature is hidden from the user */

#define FTR_VISIBLE_IF_IS_ENABLED(config)		\
	(IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN)

struct arm64_ftr_bits {
	bool		sign;	/* Value is signed ? */
	bool		visible;
	bool		strict;	/* CPU Sanity check: strict matching required ? */
	enum ftr_type	type;
	u8		shift;
	u8		width;
	s64		safe_val; /* safe value for FTR_EXACT features */
};

/*
 * @arm64_ftr_reg - Feature register
 * @strict_mask		Bits which should match across all CPUs for sanity.
 * @sys_val		Safe value across the CPUs (system view)
 */
struct arm64_ftr_reg {
	const char			*name;
	u64				strict_mask;
	u64				user_mask;
	u64				sys_val;
	u64				user_val;
	const struct arm64_ftr_bits	*ftr_bits;
};

extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;

/*
 * CPU capabilities:
 *
 * We use arm64_cpu_capabilities to represent system features, errata work
 * arounds (both used internally by kernel and tracked in cpu_hwcaps) and
 * ELF HWCAPs (which are exposed to user).
 *
 * To support systems with heterogeneous CPUs, we need to make sure that we
 * detect the capabilities correctly on the system and take appropriate
 * measures to ensure there are no incompatibilities.
 *
 * This comment tries to explain how we treat the capabilities.
 * Each capability has the following list of attributes :
 *
 * 1) Scope of Detection : The system detects a given capability by
 *    performing some checks at runtime. This could be, e.g, checking the
 *    value of a field in CPU ID feature register or checking the cpu
 *    model. The capability provides a call back ( @matches() ) to
 *    perform the check. Scope defines how the checks should be performed.
 *    There are two cases:
 *
 *     a) SCOPE_LOCAL_CPU: check all the CPUs and "detect" if at least one
 *        matches. This implies, we have to run the check on all the
 *        booting CPUs, until the system decides that state of the
 *        capability is finalised. (See section 2 below)
 *		Or
 *     b) SCOPE_SYSTEM: check all the CPUs and "detect" if all the CPUs
 *        matches. This implies, we run the check only once, when the
 *        system decides to finalise the state of the capability. If the
 *        capability relies on a field in one of the CPU ID feature
 *        registers, we use the sanitised value of the register from the
 *        CPU feature infrastructure to make the decision.
 *
 *    The process of detection is usually denoted by "update" capability
 *    state in the code.
 *
 * 2) Finalise the state : The kernel should finalise the state of a
 *    capability at some point during its execution and take necessary
 *    actions if any. Usually, this is done, after all the boot-time
 *    enabled CPUs are brought up by the kernel, so that it can make
 *    better decision based on the available set of CPUs. However, there
 *    are some special cases, where the action is taken during the early
 *    boot by the primary boot CPU. (e.g, running the kernel at EL2 with
 *    Virtualisation Host Extensions). The kernel usually disallows any
 *    changes to the state of a capability once it finalises the capability
 *    and takes any action, as it may be impossible to execute the actions
 *    safely. A CPU brought up after a capability is "finalised" is
 *    referred to as "Late CPU" w.r.t the capability. e.g, all secondary
 *    CPUs are treated "late CPUs" for capabilities determined by the boot
 *    CPU.
 *
 * 3) Verification: When a CPU is brought online (e.g, by user or by the
 *    kernel), the kernel should make sure that it is safe to use the CPU,
 *    by verifying that the CPU is compliant with the state of the
 *    capabilities finalised already. This happens via :
 *
 *	secondary_start_kernel()-> check_local_cpu_capabilities()
 *
 *    As explained in (2) above, capabilities could be finalised at
 *    different points in the execution. Each CPU is verified against the
 *    "finalised" capabilities and if there is a conflict, the kernel takes
 *    an action, based on the severity (e.g, a CPU could be prevented from
 *    booting or cause a kernel panic). The CPU is allowed to "affect" the
 *    state of the capability, if it has not been finalised already.
 *    See section 5 for more details on conflicts.
 *
 * 4) Action: As mentioned in (2), the kernel can take an action for each
 *    detected capability, on all CPUs on the system. Appropriate actions
 *    include, turning on an architectural feature, modifying the control
 *    registers (e.g, SCTLR, TCR etc.) or patching the kernel via
 *    alternatives. The kernel patching is batched and performed at later
 *    point. The actions are always initiated only after the capability
 *    is finalised. This is usally denoted by "enabling" the capability.
 *    The actions are initiated as follows :
 *	a) Action is triggered on all online CPUs, after the capability is
 *	finalised, invoked within the stop_machine() context from
 *	enable_cpu_capabilitie().
 *
 *	b) Any late CPU, brought up after (1), the action is triggered via:
 *
 *	  check_local_cpu_capabilities() -> verify_local_cpu_capabilities()
 *
 * 5) Conflicts: Based on the state of the capability on a late CPU vs.
 *    the system state, we could have the following combinations :
 *
 *		x-----------------------------x
 *		| Type  | System   | Late CPU |
 *		|-----------------------------|
 *		|  a    |   y      |    n     |
 *		|-----------------------------|
 *		|  b    |   n      |    y     |
 *		x-----------------------------x
 *
 *     Two separate flag bits are defined to indicate whether each kind of
 *     conflict can be allowed:
 *		ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU - Case(a) is allowed
 *		ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU - Case(b) is allowed
 *
 *     Case (a) is not permitted for a capability that the system requires
 *     all CPUs to have in order for the capability to be enabled. This is
 *     typical for capabilities that represent enhanced functionality.
 *
 *     Case (b) is not permitted for a capability that must be enabled
 *     during boot if any CPU in the system requires it in order to run
 *     safely. This is typical for erratum work arounds that cannot be
 *     enabled after the corresponding capability is finalised.
 *
 *     In some non-typical cases either both (a) and (b), or neither,
 *     should be permitted. This can be described by including neither
 *     or both flags in the capability's type field.
 */


/* Decide how the capability is detected. On a local CPU vs System wide */
#define ARM64_CPUCAP_SCOPE_LOCAL_CPU		((u16)BIT(0))
#define ARM64_CPUCAP_SCOPE_SYSTEM		((u16)BIT(1))
#define ARM64_CPUCAP_SCOPE_MASK			\
	(ARM64_CPUCAP_SCOPE_SYSTEM	|	\
	 ARM64_CPUCAP_SCOPE_LOCAL_CPU)

#define SCOPE_SYSTEM				ARM64_CPUCAP_SCOPE_SYSTEM
#define SCOPE_LOCAL_CPU				ARM64_CPUCAP_SCOPE_LOCAL_CPU
#define SCOPE_ALL				ARM64_CPUCAP_SCOPE_MASK

/*
 * Is it permitted for a late CPU to have this capability when system
 * hasn't already enabled it ?
 */
#define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU	((u16)BIT(4))
/* Is it safe for a late CPU to miss this capability when system has it */
#define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU	((u16)BIT(5))

/*
 * CPU errata workarounds that need to be enabled at boot time if one or
 * more CPUs in the system requires it. When one of these capabilities
 * has been enabled, it is safe to allow any CPU to boot that doesn't
 * require the workaround. However, it is not safe if a "late" CPU
 * requires a workaround and the system hasn't enabled it already.
 */
#define ARM64_CPUCAP_LOCAL_CPU_ERRATUM		\
	(ARM64_CPUCAP_SCOPE_LOCAL_CPU | ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU)
/*
 * CPU feature detected at boot time based on system-wide value of a
 * feature. It is safe for a late CPU to have this feature even though
 * the system hasn't enabled it, although the featuer will not be used
 * by Linux in this case. If the system has enabled this feature already,
 * then every late CPU must have it.
 */
#define ARM64_CPUCAP_SYSTEM_FEATURE	\
	(ARM64_CPUCAP_SCOPE_SYSTEM | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)

struct arm64_cpu_capabilities {
	const char *desc;
	u16 capability;
	u16 type;
	bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
	/*
	 * Take the appropriate actions to enable this capability for this CPU.
	 * For each successfully booted CPU, this method is called for each
	 * globally detected capability.
	 */
	void (*cpu_enable)(const struct arm64_cpu_capabilities *cap);
	union {
		struct {	/* To be used for erratum handling only */
			u32 midr_model;
			u32 midr_range_min, midr_range_max;
			const struct arm64_midr_revidr {
				u32 midr_rv;		/* revision/variant */
				u32 revidr_mask;
			} * const fixed_revs;
		};

		struct {	/* Feature register checking */
			u32 sys_reg;
			u8 field_pos;
			u8 min_field_value;
			u8 hwcap_type;
			bool sign;
			unsigned long hwcap;
		};
	};
};

static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
{
	return cap->type & ARM64_CPUCAP_SCOPE_MASK;
}

static inline bool
cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
{
	return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU);
}

static inline bool
cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap)
{
	return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU);
}

extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
extern struct static_key_false arm64_const_caps_ready;

bool this_cpu_has_cap(unsigned int cap);

static inline bool cpu_have_feature(unsigned int num)
{
	return elf_hwcap & (1UL << num);
}

/* System capability check for constant caps */
static inline bool __cpus_have_const_cap(int num)
{
	if (num >= ARM64_NCAPS)
		return false;
	return static_branch_unlikely(&cpu_hwcap_keys[num]);
}

static inline bool cpus_have_cap(unsigned int num)
{
	if (num >= ARM64_NCAPS)
		return false;
	return test_bit(num, cpu_hwcaps);
}

static inline bool cpus_have_const_cap(int num)
{
	if (static_branch_likely(&arm64_const_caps_ready))
		return __cpus_have_const_cap(num);
	else
		return cpus_have_cap(num);
}

static inline void cpus_set_cap(unsigned int num)
{
	if (num >= ARM64_NCAPS) {
		pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
			num, ARM64_NCAPS);
	} else {
		__set_bit(num, cpu_hwcaps);
	}
}

static inline int __attribute_const__
cpuid_feature_extract_signed_field_width(u64 features, int field, int width)
{
	return (s64)(features << (64 - width - field)) >> (64 - width);
}

static inline int __attribute_const__
cpuid_feature_extract_signed_field(u64 features, int field)
{
	return cpuid_feature_extract_signed_field_width(features, field, 4);
}

static inline unsigned int __attribute_const__
cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width)
{
	return (u64)(features << (64 - width - field)) >> (64 - width);
}

static inline unsigned int __attribute_const__
cpuid_feature_extract_unsigned_field(u64 features, int field)
{
	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
}

static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
{
	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
}

static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg)
{
	return (reg->user_val | (reg->sys_val & reg->user_mask));
}

static inline int __attribute_const__
cpuid_feature_extract_field_width(u64 features, int field, int width, bool sign)
{
	return (sign) ?
		cpuid_feature_extract_signed_field_width(features, field, width) :
		cpuid_feature_extract_unsigned_field_width(features, field, width);
}

static inline int __attribute_const__
cpuid_feature_extract_field(u64 features, int field, bool sign)
{
	return cpuid_feature_extract_field_width(features, field, 4, sign);
}

static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val)
{
	return (s64)cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width, ftrp->sign);
}

static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
{
	return cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_BIGENDEL_SHIFT) == 0x1 ||
		cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_BIGENDEL0_SHIFT) == 0x1;
}

static inline bool id_aa64pfr0_32bit_el0(u64 pfr0)
{
	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL0_SHIFT);

	return val == ID_AA64PFR0_EL0_32BIT_64BIT;
}

static inline bool id_aa64pfr0_sve(u64 pfr0)
{
	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_SVE_SHIFT);

	return val > 0;
}

void __init setup_cpu_features(void);
void check_local_cpu_capabilities(void);


u64 read_sanitised_ftr_reg(u32 id);

static inline bool cpu_supports_mixed_endian_el0(void)
{
	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
}

static inline bool system_supports_32bit_el0(void)
{
	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
}

static inline bool system_supports_mixed_endian_el0(void)
{
	return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1));
}

static inline bool system_supports_fpsimd(void)
{
	return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD);
}

static inline bool system_uses_ttbr0_pan(void)
{
	return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
		!cpus_have_const_cap(ARM64_HAS_PAN);
}

static inline bool system_supports_sve(void)
{
	return IS_ENABLED(CONFIG_ARM64_SVE) &&
		cpus_have_const_cap(ARM64_SVE);
}

/*
 * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE
 * vector length.
 *
 * Use only if SVE is present.
 * This function clobbers the SVE vector length.
 */
static inline u64 read_zcr_features(void)
{
	u64 zcr;
	unsigned int vq_max;

	/*
	 * Set the maximum possible VL, and write zeroes to all other
	 * bits to see if they stick.
	 */
	sve_kernel_enable(NULL);
	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);

	zcr = read_sysreg_s(SYS_ZCR_EL1);
	zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
	vq_max = sve_vq_from_vl(sve_get_vl());
	zcr |= vq_max - 1; /* set LEN field to maximum effective value */

	return zcr;
}

#endif /* __ASSEMBLY__ */

#endif