linux_dsm_epyc7002/arch/arm64/include/asm/cpufeature.h

315 lines
8.3 KiB
C
Raw Normal View History

/*
* 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;
/* scope of capability check */
enum {
SCOPE_SYSTEM,
SCOPE_LOCAL_CPU,
};
struct arm64_cpu_capabilities {
const char *desc;
u16 capability;
int def_scope; /* default scope */
bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
2018-03-26 21:12:28 +07:00
/*
* 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;
};
};
};
extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
arm64/cpufeature: don't use mutex in bringup path Currently, cpus_set_cap() calls static_branch_enable_cpuslocked(), which must take the jump_label mutex. We call cpus_set_cap() in the secondary bringup path, from the idle thread where interrupts are disabled. Taking a mutex in this path "is a NONO" regardless of whether it's contended, and something we must avoid. We didn't spot this until recently, as ___might_sleep() won't warn for this case until all CPUs have been brought up. This patch avoids taking the mutex in the secondary bringup path. The poking of static keys is deferred until enable_cpu_capabilities(), which runs in a suitable context on the boot CPU. To account for the static keys being set later, cpus_have_const_cap() is updated to use another static key to check whether the const cap keys have been initialised, falling back to the caps bitmap until this is the case. This means that users of cpus_have_const_cap() gain should only gain a single additional NOP in the fast path once the const caps are initialised, but should always see the current cap value. The hyp code should never dereference the caps array, since the caps are initialized before we run the module initcall to initialise hyp. A check is added to the hyp init code to document this requirement. This change will sidestep a number of issues when the upcoming hotplug locking rework is merged. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Marc Zyniger <marc.zyngier@arm.com> Reviewed-by: Suzuki Poulose <suzuki.poulose@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Christoffer Dall <christoffer.dall@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Sewior <bigeasy@linutronix.de> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2017-05-16 21:18:05 +07:00
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 */
arm64/cpufeature: don't use mutex in bringup path Currently, cpus_set_cap() calls static_branch_enable_cpuslocked(), which must take the jump_label mutex. We call cpus_set_cap() in the secondary bringup path, from the idle thread where interrupts are disabled. Taking a mutex in this path "is a NONO" regardless of whether it's contended, and something we must avoid. We didn't spot this until recently, as ___might_sleep() won't warn for this case until all CPUs have been brought up. This patch avoids taking the mutex in the secondary bringup path. The poking of static keys is deferred until enable_cpu_capabilities(), which runs in a suitable context on the boot CPU. To account for the static keys being set later, cpus_have_const_cap() is updated to use another static key to check whether the const cap keys have been initialised, falling back to the caps bitmap until this is the case. This means that users of cpus_have_const_cap() gain should only gain a single additional NOP in the fast path once the const caps are initialised, but should always see the current cap value. The hyp code should never dereference the caps array, since the caps are initialized before we run the module initcall to initialise hyp. A check is added to the hyp init code to document this requirement. This change will sidestep a number of issues when the upcoming hotplug locking rework is merged. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Marc Zyniger <marc.zyngier@arm.com> Reviewed-by: Suzuki Poulose <suzuki.poulose@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Christoffer Dall <christoffer.dall@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Sewior <bigeasy@linutronix.de> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2017-05-16 21:18:05 +07:00
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);
}
arm64/cpufeature: don't use mutex in bringup path Currently, cpus_set_cap() calls static_branch_enable_cpuslocked(), which must take the jump_label mutex. We call cpus_set_cap() in the secondary bringup path, from the idle thread where interrupts are disabled. Taking a mutex in this path "is a NONO" regardless of whether it's contended, and something we must avoid. We didn't spot this until recently, as ___might_sleep() won't warn for this case until all CPUs have been brought up. This patch avoids taking the mutex in the secondary bringup path. The poking of static keys is deferred until enable_cpu_capabilities(), which runs in a suitable context on the boot CPU. To account for the static keys being set later, cpus_have_const_cap() is updated to use another static key to check whether the const cap keys have been initialised, falling back to the caps bitmap until this is the case. This means that users of cpus_have_const_cap() gain should only gain a single additional NOP in the fast path once the const caps are initialised, but should always see the current cap value. The hyp code should never dereference the caps array, since the caps are initialized before we run the module initcall to initialise hyp. A check is added to the hyp init code to document this requirement. This change will sidestep a number of issues when the upcoming hotplug locking rework is merged. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Marc Zyniger <marc.zyngier@arm.com> Reviewed-by: Suzuki Poulose <suzuki.poulose@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Christoffer Dall <christoffer.dall@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Sewior <bigeasy@linutronix.de> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2017-05-16 21:18:05 +07:00
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);
arm64: Rearrange CPU errata workaround checks Right now we run through the work around checks on a CPU from __cpuinfo_store_cpu. There are some problems with that: 1) We initialise the system wide CPU feature registers only after the Boot CPU updates its cpuinfo. Now, if a work around depends on the variance of a CPU ID feature (e.g, check for Cache Line size mismatch), we have no way of performing it cleanly for the boot CPU. 2) It is out of place, invoked from __cpuinfo_store_cpu() in cpuinfo.c. It is not an obvious place for that. This patch rearranges the CPU specific capability(aka work around) checks. 1) At the moment we use verify_local_cpu_capabilities() to check if a new CPU has all the system advertised features. Use this for the secondary CPUs to perform the work around check. For that we rename verify_local_cpu_capabilities() => check_local_cpu_capabilities() which: If the system wide capabilities haven't been initialised (i.e, the CPU is activated at the boot), update the system wide detected work arounds. Otherwise (i.e a CPU hotplugged in later) verify that this CPU conforms to the system wide capabilities. 2) Boot CPU updates the work arounds from smp_prepare_boot_cpu() after we have initialised the system wide CPU feature values. Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andre Przywara <andre.przywara@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-09-09 20:07:10 +07:00
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